Upload config.json with huggingface_hub
Browse files- config.json +46 -0
config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "mistral-community/Mixtral-8x22B-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": 6144,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 16384,
|
13 |
+
"max_position_embeddings": 65536,
|
14 |
+
"model_type": "mixtral",
|
15 |
+
"num_attention_heads": 48,
|
16 |
+
"num_experts_per_tok": 2,
|
17 |
+
"num_hidden_layers": 56,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"num_local_experts": 8,
|
20 |
+
"output_router_logits": true,
|
21 |
+
"quantization_config": {
|
22 |
+
"_load_in_4bit": true,
|
23 |
+
"_load_in_8bit": false,
|
24 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
25 |
+
"bnb_4bit_quant_storage": "bfloat16",
|
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,
|
38 |
+
"router_aux_loss_coef": 0.001,
|
39 |
+
"router_jitter_noise": 0.0,
|
40 |
+
"sliding_window": null,
|
41 |
+
"tie_word_embeddings": false,
|
42 |
+
"torch_dtype": "bfloat16",
|
43 |
+
"transformers_version": "4.40.0.dev0",
|
44 |
+
"use_cache": false,
|
45 |
+
"vocab_size": 32000
|
46 |
+
}
|