voidful commited on
Commit
1dd2fd4
·
verified ·
1 Parent(s): 1437143

Upload Qwen3ForCausalLM

Browse files
config.json CHANGED
@@ -5,7 +5,7 @@
5
  "attention_bias": false,
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 151643,
8
- "dtype": "bfloat16",
9
  "eos_token_id": 151645,
10
  "head_dim": 128,
11
  "hidden_act": "silu",
@@ -56,15 +56,12 @@
56
  "num_attention_heads": 32,
57
  "num_hidden_layers": 36,
58
  "num_key_value_heads": 8,
59
- "pad_token_id": null,
60
  "rms_norm_eps": 1e-06,
61
- "rope_parameters": {
62
- "rope_theta": 5000000,
63
- "rope_type": "default"
64
- },
65
  "sliding_window": null,
66
  "tie_word_embeddings": true,
67
- "transformers_version": "5.3.0",
68
  "use_cache": true,
69
  "use_sliding_window": false,
70
  "vocab_size": 172149
 
5
  "attention_bias": false,
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 151643,
8
+ "dtype": "float32",
9
  "eos_token_id": 151645,
10
  "head_dim": 128,
11
  "hidden_act": "silu",
 
56
  "num_attention_heads": 32,
57
  "num_hidden_layers": 36,
58
  "num_key_value_heads": 8,
 
59
  "rms_norm_eps": 1e-06,
60
+ "rope_scaling": null,
61
+ "rope_theta": 5000000,
 
 
62
  "sliding_window": null,
63
  "tie_word_embeddings": true,
64
+ "transformers_version": "4.57.6",
65
  "use_cache": true,
66
  "use_sliding_window": false,
67
  "vocab_size": 172149
generation_config.json CHANGED
@@ -9,5 +9,5 @@
9
  "temperature": 0.7,
10
  "top_k": 20,
11
  "top_p": 0.8,
12
- "transformers_version": "5.3.0"
13
  }
 
9
  "temperature": 0.7,
10
  "top_k": 20,
11
  "top_p": 0.8,
12
+ "transformers_version": "4.57.6"
13
  }
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c1a1ac3502f12d0e35a95fcadb97a33b30ca38378b11dd0968a2d0a292693dcd
3
  size 4992602008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6da1229e4a11448bb3fdc603b2d368dc0f347efa7739ec210653ce432497cf6a
3
  size 4992602008