Upload MistralForCausalLM
Browse files- config.json +3 -2
- generation_config.json +5 -2
- model-00001-of-00003.safetensors +1 -1
- model-00002-of-00003.safetensors +1 -1
- model-00003-of-00003.safetensors +1 -1
config.json
CHANGED
|
@@ -4,6 +4,7 @@
|
|
| 4 |
],
|
| 5 |
"attention_dropout": 0.0,
|
| 6 |
"bos_token_id": 1,
|
|
|
|
| 7 |
"eos_token_id": 2,
|
| 8 |
"head_dim": null,
|
| 9 |
"hidden_act": "silu",
|
|
@@ -15,12 +16,12 @@
|
|
| 15 |
"num_attention_heads": 32,
|
| 16 |
"num_hidden_layers": 32,
|
| 17 |
"num_key_value_heads": 8,
|
|
|
|
| 18 |
"rms_norm_eps": 1e-05,
|
| 19 |
"rope_theta": 1000000.0,
|
| 20 |
"sliding_window": null,
|
| 21 |
"tie_word_embeddings": false,
|
| 22 |
-
"
|
| 23 |
-
"transformers_version": "4.53.2",
|
| 24 |
"use_cache": false,
|
| 25 |
"vocab_size": 32768
|
| 26 |
}
|
|
|
|
| 4 |
],
|
| 5 |
"attention_dropout": 0.0,
|
| 6 |
"bos_token_id": 1,
|
| 7 |
+
"dtype": "bfloat16",
|
| 8 |
"eos_token_id": 2,
|
| 9 |
"head_dim": null,
|
| 10 |
"hidden_act": "silu",
|
|
|
|
| 16 |
"num_attention_heads": 32,
|
| 17 |
"num_hidden_layers": 32,
|
| 18 |
"num_key_value_heads": 8,
|
| 19 |
+
"pad_token_id": 2,
|
| 20 |
"rms_norm_eps": 1e-05,
|
| 21 |
"rope_theta": 1000000.0,
|
| 22 |
"sliding_window": null,
|
| 23 |
"tie_word_embeddings": false,
|
| 24 |
+
"transformers_version": "4.56.0",
|
|
|
|
| 25 |
"use_cache": false,
|
| 26 |
"vocab_size": 32768
|
| 27 |
}
|
generation_config.json
CHANGED
|
@@ -1,6 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 1,
|
| 4 |
-
"eos_token_id":
|
| 5 |
-
|
|
|
|
|
|
|
|
|
|
| 6 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
2
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 2,
|
| 8 |
+
"transformers_version": "4.56.0"
|
| 9 |
}
|
model-00001-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4949453792
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3aec75a05ac88b8d114c4b162b270b49e7a39ff23679f891ee6b0211737d863
|
| 3 |
size 4949453792
|
model-00002-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4999819336
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:16873715ee645734cfbe7ce904c6b8244d1e40496f3f9fd6535f4ba1951fb115
|
| 3 |
size 4999819336
|
model-00003-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4546807800
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:65cff43fa3ad762cfa44666bbe56fc6e5323e8aab8c815ad639a684068846f28
|
| 3 |
size 4546807800
|