(Trained with Unsloth)
Browse files- config.json +1 -31
- generation_config.json +1 -1
- tokenizer.json +2 -2
config.json
CHANGED
|
@@ -10,36 +10,6 @@
|
|
| 10 |
"hidden_size": 2048,
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
"intermediate_size": 6144,
|
| 13 |
-
"layer_types": [
|
| 14 |
-
"full_attention",
|
| 15 |
-
"full_attention",
|
| 16 |
-
"full_attention",
|
| 17 |
-
"full_attention",
|
| 18 |
-
"full_attention",
|
| 19 |
-
"full_attention",
|
| 20 |
-
"full_attention",
|
| 21 |
-
"full_attention",
|
| 22 |
-
"full_attention",
|
| 23 |
-
"full_attention",
|
| 24 |
-
"full_attention",
|
| 25 |
-
"full_attention",
|
| 26 |
-
"full_attention",
|
| 27 |
-
"full_attention",
|
| 28 |
-
"full_attention",
|
| 29 |
-
"full_attention",
|
| 30 |
-
"full_attention",
|
| 31 |
-
"full_attention",
|
| 32 |
-
"full_attention",
|
| 33 |
-
"full_attention",
|
| 34 |
-
"full_attention",
|
| 35 |
-
"full_attention",
|
| 36 |
-
"full_attention",
|
| 37 |
-
"full_attention",
|
| 38 |
-
"full_attention",
|
| 39 |
-
"full_attention",
|
| 40 |
-
"full_attention",
|
| 41 |
-
"full_attention"
|
| 42 |
-
],
|
| 43 |
"max_position_embeddings": 40960,
|
| 44 |
"max_window_layers": 28,
|
| 45 |
"model_type": "qwen3",
|
|
@@ -53,7 +23,7 @@
|
|
| 53 |
"sliding_window": null,
|
| 54 |
"tie_word_embeddings": true,
|
| 55 |
"torch_dtype": "float16",
|
| 56 |
-
"transformers_version": "4.
|
| 57 |
"unsloth_fixed": true,
|
| 58 |
"unsloth_version": "2025.7.8",
|
| 59 |
"use_cache": true,
|
|
|
|
| 10 |
"hidden_size": 2048,
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
"intermediate_size": 6144,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
"max_position_embeddings": 40960,
|
| 14 |
"max_window_layers": 28,
|
| 15 |
"model_type": "qwen3",
|
|
|
|
| 23 |
"sliding_window": null,
|
| 24 |
"tie_word_embeddings": true,
|
| 25 |
"torch_dtype": "float16",
|
| 26 |
+
"transformers_version": "4.52.3",
|
| 27 |
"unsloth_fixed": true,
|
| 28 |
"unsloth_version": "2025.7.8",
|
| 29 |
"use_cache": true,
|
generation_config.json
CHANGED
|
@@ -3,5 +3,5 @@
|
|
| 3 |
"eos_token_id": 151645,
|
| 4 |
"max_length": 40960,
|
| 5 |
"pad_token_id": 0,
|
| 6 |
-
"transformers_version": "4.
|
| 7 |
}
|
|
|
|
| 3 |
"eos_token_id": 151645,
|
| 4 |
"max_length": 40960,
|
| 5 |
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.52.3"
|
| 7 |
}
|
tokenizer.json
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:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|