(Trained with Unsloth)
Browse files- config.json +3 -2
- generation_config.json +1 -1
- model-00001-of-00004.safetensors +1 -1
- model-00002-of-00004.safetensors +1 -1
- model-00003-of-00004.safetensors +1 -1
config.json
CHANGED
@@ -17,13 +17,14 @@
|
|
17 |
"num_hidden_layers": 28,
|
18 |
"num_key_value_heads": 4,
|
19 |
"pad_token_id": 151665,
|
20 |
-
"rms_norm_eps":
|
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.
|
|
|
27 |
"use_cache": true,
|
28 |
"use_sliding_window": false,
|
29 |
"vocab_size": 152064
|
|
|
17 |
"num_hidden_layers": 28,
|
18 |
"num_key_value_heads": 4,
|
19 |
"pad_token_id": 151665,
|
20 |
+
"rms_norm_eps": 1e-06,
|
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": "4.48.3",
|
27 |
+
"unsloth_version": "2025.1.8",
|
28 |
"use_cache": true,
|
29 |
"use_sliding_window": false,
|
30 |
"vocab_size": 152064
|
generation_config.json
CHANGED
@@ -4,5 +4,5 @@
|
|
4 |
"max_length": 32768,
|
5 |
"max_new_tokens": 2048,
|
6 |
"pad_token_id": 151665,
|
7 |
-
"transformers_version": "4.
|
8 |
}
|
|
|
4 |
"max_length": 32768,
|
5 |
"max_new_tokens": 2048,
|
6 |
"pad_token_id": 151665,
|
7 |
+
"transformers_version": "4.48.3"
|
8 |
}
|
model-00001-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4877660776
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b6fafe5576afc1057528d577020b95e004e5b13dec5e18d9e0cf17ed18d96a8
|
3 |
size 4877660776
|
model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4932751008
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7993c882adcdbb8931ce1a040f2b5ca9f94968c8541544fd21eb39ebd2703d3a
|
3 |
size 4932751008
|
model-00003-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4330865200
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1786a21c254e98ea92cffd6fe52641f30e03f6b7f23db73541be8a354bb1b355
|
3 |
size 4330865200
|