willieseun commited on
Commit
1c7f186
·
verified ·
1 Parent(s): 18fe52c

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +45 -46
config.json CHANGED
@@ -1,46 +1,45 @@
1
- {
2
- "_name_or_path": "mistralai/Mixtral-8x7B-Instruct-v0.1",
3
- "architectures": [
4
- "MixtralForCausalLM"
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": "mixtral",
15
- "num_attention_heads": 32,
16
- "num_experts_per_tok": 2,
17
- "num_hidden_layers": 32,
18
- "num_key_value_heads": 8,
19
- "num_local_experts": 8,
20
- "output_router_logits": false,
21
- "pretraining_tp": 1,
22
- "quantization_config": {
23
- "_load_in_4bit": true,
24
- "_load_in_8bit": false,
25
- "bnb_4bit_compute_dtype": "bfloat16",
26
- "bnb_4bit_quant_storage": "uint8",
27
- "bnb_4bit_quant_type": "nf4",
28
- "bnb_4bit_use_double_quant": true,
29
- "llm_int8_enable_fp32_cpu_offload": false,
30
- "llm_int8_has_fp16_weight": false,
31
- "llm_int8_skip_modules": null,
32
- "llm_int8_threshold": 6.0,
33
- "load_in_4bit": true,
34
- "load_in_8bit": false,
35
- "quant_method": "bitsandbytes"
36
- },
37
- "rms_norm_eps": 1e-05,
38
- "rope_theta": 1000000.0,
39
- "router_aux_loss_coef": 0.02,
40
- "sliding_window": null,
41
- "tie_word_embeddings": false,
42
- "torch_dtype": "float32",
43
- "transformers_version": "4.39.0",
44
- "use_cache": false,
45
- "vocab_size": 32000
46
- }
 
1
+ {
2
+ "architectures": [
3
+ "MixtralForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
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": "mixtral",
14
+ "num_attention_heads": 32,
15
+ "num_experts_per_tok": 2,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "num_local_experts": 8,
19
+ "output_router_logits": false,
20
+ "pretraining_tp": 1,
21
+ "quantization_config": {
22
+ "_load_in_4bit": true,
23
+ "_load_in_8bit": false,
24
+ "bnb_4bit_compute_dtype": "bfloat16",
25
+ "bnb_4bit_quant_storage": "uint8",
26
+ "bnb_4bit_quant_type": "nf4",
27
+ "bnb_4bit_use_double_quant": true,
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": true,
33
+ "load_in_8bit": false,
34
+ "quant_method": "bitsandbytes"
35
+ },
36
+ "rms_norm_eps": 1e-05,
37
+ "rope_theta": 1000000.0,
38
+ "router_aux_loss_coef": 0.02,
39
+ "sliding_window": null,
40
+ "tie_word_embeddings": false,
41
+ "torch_dtype": "float32",
42
+ "transformers_version": "4.39.0",
43
+ "use_cache": false,
44
+ "vocab_size": 32000
45
+ }