nayohan commited on
Commit
9110399
1 Parent(s): 55d9033

Upload of AutoGPTQ quantized model

Browse files
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nayohan/llama3-8b-it-general-trc313k-enko-8k",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128001,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 8192,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 8,
20
+ "pretraining_tp": 1,
21
+ "quantization_config": {
22
+ "bits": 4,
23
+ "damp_percent": 0.01,
24
+ "desc_act": false,
25
+ "group_size": 128,
26
+ "is_marlin_format": false,
27
+ "model_file_base_name": "gptq_model-4bit-128g",
28
+ "model_name_or_path": "instrucTrans-8k-4bit",
29
+ "quant_method": "gptq",
30
+ "static_groups": false,
31
+ "sym": true,
32
+ "true_sequential": true
33
+ },
34
+ "rms_norm_eps": 1e-05,
35
+ "rope_scaling": null,
36
+ "rope_theta": 500000.0,
37
+ "tie_word_embeddings": false,
38
+ "torch_dtype": "float16",
39
+ "transformers_version": "4.38.0",
40
+ "use_cache": true,
41
+ "vocab_size": 128256
42
+ }
gptq_model-4bit-128g.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fe55426a025de87454f66dd6b07440347e9995746b4bf6a0e15ea5739fd67ed
3
+ size 5735720552
quantize_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bits": 4,
3
+ "group_size": 128,
4
+ "damp_percent": 0.01,
5
+ "desc_act": false,
6
+ "static_groups": false,
7
+ "sym": true,
8
+ "true_sequential": true,
9
+ "model_name_or_path": "instrucTrans-8k-4bit",
10
+ "model_file_base_name": "gptq_model-4bit-128g",
11
+ "is_marlin_format": false,
12
+ "quant_method": "gptq"
13
+ }