soob3123 commited on
Commit
b449381
·
verified ·
1 Parent(s): 3a9d802

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +52 -30
config.json CHANGED
@@ -1,32 +1,54 @@
1
  {
2
- "architectures": [
3
- "Qwen3Model"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "eos_token_id": 151645,
8
- "head_dim": 128,
9
- "hidden_act": "silu",
10
- "hidden_size": 5120,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 17408,
13
- "max_position_embeddings": 40960,
14
- "max_window_layers": 40,
15
- "model_type": "qwen3",
16
- "num_attention_heads": 40,
17
- "num_hidden_layers": 40,
18
- "num_key_value_heads": 8,
19
- "pad_token_id": 151654,
20
- "rms_norm_eps": 1e-06,
21
- "rope_scaling": null,
22
- "rope_theta": 1000000,
23
- "sliding_window": null,
24
- "tie_word_embeddings": false,
25
- "torch_dtype": "bfloat16",
26
- "transformers_version": "4.51.3",
27
- "unsloth_fixed": true,
28
- "unsloth_version": "2025.4.3",
29
- "use_cache": true,
30
- "use_sliding_window": false,
31
- "vocab_size": 151936
32
- }
 
1
  {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "eos_token_id": 151645,
8
+ "head_dim": 128,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 5120,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 17408,
13
+ "max_position_embeddings": 40960,
14
+ "max_window_layers": 40,
15
+ "model_type": "qwen3",
16
+ "num_attention_heads": 40,
17
+ "num_hidden_layers": 40,
18
+ "num_key_value_heads": 8,
19
+ "pad_token_id": 151654,
20
+ "quantization_config": {
21
+ "_load_in_4bit": true,
22
+ "_load_in_8bit": false,
23
+ "bnb_4bit_compute_dtype": "bfloat16",
24
+ "bnb_4bit_quant_storage": "uint8",
25
+ "bnb_4bit_quant_type": "nf4",
26
+ "bnb_4bit_use_double_quant": true,
27
+ "llm_int8_enable_fp32_cpu_offload": false,
28
+ "llm_int8_has_fp16_weight": false,
29
+ "llm_int8_skip_modules": [
30
+ "lm_head",
31
+ "multi_modal_projector",
32
+ "merger",
33
+ "modality_projection",
34
+ "model.layers.6.mlp",
35
+ "model.layers.38.mlp",
36
+ "model.layers.19.mlp"
37
  ],
38
+ "llm_int8_threshold": 6.0,
39
+ "load_in_4bit": true,
40
+ "load_in_8bit": false,
41
+ "quant_method": "bitsandbytes"
42
+ },
43
+ "rms_norm_eps": 1e-06,
44
+ "rope_scaling": null,
45
+ "rope_theta": 1000000,
46
+ "sliding_window": null,
47
+ "tie_word_embeddings": false,
48
+ "torch_dtype": "bfloat16",
49
+ "transformers_version": "4.52.0.dev0",
50
+ "unsloth_fixed": true,
51
+ "use_cache": true,
52
+ "use_sliding_window": false,
53
+ "vocab_size": 151936
54
+ }