ranggafermata commited on
Commit
fc85c99
·
verified ·
1 Parent(s): 794fedc

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +18 -33
config.json CHANGED
@@ -1,40 +1,25 @@
1
  {
2
  "architectures": [
3
- "Gemma3ForConditionalGeneration"
4
  ],
5
- "boi_token_index": 255999,
6
- "eoi_token_index": 256000,
7
- "eos_token_id": [
8
- 1,
9
- 106
10
- ],
11
- "image_token_index": 262144,
12
- "initializer_range": 0.02,
13
- "mm_tokens_per_image": 256,
14
  "model_type": "gemma",
15
- "text_config": {
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
- "max_position_embeddings": 131072,
27
- "model_type": "gemma3_text",
28
- "num_attention_heads": 8,
29
- "num_hidden_layers": 34,
30
- "num_key_value_heads": 4,
31
- "query_pre_attn_scalar": 256,
32
- "rms_norm_eps": 1e-06,
33
- "rope_local_base_freq": 10000.0,
34
- "rope_scaling": {
35
- "factor": 8.0,
36
- "rope_type": "linear"
37
- },
38
  "rope_theta": 1000000.0,
39
  "sliding_window": 1024,
40
  "sliding_window_pattern": 6,
 
1
  {
2
  "architectures": [
3
+ "GemmaForCausalLM"
4
  ],
5
+ "auto_map": {
6
+ "AutoModelForCausalLM": "gemma.modeling_gemma.GemmaForCausalLM",
7
+ "AutoTokenizer": "tokenization_gemma.GemmaTokenizer"
8
+ },
 
 
 
 
 
9
  "model_type": "gemma",
10
+ "torch_dtype": "bfloat16",
11
+ "transformers_version": "4.50.0",
12
+ "use_cache": true,
13
+ "vocab_size": 256000,
14
+ "hidden_size": 3072,
15
+ "intermediate_size": 8192,
16
+ "num_hidden_layers": 28,
17
+ "num_attention_heads": 16,
18
+ "max_position_embeddings": 8192,
19
+ "tie_word_embeddings": false,
20
+ "rope_scaling": null
21
+ }
22
+ {
 
 
 
 
 
 
 
 
 
 
23
  "rope_theta": 1000000.0,
24
  "sliding_window": 1024,
25
  "sliding_window_pattern": 6,