gradjitta commited on
Commit
f3df43e
1 Parent(s): 3b31661

Upload config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +37 -0
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/mlops/.cache/huggingface/hub/models--gradjitta--mistral-7b-ultrachat100k-merged/snapshots/2536c69565afd697b76b12046af6c3f4059ba311",
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
+ "quantization_config": {
18
+ "bnb_4bit_compute_dtype": "float16",
19
+ "bnb_4bit_quant_type": "nf4",
20
+ "bnb_4bit_use_double_quant": true,
21
+ "llm_int8_enable_fp32_cpu_offload": false,
22
+ "llm_int8_has_fp16_weight": false,
23
+ "llm_int8_skip_modules": null,
24
+ "llm_int8_threshold": 6.0,
25
+ "load_in_4bit": true,
26
+ "load_in_8bit": false,
27
+ "quant_method": "bitsandbytes"
28
+ },
29
+ "rms_norm_eps": 1e-05,
30
+ "rope_theta": 10000.0,
31
+ "sliding_window": 4096,
32
+ "tie_word_embeddings": false,
33
+ "torch_dtype": "float16",
34
+ "transformers_version": "4.34.1",
35
+ "use_cache": true,
36
+ "vocab_size": 32000
37
+ }