Upload folder using huggingface_hub
Browse files- config.json +72 -6
- generation_config.json +1 -1
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -5,13 +5,81 @@
|
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"bos_token_id": 1,
|
|
|
|
| 8 |
"eos_token_id": 2,
|
| 9 |
"head_dim": 64,
|
| 10 |
"hidden_act": "silu",
|
| 11 |
"hidden_size": 256,
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
"intermediate_size": 768,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
"max_position_embeddings": 8192,
|
|
|
|
| 15 |
"mlp_bias": false,
|
| 16 |
"model_type": "qwen2",
|
| 17 |
"num_attention_heads": 4,
|
|
@@ -22,16 +90,14 @@
|
|
| 22 |
"rope_scaling": {
|
| 23 |
"factor": 4.0,
|
| 24 |
"original_max_position_embeddings": 2048,
|
|
|
|
| 25 |
"type": "yarn"
|
| 26 |
},
|
| 27 |
"rope_theta": 10000,
|
|
|
|
| 28 |
"tie_word_embeddings": true,
|
| 29 |
-
"
|
| 30 |
-
"transformers_version": "4.51.3",
|
| 31 |
"use_cache": true,
|
| 32 |
-
"vocab_size": 8192,
|
| 33 |
-
|
| 34 |
-
"max_window_layers": 64,
|
| 35 |
"use_sliding_window": false,
|
| 36 |
-
"
|
| 37 |
}
|
|
|
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"bos_token_id": 1,
|
| 8 |
+
"dtype": "float32",
|
| 9 |
"eos_token_id": 2,
|
| 10 |
"head_dim": 64,
|
| 11 |
"hidden_act": "silu",
|
| 12 |
"hidden_size": 256,
|
| 13 |
"initializer_range": 0.02,
|
| 14 |
"intermediate_size": 768,
|
| 15 |
+
"layer_types": [
|
| 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 |
+
"full_attention",
|
| 51 |
+
"full_attention",
|
| 52 |
+
"full_attention",
|
| 53 |
+
"full_attention",
|
| 54 |
+
"full_attention",
|
| 55 |
+
"full_attention",
|
| 56 |
+
"full_attention",
|
| 57 |
+
"full_attention",
|
| 58 |
+
"full_attention",
|
| 59 |
+
"full_attention",
|
| 60 |
+
"full_attention",
|
| 61 |
+
"full_attention",
|
| 62 |
+
"full_attention",
|
| 63 |
+
"full_attention",
|
| 64 |
+
"full_attention",
|
| 65 |
+
"full_attention",
|
| 66 |
+
"full_attention",
|
| 67 |
+
"full_attention",
|
| 68 |
+
"full_attention",
|
| 69 |
+
"full_attention",
|
| 70 |
+
"full_attention",
|
| 71 |
+
"full_attention",
|
| 72 |
+
"full_attention",
|
| 73 |
+
"full_attention",
|
| 74 |
+
"full_attention",
|
| 75 |
+
"full_attention",
|
| 76 |
+
"full_attention",
|
| 77 |
+
"full_attention",
|
| 78 |
+
"full_attention",
|
| 79 |
+
"full_attention"
|
| 80 |
+
],
|
| 81 |
"max_position_embeddings": 8192,
|
| 82 |
+
"max_window_layers": 64,
|
| 83 |
"mlp_bias": false,
|
| 84 |
"model_type": "qwen2",
|
| 85 |
"num_attention_heads": 4,
|
|
|
|
| 90 |
"rope_scaling": {
|
| 91 |
"factor": 4.0,
|
| 92 |
"original_max_position_embeddings": 2048,
|
| 93 |
+
"rope_type": "yarn",
|
| 94 |
"type": "yarn"
|
| 95 |
},
|
| 96 |
"rope_theta": 10000,
|
| 97 |
+
"sliding_window": null,
|
| 98 |
"tie_word_embeddings": true,
|
| 99 |
+
"transformers_version": "4.57.1",
|
|
|
|
| 100 |
"use_cache": true,
|
|
|
|
|
|
|
|
|
|
| 101 |
"use_sliding_window": false,
|
| 102 |
+
"vocab_size": 8192
|
| 103 |
}
|
generation_config.json
CHANGED
|
@@ -2,5 +2,5 @@
|
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 1,
|
| 4 |
"eos_token_id": 2,
|
| 5 |
-
"transformers_version": "4.
|
| 6 |
}
|
|
|
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 1,
|
| 4 |
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.57.1"
|
| 6 |
}
|
model.safetensors
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 sha256:6ab3ac0d21c4fd8fa0ef36ea4e56a858018778600c2ddd695edbe88a99f73297
|
| 3 |
+
size 226905440
|