JojoPuppet commited on
Commit
ef28fa9
·
1 Parent(s): f335061

Upload model

Browse files
Files changed (2) hide show
  1. config.json +44 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/workspace/out_int8",
3
+ "architectures": [
4
+ "MistralModelForMultipleChoice"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "id2label": {
11
+ "0": "LABEL_0"
12
+ },
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 14336,
15
+ "label2id": {
16
+ "LABEL_0": 0
17
+ },
18
+ "max_position_embeddings": 32768,
19
+ "model_type": "mistral",
20
+ "num_attention_heads": 32,
21
+ "num_hidden_layers": 32,
22
+ "num_key_value_heads": 8,
23
+ "pad_token_id": 2,
24
+ "quantization_config": {
25
+ "bnb_4bit_compute_dtype": "float32",
26
+ "bnb_4bit_quant_type": "fp4",
27
+ "bnb_4bit_use_double_quant": false,
28
+ "llm_int8_enable_fp32_cpu_offload": false,
29
+ "llm_int8_has_fp16_weight": false,
30
+ "llm_int8_skip_modules": null,
31
+ "llm_int8_threshold": 6.0,
32
+ "load_in_4bit": false,
33
+ "load_in_8bit": true,
34
+ "quant_method": "bitsandbytes"
35
+ },
36
+ "rms_norm_eps": 1e-05,
37
+ "rope_theta": 10000.0,
38
+ "sliding_window": 4096,
39
+ "tie_word_embeddings": false,
40
+ "torch_dtype": "float16",
41
+ "transformers_version": "4.34.0",
42
+ "use_cache": true,
43
+ "vocab_size": 32000
44
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe03afd629949f70e07b47a28f8d1c7e33a6a49590a7403f7d51f5ab234acb80
3
+ size 7247686190