Commit
•
b75e2b3
1
Parent(s):
711b09a
Update config.json (#4)
Browse files- Update config.json (57e26a282f8d162f410dcd422f118913300d0649)
Co-authored-by: Richard Eveson <evesonr@users.noreply.huggingface.co>
- config.json +19 -2
config.json
CHANGED
@@ -1,7 +1,24 @@
|
|
1 |
{
|
2 |
-
"
|
|
|
|
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"transformers_version": "4.37.0",
|
6 |
-
"
|
|
|
7 |
}
|
|
|
1 |
{
|
2 |
+
"architectures": [
|
3 |
+
"MistralForCausalLM"
|
4 |
+
],
|
5 |
"bos_token_id": 1,
|
6 |
"eos_token_id": 2,
|
7 |
+
"hidden_act": "silu",
|
8 |
+
"hidden_size": 4096,
|
9 |
+
"initializer_range": 0.02,
|
10 |
+
"intermediate_size": 14336,
|
11 |
+
"max_position_embeddings": 32768,
|
12 |
+
"model_type": "mistral",
|
13 |
+
"num_attention_heads": 32,
|
14 |
+
"num_hidden_layers": 32,
|
15 |
+
"num_key_value_heads": 8,
|
16 |
+
"rms_norm_eps": 1e-05,
|
17 |
+
"rope_theta": 10000.0,
|
18 |
+
"sliding_window": 4096,
|
19 |
+
"tie_word_embeddings": false,
|
20 |
+
"torch_dtype": "bfloat16",
|
21 |
"transformers_version": "4.37.0",
|
22 |
+
"use_cache": true,
|
23 |
+
"vocab_size": 32000
|
24 |
}
|