Upload Qwen3ForCausalLM
Browse files- config.json +1 -41
- model.safetensors +1 -1
config.json
CHANGED
|
@@ -13,40 +13,6 @@
|
|
| 13 |
"initializer_range": 0.02,
|
| 14 |
"intermediate_size": 32,
|
| 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 |
],
|
|
@@ -57,13 +23,7 @@
|
|
| 57 |
"num_hidden_layers": 2,
|
| 58 |
"num_key_value_heads": 2,
|
| 59 |
"rms_norm_eps": 1e-06,
|
| 60 |
-
"rope_scaling":
|
| 61 |
-
"mrope_section": [
|
| 62 |
-
2
|
| 63 |
-
],
|
| 64 |
-
"rope_type": "default",
|
| 65 |
-
"type": "default"
|
| 66 |
-
},
|
| 67 |
"rope_theta": 1000000,
|
| 68 |
"sliding_window": null,
|
| 69 |
"tie_word_embeddings": false,
|
|
|
|
| 13 |
"initializer_range": 0.02,
|
| 14 |
"intermediate_size": 32,
|
| 15 |
"layer_types": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
"full_attention",
|
| 17 |
"full_attention"
|
| 18 |
],
|
|
|
|
| 23 |
"num_hidden_layers": 2,
|
| 24 |
"num_key_value_heads": 2,
|
| 25 |
"rms_norm_eps": 1e-06,
|
| 26 |
+
"rope_scaling": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
"rope_theta": 1000000,
|
| 28 |
"sliding_window": null,
|
| 29 |
"tie_word_embeddings": false,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4917896
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:835d9e71035ff7e2261b3a8e4d693a86921caa3b07210aee6501bd22d6bc82dc
|
| 3 |
size 4917896
|