Upload Qwen3ForCausalLM
Browse files- config.json +2 -1
- model.safetensors +1 -1
config.json
CHANGED
|
@@ -17,6 +17,7 @@
|
|
| 17 |
"num_attention_heads": 16,
|
| 18 |
"num_hidden_layers": 28,
|
| 19 |
"num_key_value_heads": 8,
|
|
|
|
| 20 |
"rms_norm_eps": 1e-06,
|
| 21 |
"rope_scaling": null,
|
| 22 |
"rope_theta": 1000000,
|
|
@@ -24,7 +25,7 @@
|
|
| 24 |
"tie_word_embeddings": true,
|
| 25 |
"torch_dtype": "bfloat16",
|
| 26 |
"transformers_version": "4.51.3",
|
| 27 |
-
"use_cache":
|
| 28 |
"use_sliding_window": false,
|
| 29 |
"vocab_size": 151936
|
| 30 |
}
|
|
|
|
| 17 |
"num_attention_heads": 16,
|
| 18 |
"num_hidden_layers": 28,
|
| 19 |
"num_key_value_heads": 8,
|
| 20 |
+
"pretraining_tp": 1,
|
| 21 |
"rms_norm_eps": 1e-06,
|
| 22 |
"rope_scaling": null,
|
| 23 |
"rope_theta": 1000000,
|
|
|
|
| 25 |
"tie_word_embeddings": true,
|
| 26 |
"torch_dtype": "bfloat16",
|
| 27 |
"transformers_version": "4.51.3",
|
| 28 |
+
"use_cache": false,
|
| 29 |
"use_sliding_window": false,
|
| 30 |
"vocab_size": 151936
|
| 31 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1192135096
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0da7934cf92b007dcc28832195f2103b72ed90f52aad7ee8ec024747c78a7ecb
|
| 3 |
size 1192135096
|