yfshi123 commited on
Commit
2fdb360
1 Parent(s): 27c3e56

Upload of AutoGPTQ quantized model

Browse files
Files changed (3) hide show
  1. config.json +24 -0
  2. gptq_model-4bit-128g.bin +3 -0
  3. quantize_config.json +10 -0
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./baichuan-vicuna-chinese-7b/",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 11008,
12
+ "max_position_embeddings": 4096,
13
+ "max_sequence_length": 4096,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "pad_token_id": 0,
18
+ "rms_norm_eps": 1e-06,
19
+ "tie_word_embeddings": false,
20
+ "torch_dtype": "float16",
21
+ "transformers_version": "4.30.2",
22
+ "use_cache": true,
23
+ "vocab_size": 64000
24
+ }
gptq_model-4bit-128g.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42088ea276f4234b703347933cf33b496ab453248f7d882777acdb34f268622d
3
+ size 4421302283
quantize_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bits": 4,
3
+ "group_size": 128,
4
+ "damp_percent": 0.01,
5
+ "desc_act": false,
6
+ "sym": true,
7
+ "true_sequential": true,
8
+ "model_name_or_path": null,
9
+ "model_file_base_name": null
10
+ }