(Trained with Unsloth)
Browse files- config.json +40 -2
- generation_config.json +1 -1
config.json
CHANGED
|
@@ -10,6 +10,44 @@
|
|
| 10 |
"hidden_size": 2560,
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
"intermediate_size": 9728,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
"max_position_embeddings": 40960,
|
| 14 |
"max_window_layers": 36,
|
| 15 |
"model_type": "qwen3",
|
|
@@ -23,9 +61,9 @@
|
|
| 23 |
"sliding_window": null,
|
| 24 |
"tie_word_embeddings": true,
|
| 25 |
"torch_dtype": "float16",
|
| 26 |
-
"transformers_version": "4.
|
| 27 |
"unsloth_fixed": true,
|
| 28 |
-
"unsloth_version": "2025.6.
|
| 29 |
"use_cache": true,
|
| 30 |
"use_sliding_window": false,
|
| 31 |
"vocab_size": 151936
|
|
|
|
| 10 |
"hidden_size": 2560,
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
"intermediate_size": 9728,
|
| 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 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention"
|
| 50 |
+
],
|
| 51 |
"max_position_embeddings": 40960,
|
| 52 |
"max_window_layers": 36,
|
| 53 |
"model_type": "qwen3",
|
|
|
|
| 61 |
"sliding_window": null,
|
| 62 |
"tie_word_embeddings": true,
|
| 63 |
"torch_dtype": "float16",
|
| 64 |
+
"transformers_version": "4.53.0",
|
| 65 |
"unsloth_fixed": true,
|
| 66 |
+
"unsloth_version": "2025.6.12",
|
| 67 |
"use_cache": true,
|
| 68 |
"use_sliding_window": false,
|
| 69 |
"vocab_size": 151936
|
generation_config.json
CHANGED
|
@@ -10,5 +10,5 @@
|
|
| 10 |
"temperature": 0.6,
|
| 11 |
"top_k": 20,
|
| 12 |
"top_p": 0.95,
|
| 13 |
-
"transformers_version": "4.
|
| 14 |
}
|
|
|
|
| 10 |
"temperature": 0.6,
|
| 11 |
"top_k": 20,
|
| 12 |
"top_p": 0.95,
|
| 13 |
+
"transformers_version": "4.53.0"
|
| 14 |
}
|