afshinO commited on
Commit
f7d0c1a
1 Parent(s): b67f45a

Upload MistralForSequenceClassification

Browse files
Files changed (2) hide show
  1. config.json +47 -0
  2. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
3
+ "architectures": [
4
+ "MistralForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "id2label": {
12
+ "0": "No",
13
+ "1": "Yes"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 14336,
17
+ "label2id": {
18
+ "No": 0,
19
+ "Yes": 1
20
+ },
21
+ "max_position_embeddings": 32768,
22
+ "model_type": "mistral",
23
+ "num_attention_heads": 32,
24
+ "num_hidden_layers": 32,
25
+ "num_key_value_heads": 8,
26
+ "problem_type": "single_label_classification",
27
+ "quantization_config": {
28
+ "bnb_4bit_compute_dtype": "bfloat16",
29
+ "bnb_4bit_quant_type": "nf4",
30
+ "bnb_4bit_use_double_quant": true,
31
+ "llm_int8_enable_fp32_cpu_offload": false,
32
+ "llm_int8_has_fp16_weight": false,
33
+ "llm_int8_skip_modules": null,
34
+ "llm_int8_threshold": 6.0,
35
+ "load_in_4bit": true,
36
+ "load_in_8bit": false,
37
+ "quant_method": "bitsandbytes"
38
+ },
39
+ "rms_norm_eps": 1e-05,
40
+ "rope_theta": 1000000.0,
41
+ "sliding_window": null,
42
+ "tie_word_embeddings": false,
43
+ "torch_dtype": "bfloat16",
44
+ "transformers_version": "4.37.2",
45
+ "use_cache": true,
46
+ "vocab_size": 32000
47
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1944fdffa051f365999df985d87e66ab4df262b9a96b1bf41f0b7499f6031aff
3
+ size 3863576352