ilarramendi commited on
Commit
851edb7
1 Parent(s): 684378d

Delete config.json

Browse files
Files changed (1) hide show
  1. config.json +0 -49
config.json DELETED
@@ -1,49 +0,0 @@
1
- {
2
- "_name_or_path": "ilarramendi/srt-translate-gemma-2-1epoch",
3
- "architectures": [
4
- "Gemma2ForCausalLM"
5
- ],
6
- "attention_bias": false,
7
- "attention_dropout": 0.0,
8
- "attn_logit_softcapping": 50.0,
9
- "bos_token_id": 2,
10
- "cache_implementation": "hybrid",
11
- "eos_token_id": 1,
12
- "final_logit_softcapping": 30.0,
13
- "head_dim": 256,
14
- "hidden_act": "gelu_pytorch_tanh",
15
- "hidden_activation": "gelu_pytorch_tanh",
16
- "hidden_size": 3584,
17
- "initializer_range": 0.02,
18
- "intermediate_size": 14336,
19
- "max_position_embeddings": 8192,
20
- "model_type": "gemma2",
21
- "num_attention_heads": 16,
22
- "num_hidden_layers": 42,
23
- "num_key_value_heads": 8,
24
- "pad_token_id": 0,
25
- "quantization_config": {
26
- "_load_in_4bit": true,
27
- "_load_in_8bit": false,
28
- "bnb_4bit_compute_dtype": "bfloat16",
29
- "bnb_4bit_quant_storage": "uint8",
30
- "bnb_4bit_quant_type": "nf4",
31
- "bnb_4bit_use_double_quant": true,
32
- "llm_int8_enable_fp32_cpu_offload": false,
33
- "llm_int8_has_fp16_weight": false,
34
- "llm_int8_skip_modules": null,
35
- "llm_int8_threshold": 6.0,
36
- "load_in_4bit": true,
37
- "load_in_8bit": false,
38
- "quant_method": "bitsandbytes"
39
- },
40
- "query_pre_attn_scalar": 224,
41
- "rms_norm_eps": 1e-06,
42
- "rope_theta": 10000.0,
43
- "sliding_window": 4096,
44
- "sliding_window_size": 4096,
45
- "torch_dtype": "bfloat16",
46
- "transformers_version": "4.43.0.dev0",
47
- "use_cache": true,
48
- "vocab_size": 256000
49
- }