Upload config.json with huggingface_hub
Browse files- config.json +36 -0
config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "NousResearch/Yarn-Mistral-7b-128k",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"auto_map": {
|
7 |
+
"AutoConfig": "NousResearch/Yarn-Mistral-7b-128k--configuration_mistral.MistralConfig",
|
8 |
+
"AutoModelForCausalLM": "NousResearch/Yarn-Mistral-7b-128k--modeling_mistral_yarn.MistralForCausalLM"
|
9 |
+
},
|
10 |
+
"bos_token_id": 1,
|
11 |
+
"eos_token_id": 2,
|
12 |
+
"hidden_act": "silu",
|
13 |
+
"hidden_size": 4096,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 14336,
|
16 |
+
"max_position_embeddings": 32768,
|
17 |
+
"max_sequence_length": 131072,
|
18 |
+
"model_type": "mistral",
|
19 |
+
"num_attention_heads": 32,
|
20 |
+
"num_hidden_layers": 32,
|
21 |
+
"num_key_value_heads": 8,
|
22 |
+
"rms_norm_eps": 1e-05,
|
23 |
+
"rope_scaling": {
|
24 |
+
"factor": 16.0,
|
25 |
+
"finetuned": true,
|
26 |
+
"original_max_position_embeddings": 8192,
|
27 |
+
"type": "yarn"
|
28 |
+
},
|
29 |
+
"rope_theta": 10000.0,
|
30 |
+
"sliding_window": 131072,
|
31 |
+
"tie_word_embeddings": false,
|
32 |
+
"torch_dtype": "bfloat16",
|
33 |
+
"transformers_version": "4.35.2",
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 32000
|
36 |
+
}
|