Upload folder using huggingface_hub
Browse files- config.json +47 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +0 -0
- quantize_config.json +13 -0
config.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/gemma-2-27b-it",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Gemma2ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"attn_logit_softcapping": 50.0,
|
| 9 |
+
"bos_token_id": 2,
|
| 10 |
+
"cache_implementation": "hybrid",
|
| 11 |
+
"eos_token_id": 1,
|
| 12 |
+
"final_logit_softcapping": 30.0,
|
| 13 |
+
"head_dim": 128,
|
| 14 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 15 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 16 |
+
"hidden_size": 4608,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 36864,
|
| 19 |
+
"max_position_embeddings": 8192,
|
| 20 |
+
"model_type": "gemma2",
|
| 21 |
+
"num_attention_heads": 32,
|
| 22 |
+
"num_hidden_layers": 46,
|
| 23 |
+
"num_key_value_heads": 16,
|
| 24 |
+
"pad_token_id": 0,
|
| 25 |
+
"quantization_config": {
|
| 26 |
+
"bits": 4,
|
| 27 |
+
"checkpoint_format": "gptq",
|
| 28 |
+
"damp_percent": 0.1,
|
| 29 |
+
"desc_act": true,
|
| 30 |
+
"group_size": 128,
|
| 31 |
+
"model_file_base_name": null,
|
| 32 |
+
"model_name_or_path": null,
|
| 33 |
+
"quant_method": "gptq",
|
| 34 |
+
"static_groups": false,
|
| 35 |
+
"sym": true,
|
| 36 |
+
"true_sequential": true
|
| 37 |
+
},
|
| 38 |
+
"query_pre_attn_scalar": 144,
|
| 39 |
+
"rms_norm_eps": 1e-06,
|
| 40 |
+
"rope_theta": 10000.0,
|
| 41 |
+
"sliding_window": 4096,
|
| 42 |
+
"sliding_window_size": 4096,
|
| 43 |
+
"torch_dtype": "bfloat16",
|
| 44 |
+
"transformers_version": "4.45.0",
|
| 45 |
+
"use_cache": true,
|
| 46 |
+
"vocab_size": 256000
|
| 47 |
+
}
|
model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a2cc675ba9903aea1ccb21b48ed26252fc7145f5e01f9914acd9515d6c4cefa
|
| 3 |
+
size 5307691392
|
model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0afe65d08ace900e708c19fbaee7e9112d84243fcf034ea427a471ef55a42f4
|
| 3 |
+
size 5300481920
|
model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1151410bcf58ebf889f6a1a553bc51a55a15ff2f529e0ead95b9ce180448390f
|
| 3 |
+
size 5300481888
|
model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:67cc04419f406d2c79c0b39e701d49df95eec25279a8bc560689e867be87ee83
|
| 3 |
+
size 2355621936
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
quantize_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bits": 4,
|
| 3 |
+
"group_size": 128,
|
| 4 |
+
"damp_percent": 0.1,
|
| 5 |
+
"desc_act": true,
|
| 6 |
+
"static_groups": false,
|
| 7 |
+
"sym": true,
|
| 8 |
+
"true_sequential": true,
|
| 9 |
+
"model_name_or_path": null,
|
| 10 |
+
"model_file_base_name": null,
|
| 11 |
+
"quant_method": "gptq",
|
| 12 |
+
"checkpoint_format": "gptq"
|
| 13 |
+
}
|