Rohithqwerty commited on
Commit
3008855
1 Parent(s): 9ce3b25

(Trained with Unsloth)

Browse files
Files changed (1) hide show
  1. config.json +2 -39
config.json CHANGED
@@ -1,40 +1,3 @@
1
  {
2
- "_name_or_path": "unsloth/mistral-7b-v0.3-bnb-4bit",
3
- "architectures": [
4
- "MistralForCausalLM"
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
- "initializer_range": 0.02,
12
- "intermediate_size": 14336,
13
- "max_position_embeddings": 32768,
14
- "model_type": "mistral",
15
- "num_attention_heads": 32,
16
- "num_hidden_layers": 32,
17
- "num_key_value_heads": 8,
18
- "pad_token_id": 770,
19
- "quantization_config": {
20
- "bnb_4bit_compute_dtype": "float16",
21
- "bnb_4bit_quant_type": "nf4",
22
- "bnb_4bit_use_double_quant": true,
23
- "llm_int8_enable_fp32_cpu_offload": false,
24
- "llm_int8_has_fp16_weight": false,
25
- "llm_int8_skip_modules": null,
26
- "llm_int8_threshold": 6.0,
27
- "load_in_4bit": true,
28
- "load_in_8bit": false,
29
- "quant_method": "bitsandbytes"
30
- },
31
- "rms_norm_eps": 1e-05,
32
- "rope_theta": 1000000.0,
33
- "sliding_window": null,
34
- "tie_word_embeddings": false,
35
- "torch_dtype": "float16",
36
- "transformers_version": "4.41.2",
37
- "unsloth_version": "2024.5",
38
- "use_cache": true,
39
- "vocab_size": 32768
40
- }
 
1
  {
2
+ "model_type": "mistral"
3
+ }