Hugging Face's logo

llamafactory
/
tiny-random-qwen3

Text Generation
Safetensors
Chinese
English
qwen3
qwen
llama-factory
conversational
Model card Files
xet
Community
hiyouga commited on
Commit
b2fccec
·
verified ·
1 Parent(s): 1fa6468

Upload Qwen3ForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +34 -30
  2. generation_config.json +5 -12
  3. model.safetensors +2 -2
config.json CHANGED
@@ -1,30 +1,34 @@
1
- {
2
- "architectures": [
3
- "Qwen3ForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 151643,
8
- "eos_token_id": 151645,
9
- "head_dim": 4,
10
- "hidden_act": "silu",
11
- "hidden_size": 16,
12
- "initializer_range": 0.02,
13
- "intermediate_size": 64,
14
- "max_position_embeddings": 32768,
15
- "max_window_layers": 36,
16
- "model_type": "qwen3",
17
- "num_attention_heads": 4,
18
- "num_hidden_layers": 2,
19
- "num_key_value_heads": 4,
20
- "rms_norm_eps": 1e-06,
21
- "rope_scaling": null,
22
- "rope_theta": 5000000,
23
- "sliding_window": null,
24
- "tie_word_embeddings": true,
25
- "torch_dtype": "bfloat16",
26
- "transformers_version": "4.51.0",
27
- "use_cache": true,
28
- "use_sliding_window": false,
29
- "vocab_size": 151936
30
- }
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
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": 4,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 16,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 64,
15
+ "layer_types": [
16
+ "full_attention",
17
+ "full_attention"
18
+ ],
19
+ "max_position_embeddings": 32768,
20
+ "max_window_layers": 36,
21
+ "model_type": "qwen3",
22
+ "num_attention_heads": 4,
23
+ "num_hidden_layers": 2,
24
+ "num_key_value_heads": 4,
25
+ "rms_norm_eps": 1e-06,
26
+ "rope_scaling": null,
27
+ "rope_theta": 5000000,
28
+ "sliding_window": null,
29
+ "tie_word_embeddings": true,
30
+ "transformers_version": "4.57.1",
31
+ "use_cache": true,
32
+ "use_sliding_window": false,
33
+ "vocab_size": 151936
34
+ }
generation_config.json CHANGED
@@ -1,13 +1,6 @@
1
  {
2
- "bos_token_id": 151643,
3
- "do_sample": true,
4
- "eos_token_id": [
5
- 151645,
6
- 151643
7
- ],
8
- "pad_token_id": 151643,
9
- "temperature": 0.7,
10
- "top_k": 20,
11
- "top_p": 0.8,
12
- "transformers_version": "4.51.0"
13
- }
 
1
  {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151645,
5
+ "transformers_version": "4.57.1"
6
+ }
 
 
 
 
 
 
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98e97af0116b9c42003e6f2c83d7f6da89d930ef9fa2c3c59b61a8be9aec39fe
3
- size 9742632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:124a62e63cd07a74709075a2f5999db14aa7d301f7de1e226a3b1da73b502ee2
3
+ size 4881064