Hugging Face's logo

trl-internal-testing
/
tiny-Qwen3ForCausalLM

Text Generation
Transformers
Safetensors
qwen3
trl
conversational
text-generation-inference
Model card Files
xet
Community
qgallouedec HF Staff commited on
Commit
983ce3d
·
verified ·
1 Parent(s): 397c180

Upload Qwen3ForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +42 -6
  2. generation_config.json +3 -1
  3. model.safetensors +2 -2
config.json CHANGED
@@ -4,29 +4,65 @@
4
  ],
5
  "attention_bias": false,
6
  "attention_dropout": 0.0,
 
 
 
7
  "head_dim": 128,
8
  "hidden_act": "silu",
9
  "hidden_size": 8,
10
  "initializer_range": 0.02,
11
  "intermediate_size": 32,
12
  "layer_types": [
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13
  "full_attention",
14
  "full_attention"
15
  ],
16
- "max_position_embeddings": 32768,
17
- "max_window_layers": 28,
18
  "model_type": "qwen3",
19
  "num_attention_heads": 4,
20
  "num_hidden_layers": 2,
21
  "num_key_value_heads": 2,
22
  "rms_norm_eps": 1e-06,
23
  "rope_scaling": null,
24
- "rope_theta": 10000.0,
25
  "sliding_window": null,
26
  "tie_word_embeddings": false,
27
- "torch_dtype": "float32",
28
- "transformers_version": "4.55.0.dev0",
29
  "use_cache": true,
30
  "use_sliding_window": false,
31
- "vocab_size": 151669
32
  }
 
4
  ],
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",
12
  "hidden_size": 8,
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
  ],
53
+ "max_position_embeddings": 40960,
54
+ "max_window_layers": 36,
55
  "model_type": "qwen3",
56
  "num_attention_heads": 4,
57
  "num_hidden_layers": 2,
58
  "num_key_value_heads": 2,
59
  "rms_norm_eps": 1e-06,
60
  "rope_scaling": null,
61
+ "rope_theta": 1000000,
62
  "sliding_window": null,
63
  "tie_word_embeddings": false,
64
+ "transformers_version": "4.57.0.dev0",
 
65
  "use_cache": true,
66
  "use_sliding_window": false,
67
+ "vocab_size": 151936
68
  }
generation_config.json CHANGED
@@ -1,4 +1,6 @@
1
  {
2
  "_from_model_config": true,
3
- "transformers_version": "4.55.0.dev0"
 
 
4
  }
 
1
  {
2
  "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151645,
5
+ "transformers_version": "4.57.0.dev0"
6
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:571ceeaae35f83460a2d8c236db4638bea80a927626078e569c6e59df6ca3fc2
3
- size 9816064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cd44a4baaa372e3d60969e1d2296cb588ff47495d4bc5398351d4d674b98946
3
+ size 9833152