jungiebeen
commited on
Commit
•
56aa6c3
1
Parent(s):
b6772a0
Upload MistralForCausalLM
Browse files- config.json +16 -37
- generation_config.json +1 -4
- model.safetensors +2 -2
config.json
CHANGED
@@ -1,46 +1,25 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "/workspace/pretraining/local-models/training/2024-02-
|
3 |
-
"activation_dropout": 0.0,
|
4 |
-
"activation_function": "gelu",
|
5 |
"architectures": [
|
6 |
-
"
|
7 |
],
|
8 |
-
"
|
9 |
-
"bos_token_id": 0,
|
10 |
-
"classifier_dropout": 0.0,
|
11 |
-
"d_model": 768,
|
12 |
-
"decoder_attention_heads": 12,
|
13 |
-
"decoder_ffn_dim": 3072,
|
14 |
-
"decoder_layerdrop": 0.0,
|
15 |
-
"decoder_layers": 15,
|
16 |
-
"decoder_start_token_id": 2,
|
17 |
-
"dropout": 0.1,
|
18 |
-
"encoder_attention_heads": 12,
|
19 |
-
"encoder_ffn_dim": 3072,
|
20 |
-
"encoder_layerdrop": 0.0,
|
21 |
-
"encoder_layers": 15,
|
22 |
"eos_token_id": 2,
|
23 |
-
"
|
24 |
-
"
|
25 |
-
|
26 |
-
|
27 |
-
"2": "LABEL_2"
|
28 |
-
},
|
29 |
-
"init_std": 0.02,
|
30 |
-
"is_decoder": true,
|
31 |
-
"is_encoder_decoder": false,
|
32 |
-
"label2id": {
|
33 |
-
"LABEL_0": 0,
|
34 |
-
"LABEL_1": 1,
|
35 |
-
"LABEL_2": 2
|
36 |
-
},
|
37 |
"max_position_embeddings": 1024,
|
38 |
-
"model_type": "
|
39 |
-
"
|
40 |
-
"
|
41 |
-
"
|
|
|
|
|
|
|
|
|
42 |
"torch_dtype": "float32",
|
43 |
"transformers_version": "4.34.1",
|
44 |
"use_cache": true,
|
45 |
-
"vocab_size":
|
46 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/workspace/pretraining/local-models/training/2024-02-08_14-47-53",
|
|
|
|
|
3 |
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
],
|
6 |
+
"bos_token_id": 1,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
"eos_token_id": 2,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 864,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 2382,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
"max_position_embeddings": 1024,
|
13 |
+
"model_type": "mistral",
|
14 |
+
"num_attention_heads": 12,
|
15 |
+
"num_hidden_layers": 18,
|
16 |
+
"num_key_value_heads": 2,
|
17 |
+
"rms_norm_eps": 1e-06,
|
18 |
+
"rope_theta": 10000.0,
|
19 |
+
"sliding_window": 4096,
|
20 |
+
"tie_word_embeddings": true,
|
21 |
"torch_dtype": "float32",
|
22 |
"transformers_version": "4.34.1",
|
23 |
"use_cache": true,
|
24 |
+
"vocab_size": 50257
|
25 |
}
|
generation_config.json
CHANGED
@@ -1,9 +1,6 @@
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
-
"bos_token_id":
|
4 |
-
"decoder_start_token_id": 2,
|
5 |
"eos_token_id": 2,
|
6 |
-
"forced_eos_token_id": 2,
|
7 |
-
"pad_token_id": 1,
|
8 |
"transformers_version": "4.34.1"
|
9 |
}
|
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
|
|
4 |
"eos_token_id": 2,
|
|
|
|
|
5 |
"transformers_version": "4.34.1"
|
6 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61992964bb2f88fb9c6fcf5e6a29f32bb494d6600593d75dbb69db1e402a5eb4
|
3 |
+
size 743784040
|