diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..af02981a7232c7c018fa608db30f8ec7f3774de4 --- /dev/null +++ b/config.json @@ -0,0 +1,43 @@ +{ + "_name_or_path": "SeaLLMs/SeaLLMs-v3-7B", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151643, + "hidden_act": "silu", + "hidden_size": 3584, + "initializer_range": 0.02, + "intermediate_size": 18944, + "max_position_embeddings": 131072, + "max_window_layers": 28, + "model_type": "qwen2", + "num_attention_heads": 28, + "num_hidden_layers": 28, + "num_key_value_heads": 4, + "pad_token_id": 151643, + "quantization_config": { + "bnb_4bit_compute_dtype": "float16", + "bnb_4bit_quant_type": "nf4", + "bnb_4bit_use_double_quant": true, + "llm_int8_enable_fp32_cpu_offload": false, + "llm_int8_has_fp16_weight": false, + "llm_int8_skip_modules": null, + "llm_int8_threshold": 6.0, + "load_in_4bit": true, + "load_in_8bit": false, + "quant_method": "bitsandbytes" + }, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.44.2", + "unsloth_version": "2024.8", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 152064 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..03c285af071d7b3f10f9827c25addab69736f4c8 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,8 @@ +{ + "bos_token_id": 151643, + "eos_token_id": 151643, + "max_length": 131072, + "max_new_tokens": 2048, + "pad_token_id": 151643, + "transformers_version": "4.44.2" +} diff --git a/model-00001-of-00002.safetensors b/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a5a38872f49e309cc627254a85cc7b1e061c842a --- /dev/null +++ b/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1da88b0ddacd34781119dea02c58dae6b989ce246b72ed3eff31ca73007ee6ed +size 4457259441 diff --git a/model-00002-of-00002.safetensors b/model-00002-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..358bc8cd1a7a5861baaef59412d6b810afa81e94 --- /dev/null +++ b/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a17b24a36727400faebe507c4efd3192abb501c59965c969027a6676c70902e5 +size 1089994880 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..3988d4eb2af04fe8d9a1582f60a9a84c114df4eb --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,1326 @@ +{ + "metadata": { + "total_size": 5547097905 + }, + "weight_map": { + "lm_head.weight": "model-00002-of-00002.safetensors", + "model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors", + "model.norm.weight": "model-00001-of-00002.safetensors" + } +}