Text Generation
Transformers
Safetensors
English
llama
biology
medical
text-generation-inference
4-bit precision
gptq
TheBloke commited on
Commit
c7f86d7
1 Parent(s): cf4935a

GPTQ model commit

Browse files
config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/workspace/process/adaptllm_medicine-llm/source",
3
+ "architectures": [
4
+ "LLaMAForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "eos_token_id": 1,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 11008,
14
+ "max_position_embeddings": 2048,
15
+ "max_sequence_length": 2048,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 32,
20
+ "pad_token_id": 32000,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-06,
23
+ "rope_scaling": null,
24
+ "rope_theta": 10000.0,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "float16",
27
+ "transformers_version": "4.37.0.dev0",
28
+ "use_cache": true,
29
+ "vocab_size": 32001,
30
+ "quantization_config": {
31
+ "bits": 4,
32
+ "group_size": 128,
33
+ "damp_percent": 0.1,
34
+ "desc_act": true,
35
+ "static_groups": false,
36
+ "sym": true,
37
+ "true_sequential": true,
38
+ "model_name_or_path": null,
39
+ "model_file_base_name": "model",
40
+ "quant_method": "gptq",
41
+ "modules_in_block_to_quantize": [
42
+ [
43
+ "self_attn.k_proj",
44
+ "self_attn.v_proj",
45
+ "self_attn.q_proj"
46
+ ],
47
+ [
48
+ "self_attn.o_proj"
49
+ ],
50
+ [
51
+ "mlp.up_proj",
52
+ "mlp.gate_proj"
53
+ ],
54
+ [
55
+ "mlp.down_proj"
56
+ ]
57
+ ]
58
+ }
59
+ }
generation_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"_from_model_config": true, "bos_token_id": 0, "eos_token_id": 1, "pad_token_id": 0, "transformers_version": "4.27.0.dev0"}
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c392c773bf9ca598661d9b310f9ec79e58e94e82fc1cba5c2c05ed5b822d689f
3
+ size 3896731112
quantize_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
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": "model"
11
+ }
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {}
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa299a0662fc3bf7ada4d816b1cb9fdeb472e9edf6c2ffbc7f00e1b5ff5ff968
3
+ size 499739
tokenizer_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "model_max_length": 2048,
5
+ "tokenizer_class": "LlamaTokenizer",
6
+ "unk_token": "<unk>",
7
+ "pad_token": "<pad>"
8
+ }