Lamimad commited on
Commit
934c92e
1 Parent(s): dc7b86e

Upload MistralForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +46 -0
  2. generation_config.json +7 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "TheBloke/Mistral-7B-Instruct-v0.1-GPTQ",
3
+ "architectures": [
4
+ "MistralForCausalLM"
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": 14336,
12
+ "max_position_embeddings": 32768,
13
+ "model_type": "mistral",
14
+ "num_attention_heads": 32,
15
+ "num_hidden_layers": 32,
16
+ "num_key_value_heads": 8,
17
+ "pad_token_id": 0,
18
+ "pretraining_tp": 1,
19
+ "quantization_config": {
20
+ "batch_size": 1,
21
+ "bits": 4,
22
+ "block_name_to_quantize": null,
23
+ "damp_percent": 0.1,
24
+ "dataset": null,
25
+ "desc_act": true,
26
+ "disable_exllama": false,
27
+ "group_size": 32,
28
+ "max_input_length": null,
29
+ "model_seqlen": null,
30
+ "module_name_preceding_first_block": null,
31
+ "pad_token_id": null,
32
+ "quant_method": "gptq",
33
+ "sym": true,
34
+ "tokenizer": null,
35
+ "true_sequential": true,
36
+ "use_cuda_fp16": false
37
+ },
38
+ "rms_norm_eps": 1e-05,
39
+ "rope_theta": 10000.0,
40
+ "sliding_window": 4096,
41
+ "tie_word_embeddings": false,
42
+ "torch_dtype": "float16",
43
+ "transformers_version": "4.34.0.dev0",
44
+ "use_cache": true,
45
+ "vocab_size": 32000
46
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.34.0.dev0"
7
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adb6819c8662634b5e6c341901ecee124b27b4caf9cd1e195c15434fabb4ae10
3
+ size 4567872548