Hugging Face's logo

minkdank
/
LLAMA-JSON-data-extration

Safetensors
GGUF
llama
llama.cpp
unsloth
conversational
Model card Files
xet
Community
minkdank commited on
Commit
f9433a1
·
verified ·
1 Parent(s): af501bd

Trained with Unsloth - config

Browse files
Files changed (1) hide show
  1. config.json +37 -98
config.json CHANGED
@@ -1,99 +1,38 @@
1
  {
2
- "architectures": [
3
- "Gemma3ForConditionalGeneration"
4
- ],
5
- "boi_token_index": 255999,
6
- "bos_token_id": 2,
7
- "eoi_token_index": 256000,
8
- "eos_token_id": 106,
9
- "image_token_index": 262144,
10
- "initializer_range": 0.02,
11
- "mm_tokens_per_image": 256,
12
- "model_type": "gemma3",
13
- "pad_token_id": 0,
14
- "text_config": {
15
- "_sliding_window_pattern": 6,
16
- "attention_bias": false,
17
- "attention_dropout": 0.0,
18
- "attn_logit_softcapping": null,
19
- "cache_implementation": "hybrid",
20
- "final_logit_softcapping": null,
21
- "head_dim": 256,
22
- "hidden_activation": "gelu_pytorch_tanh",
23
- "hidden_size": 2560,
24
- "initializer_range": 0.02,
25
- "intermediate_size": 10240,
26
- "layer_types": [
27
- "sliding_attention",
28
- "sliding_attention",
29
- "sliding_attention",
30
- "sliding_attention",
31
- "sliding_attention",
32
- "full_attention",
33
- "sliding_attention",
34
- "sliding_attention",
35
- "sliding_attention",
36
- "sliding_attention",
37
- "sliding_attention",
38
- "full_attention",
39
- "sliding_attention",
40
- "sliding_attention",
41
- "sliding_attention",
42
- "sliding_attention",
43
- "sliding_attention",
44
- "full_attention",
45
- "sliding_attention",
46
- "sliding_attention",
47
- "sliding_attention",
48
- "sliding_attention",
49
- "sliding_attention",
50
- "full_attention",
51
- "sliding_attention",
52
- "sliding_attention",
53
- "sliding_attention",
54
- "sliding_attention",
55
- "sliding_attention",
56
- "full_attention",
57
- "sliding_attention",
58
- "sliding_attention",
59
- "sliding_attention",
60
- "sliding_attention"
61
- ],
62
- "max_position_embeddings": 131072,
63
- "model_type": "gemma3_text",
64
- "num_attention_heads": 8,
65
- "num_hidden_layers": 34,
66
- "num_key_value_heads": 4,
67
- "query_pre_attn_scalar": 256,
68
- "rms_norm_eps": 1e-06,
69
- "rope_local_base_freq": 10000.0,
70
- "rope_scaling": {
71
- "factor": 8.0,
72
- "rope_type": "linear"
73
- },
74
- "rope_theta": 1000000.0,
75
- "sliding_window": 1024,
76
- "torch_dtype": "bfloat16",
77
- "use_cache": true,
78
- "vocab_size": 262208
79
- },
80
- "torch_dtype": "bfloat16",
81
- "transformers_version": "4.55.4",
82
- "unsloth_fixed": true,
83
- "unsloth_version": "2025.11.2",
84
- "vision_config": {
85
- "attention_dropout": 0.0,
86
- "hidden_act": "gelu_pytorch_tanh",
87
- "hidden_size": 1152,
88
- "image_size": 896,
89
- "intermediate_size": 4304,
90
- "layer_norm_eps": 1e-06,
91
- "model_type": "siglip_vision_model",
92
- "num_attention_heads": 16,
93
- "num_channels": 3,
94
- "num_hidden_layers": 27,
95
- "patch_size": 14,
96
- "torch_dtype": "bfloat16",
97
- "vision_use_head": false
98
- }
99
- }
 
1
  {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": 128009,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 3072,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 8192,
14
+ "max_position_embeddings": 131072,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 24,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 8,
20
+ "pad_token_id": 128004,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": {
24
+ "factor": 32.0,
25
+ "high_freq_factor": 4.0,
26
+ "low_freq_factor": 1.0,
27
+ "original_max_position_embeddings": 8192,
28
+ "rope_type": "llama3"
29
+ },
30
+ "rope_theta": 500000.0,
31
+ "tie_word_embeddings": true,
32
+ "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.55.4",
34
+ "unsloth_fixed": true,
35
+ "unsloth_version": "2025.11.3",
36
+ "use_cache": true,
37
+ "vocab_size": 128256
38
+ }