Upload Qwen3ForCausalLM
Browse files- config.json +33 -3
- generation_config.json +1 -1
- model.safetensors +3 -0
config.json
CHANGED
|
@@ -8,9 +8,39 @@
|
|
| 8 |
"eos_token_id": 151645,
|
| 9 |
"head_dim": 128,
|
| 10 |
"hidden_act": "silu",
|
| 11 |
-
"hidden_size":
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
-
"intermediate_size":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
"max_position_embeddings": 40960,
|
| 15 |
"max_window_layers": 28,
|
| 16 |
"model_type": "qwen3",
|
|
@@ -23,7 +53,7 @@
|
|
| 23 |
"sliding_window": null,
|
| 24 |
"tie_word_embeddings": true,
|
| 25 |
"torch_dtype": "float32",
|
| 26 |
-
"transformers_version": "4.
|
| 27 |
"use_cache": true,
|
| 28 |
"use_sliding_window": false,
|
| 29 |
"vocab_size": 151936
|
|
|
|
| 8 |
"eos_token_id": 151645,
|
| 9 |
"head_dim": 128,
|
| 10 |
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_types": [
|
| 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 |
+
],
|
| 44 |
"max_position_embeddings": 40960,
|
| 45 |
"max_window_layers": 28,
|
| 46 |
"model_type": "qwen3",
|
|
|
|
| 53 |
"sliding_window": null,
|
| 54 |
"tie_word_embeddings": true,
|
| 55 |
"torch_dtype": "float32",
|
| 56 |
+
"transformers_version": "4.53.0",
|
| 57 |
"use_cache": true,
|
| 58 |
"use_sliding_window": false,
|
| 59 |
"vocab_size": 151936
|
generation_config.json
CHANGED
|
@@ -9,5 +9,5 @@
|
|
| 9 |
"temperature": 0.6,
|
| 10 |
"top_k": 20,
|
| 11 |
"top_p": 0.95,
|
| 12 |
-
"transformers_version": "4.
|
| 13 |
}
|
|
|
|
| 9 |
"temperature": 0.6,
|
| 10 |
"top_k": 20,
|
| 11 |
"top_p": 0.95,
|
| 12 |
+
"transformers_version": "4.53.0"
|
| 13 |
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0013beb29261fb78ef2f1932eece31c07e1376794000cb11119d923330bcef1a
|
| 3 |
+
size 2384234968
|