Hugging Face's logo

SamChen888
/
Gemma2-9B-Finetune-RDE

PEFT
Safetensors
t5
llama-factory
lora
Generated from Trainer
Model card Files Community
SamChen888 commited on
Commit
c1bc1a8
·
verified ·
1 Parent(s): bf66e36

Update

Browse files
Files changed (1) hide show
  1. config.json +55 -26
config.json CHANGED
@@ -1,33 +1,62 @@
1
  {
 
2
  "architectures": [
3
- "Gemma2ForCausalLM"
4
  ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "attn_logit_softcapping": 50.0,
8
- "bos_token_id": 2,
9
- "cache_implementation": "hybrid",
 
 
10
  "eos_token_id": 1,
11
- "final_logit_softcapping": 30.0,
12
- "head_dim": 256,
13
- "hidden_act": "gelu_pytorch_tanh",
14
- "hidden_activation": "gelu_pytorch_tanh",
15
- "hidden_size": 3584,
16
- "initializer_range": 0.02,
17
- "intermediate_size": 14336,
18
- "max_position_embeddings": 8192,
19
- "model_type": "gemma2",
20
- "num_attention_heads": 16,
21
- "num_hidden_layers": 42,
22
- "num_key_value_heads": 8,
23
  "pad_token_id": 0,
24
- "query_pre_attn_scalar": 256,
25
- "rms_norm_eps": 1e-06,
26
- "rope_theta": 10000.0,
27
- "sliding_window": 4096,
28
- "sliding_window_size": 4096,
29
- "torch_dtype": "bfloat16",
30
- "transformers_version": "4.42.0.dev0",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
31
  "use_cache": true,
32
- "vocab_size": 256000
33
  }
 
1
  {
2
+ "_name_or_path": "ShashiVish/t5-small-fine-tune-cover-letter",
3
  "architectures": [
4
+ "T5ForConditionalGeneration"
5
  ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 512,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "relu",
12
+ "dropout_rate": 0.1,
13
  "eos_token_id": 1,
14
+ "feed_forward_proj": "relu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": false,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "max_length": 512,
20
+ "model_type": "t5",
21
+ "n_positions": 512,
22
+ "num_decoder_layers": 6,
23
+ "num_heads": 8,
24
+ "num_layers": 6,
25
+ "output_past": true,
26
  "pad_token_id": 0,
27
+ "relative_attention_max_distance": 128,
28
+ "relative_attention_num_buckets": 32,
29
+ "task_specific_params": {
30
+ "summarization": {
31
+ "early_stopping": true,
32
+ "length_penalty": 2.0,
33
+ "max_length": 200,
34
+ "min_length": 30,
35
+ "no_repeat_ngram_size": 3,
36
+ "num_beams": 4,
37
+ "prefix": "summarize: "
38
+ },
39
+ "translation_en_to_de": {
40
+ "early_stopping": true,
41
+ "max_length": 300,
42
+ "num_beams": 4,
43
+ "prefix": "translate English to German: "
44
+ },
45
+ "translation_en_to_fr": {
46
+ "early_stopping": true,
47
+ "max_length": 300,
48
+ "num_beams": 4,
49
+ "prefix": "translate English to French: "
50
+ },
51
+ "translation_en_to_ro": {
52
+ "early_stopping": true,
53
+ "max_length": 300,
54
+ "num_beams": 4,
55
+ "prefix": "translate English to Romanian: "
56
+ }
57
+ },
58
+ "torch_dtype": "float32",
59
+ "transformers_version": "4.44.2",
60
  "use_cache": true,
61
+ "vocab_size": 32128
62
  }