Hugging Face's logo

yasmineee
/
model

Text Generation
Transformers
Safetensors
English
qwen2
text-generation-inference
unsloth
conversational
Model card Files
xet
Community
yasmineee commited on
Commit
7ad4e6b
·
verified ·
1 Parent(s): ac2535d

(Trained with Unsloth)

Browse files
Files changed (2) hide show
  1. config.json +60 -121
  2. tokenizer.json +2 -2
config.json CHANGED
@@ -1,123 +1,62 @@
1
  {
2
- "architectures": [
3
- "Qwen2ForCausalLM"
4
- ],
5
- "attention_dropout": 0.0,
6
- "bos_token_id": 151646,
7
- "eos_token_id": 151643,
8
- "hidden_act": "silu",
9
- "hidden_size": 3584,
10
- "initializer_range": 0.02,
11
- "intermediate_size": 18944,
12
- "layer_types": [
13
- "full_attention",
14
- "full_attention",
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
- ],
42
- "max_position_embeddings": 131072,
43
- "max_window_layers": 28,
44
- "model_type": "qwen2",
45
- "num_attention_heads": 28,
46
- "num_hidden_layers": 28,
47
- "num_key_value_heads": 4,
48
- "pad_token_id": 151654,
49
- "quantization_config": {
50
- "bnb_4bit_compute_dtype": "bfloat16",
51
- "bnb_4bit_quant_type": "nf4",
52
- "bnb_4bit_use_double_quant": true,
53
- "llm_int8_enable_fp32_cpu_offload": false,
54
- "llm_int8_has_fp16_weight": false,
55
- "llm_int8_skip_modules": [
56
- "model.layers.0.self_attn.q_proj",
57
- "model.layers.0.self_attn.k_proj",
58
- "model.layers.0.self_attn.v_proj",
59
- "model.layers.0.self_attn.o_proj",
60
- "model.layers.0.mlp.gate_proj",
61
- "model.layers.0.mlp.up_proj",
62
- "model.layers.0.mlp.down_proj",
63
- "model.layers.1.self_attn.q_proj",
64
- "model.layers.1.self_attn.k_proj",
65
- "model.layers.1.self_attn.v_proj",
66
- "model.layers.1.self_attn.o_proj",
67
- "model.layers.1.mlp.gate_proj",
68
- "model.layers.1.mlp.up_proj",
69
- "model.layers.1.mlp.down_proj",
70
- "model.layers.2.self_attn.q_proj",
71
- "model.layers.2.self_attn.k_proj",
72
- "model.layers.2.self_attn.v_proj",
73
- "model.layers.2.self_attn.o_proj",
74
- "model.layers.2.mlp.gate_proj",
75
- "model.layers.2.mlp.up_proj",
76
- "model.layers.2.mlp.down_proj",
77
- "model.layers.3.self_attn.q_proj",
78
- "model.layers.3.self_attn.k_proj",
79
- "model.layers.3.self_attn.v_proj",
80
- "model.layers.3.self_attn.o_proj",
81
- "model.layers.3.mlp.gate_proj",
82
- "model.layers.3.mlp.up_proj",
83
- "model.layers.3.mlp.down_proj",
84
- "model.layers.4.mlp.gate_proj",
85
- "model.layers.4.mlp.up_proj",
86
- "model.layers.4.mlp.down_proj",
87
- "model.layers.11.mlp.gate_proj",
88
- "model.layers.11.mlp.up_proj",
89
- "model.layers.11.mlp.down_proj",
90
- "model.layers.24.mlp.gate_proj",
91
- "model.layers.24.mlp.up_proj",
92
- "model.layers.24.mlp.down_proj",
93
- "model.layers.25.mlp.gate_proj",
94
- "model.layers.25.mlp.up_proj",
95
- "model.layers.25.mlp.down_proj",
96
- "model.layers.26.mlp.gate_proj",
97
- "model.layers.26.mlp.up_proj",
98
- "model.layers.26.mlp.down_proj",
99
- "model.layers.27.self_attn.q_proj",
100
- "model.layers.27.self_attn.k_proj",
101
- "model.layers.27.self_attn.v_proj",
102
- "model.layers.27.self_attn.o_proj",
103
- "lm_head"
104
  ],
105
- "llm_int8_threshold": 6.0,
106
- "load_in_4bit": true,
107
- "load_in_8bit": false,
108
- "quant_method": "bitsandbytes"
109
- },
110
- "rms_norm_eps": 1e-06,
111
- "rope_scaling": null,
112
- "rope_theta": 10000,
113
- "sliding_window": null,
114
- "tie_word_embeddings": false,
115
- "torch_dtype": "bfloat16",
116
- "transformers_version": "4.55.0",
117
- "unsloth_fixed": true,
118
- "unsloth_version": "2025.8.4",
119
- "use_cache": true,
120
- "use_mrope": false,
121
- "use_sliding_window": false,
122
- "vocab_size": 152064
123
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151646,
7
+ "eos_token_id": 151643,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 3584,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 18944,
12
+ "layer_types": [
13
+ "full_attention",
14
+ "full_attention",
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
+ ],
42
+ "max_position_embeddings": 131072,
43
+ "max_window_layers": 28,
44
+ "model_type": "qwen2",
45
+ "num_attention_heads": 28,
46
+ "num_hidden_layers": 28,
47
+ "num_key_value_heads": 4,
48
+ "pad_token_id": 151654,
49
+ "rms_norm_eps": 1e-06,
50
+ "rope_scaling": null,
51
+ "rope_theta": 10000,
52
+ "sliding_window": null,
53
+ "tie_word_embeddings": false,
54
+ "torch_dtype": "bfloat16",
55
+ "transformers_version": "4.55.0",
56
+ "unsloth_fixed": true,
57
+ "unsloth_version": "2025.8.4",
58
+ "use_cache": true,
59
+ "use_mrope": false,
60
+ "use_sliding_window": false,
61
+ "vocab_size": 152064
62
+ }
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
3
- size 11422778
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d49e08c96fcd0fb570ca5259ffb933ce28eb5c68f2c28505ca4c1cf5d6b35fd
3
+ size 11422877