(Trained with Unsloth)
Browse files- config.json +2 -29
config.json
CHANGED
@@ -1,30 +1,3 @@
|
|
1 |
{
|
2 |
-
|
3 |
-
|
4 |
-
"MistralForCausalLM"
|
5 |
-
],
|
6 |
-
"attention_dropout": 0.0,
|
7 |
-
"bos_token_id": 1,
|
8 |
-
"eos_token_id": 2,
|
9 |
-
"head_dim": 128,
|
10 |
-
"hidden_act": "silu",
|
11 |
-
"hidden_size": 4096,
|
12 |
-
"initializer_range": 0.02,
|
13 |
-
"intermediate_size": 14336,
|
14 |
-
"max_position_embeddings": 32768,
|
15 |
-
"model_type": "mistral",
|
16 |
-
"num_attention_heads": 32,
|
17 |
-
"num_hidden_layers": 32,
|
18 |
-
"num_key_value_heads": 8,
|
19 |
-
"pad_token_id": 770,
|
20 |
-
"rms_norm_eps": 1e-05,
|
21 |
-
"rope_scaling": null,
|
22 |
-
"rope_theta": 1000000.0,
|
23 |
-
"sliding_window": null,
|
24 |
-
"tie_word_embeddings": false,
|
25 |
-
"torch_dtype": "bfloat16",
|
26 |
-
"transformers_version": "4.46.3",
|
27 |
-
"unsloth_version": "2024.12.4",
|
28 |
-
"use_cache": true,
|
29 |
-
"vocab_size": 32768
|
30 |
-
}
|
|
|
1 |
{
|
2 |
+
"model_type": "mistral"
|
3 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|