perlthoughts
commited on
Commit
•
492c3f8
1
Parent(s):
beecdf5
Upload MistralForCausalLM
Browse files- config.json +3 -3
- generation_config.json +1 -1
- model-00001-of-00003.safetensors +1 -1
- model-00002-of-00003.safetensors +1 -1
- model-00003-of-00003.safetensors +1 -1
config.json
CHANGED
@@ -4,7 +4,7 @@
|
|
4 |
"MistralForCausalLM"
|
5 |
],
|
6 |
"bos_token_id": 1,
|
7 |
-
"eos_token_id":
|
8 |
"hidden_act": "silu",
|
9 |
"hidden_size": 4096,
|
10 |
"initializer_range": 0.02,
|
@@ -15,8 +15,8 @@
|
|
15 |
"num_hidden_layers": 32,
|
16 |
"num_key_value_heads": 8,
|
17 |
"rms_norm_eps": 1e-05,
|
18 |
-
"rope_theta":
|
19 |
-
"sliding_window":
|
20 |
"tie_word_embeddings": false,
|
21 |
"torch_dtype": "float16",
|
22 |
"transformers_version": "4.35.2",
|
|
|
4 |
"MistralForCausalLM"
|
5 |
],
|
6 |
"bos_token_id": 1,
|
7 |
+
"eos_token_id": 2,
|
8 |
"hidden_act": "silu",
|
9 |
"hidden_size": 4096,
|
10 |
"initializer_range": 0.02,
|
|
|
15 |
"num_hidden_layers": 32,
|
16 |
"num_key_value_heads": 8,
|
17 |
"rms_norm_eps": 1e-05,
|
18 |
+
"rope_theta": 10000.0,
|
19 |
+
"sliding_window": 4096,
|
20 |
"tie_word_embeddings": false,
|
21 |
"torch_dtype": "float16",
|
22 |
"transformers_version": "4.35.2",
|
generation_config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
-
"eos_token_id":
|
5 |
"transformers_version": "4.35.2"
|
6 |
}
|
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
"transformers_version": "4.35.2"
|
6 |
}
|
model-00001-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4943178624
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d6e873da6b3c118431d849974fb65bc8f9147bf64a32cdf5f9c9304f66392872
|
3 |
size 4943178624
|
model-00002-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999819232
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9335dc33d285fa85f1c2112cda45194a7542c582e9f65a9785ba8572e0798007
|
3 |
size 4999819232
|
model-00003-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4540532640
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fabc5d68dba15b6d8e4cddd563bc21fa7bd73a785e17e489f30b10bfbf786508
|
3 |
size 4540532640
|