Hugging Face's logo

GTKING
/
ZFusionAI_Hacker

Safetensors
GGUF
qwen3
llama.cpp
qwen
uncensored
quantized
offline
local-ai
conversational
Model card Files
xet
Community
GTKING commited on
Commit
835f92b
·
verified ·
1 Parent(s): 7ae273e

Upload Qwen3ForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +48 -25
  2. generation_config.json +7 -5
  3. model.safetensors +2 -2
config.json CHANGED
@@ -1,39 +1,62 @@
1
  {
2
  "architectures": [
3
- "LlamaForCausalLM"
4
  ],
5
  "attention_bias": false,
6
  "attention_dropout": 0.0,
7
- "bos_token_id": 128000,
8
  "dtype": "bfloat16",
9
- "eos_token_id": [
10
- 128001,
11
- 128008,
12
- 128009
13
- ],
14
- "head_dim": 64,
15
  "hidden_act": "silu",
16
  "hidden_size": 2048,
17
  "initializer_range": 0.02,
18
- "intermediate_size": 8192,
19
- "max_position_embeddings": 131072,
20
- "mlp_bias": false,
21
- "model_type": "llama",
22
- "num_attention_heads": 32,
23
- "num_hidden_layers": 16,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
24
  "num_key_value_heads": 8,
25
- "pretraining_tp": 1,
26
- "rms_norm_eps": 1e-05,
27
- "rope_scaling": {
28
- "factor": 32.0,
29
- "high_freq_factor": 4.0,
30
- "low_freq_factor": 1.0,
31
- "original_max_position_embeddings": 8192,
32
- "rope_type": "llama3"
33
- },
34
- "rope_theta": 500000.0,
35
  "tie_word_embeddings": true,
36
  "transformers_version": "4.57.1",
 
 
37
  "use_cache": true,
38
- "vocab_size": 128256
 
39
  }
 
1
  {
2
  "architectures": [
3
+ "Qwen3ForCausalLM"
4
  ],
5
  "attention_bias": false,
6
  "attention_dropout": 0.0,
 
7
  "dtype": "bfloat16",
8
+ "eos_token_id": 151645,
9
+ "head_dim": 128,
 
 
 
 
10
  "hidden_act": "silu",
11
  "hidden_size": 2048,
12
  "initializer_range": 0.02,
13
+ "intermediate_size": 6144,
14
+ "layer_types": [
15
+ "full_attention",
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
+ ],
44
+ "max_position_embeddings": 40960,
45
+ "max_window_layers": 28,
46
+ "model_type": "qwen3",
47
+ "num_attention_heads": 16,
48
+ "num_hidden_layers": 28,
49
  "num_key_value_heads": 8,
50
+ "pad_token_id": 151654,
51
+ "rms_norm_eps": 1e-06,
52
+ "rope_scaling": null,
53
+ "rope_theta": 1000000,
54
+ "sliding_window": null,
 
 
 
 
 
55
  "tie_word_embeddings": true,
56
  "transformers_version": "4.57.1",
57
+ "unsloth_fixed": true,
58
+ "unsloth_version": "2025.4.7",
59
  "use_cache": true,
60
+ "use_sliding_window": false,
61
+ "vocab_size": 151936
62
  }
generation_config.json CHANGED
@@ -1,12 +1,14 @@
1
  {
2
- "bos_token_id": 128000,
3
  "do_sample": true,
4
  "eos_token_id": [
5
- 128001,
6
- 128008,
7
- 128009
8
  ],
 
 
9
  "temperature": 0.6,
10
- "top_p": 0.9,
 
11
  "transformers_version": "4.57.1"
12
  }
 
1
  {
2
+ "bos_token_id": 151643,
3
  "do_sample": true,
4
  "eos_token_id": [
5
+ 151645,
6
+ 151643
 
7
  ],
8
+ "max_length": 40960,
9
+ "pad_token_id": 151654,
10
  "temperature": 0.6,
11
+ "top_k": 20,
12
+ "top_p": 0.95,
13
  "transformers_version": "4.57.1"
14
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e757608f57db9b5288e49ed725ede2c41f4eee62f9cc39c9e32471a70e892105
3
- size 2471645608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb0e3317d4be5e8f91aa6717c04346191374829b0fa4a028a1f521e96b451ec9
3
+ size 3441185608