Hugging Face's logo

AravindAct
/
output

Text Generation
Transformers
PyTorch
TensorBoard
llama
Generated from Trainer
text-generation-inference
Model card Files
xet
 Metrics Community
1
AravindAct commited on
Commit
f73d1d3
·
1 Parent(s): 02d06c8

Training in progress, epoch 1

Browse files
Files changed (3) hide show
  1. config.json +17 -54
  2. pytorch_model.bin +2 -2
  3. training_args.bin +2 -2
config.json CHANGED
@@ -1,60 +1,23 @@
1
  {
2
- "_name_or_path": "t5-base",
3
  "architectures": [
4
- "T5ForConditionalGeneration"
5
  ],
6
- "d_ff": 3072,
7
- "d_kv": 64,
8
- "d_model": 768,
9
- "decoder_start_token_id": 0,
10
- "dense_act_fn": "relu",
11
- "dropout_rate": 0.1,
12
  "eos_token_id": 1,
13
- "feed_forward_proj": "relu",
14
- "initializer_factor": 1.0,
15
- "is_encoder_decoder": true,
16
- "is_gated_act": false,
17
- "layer_norm_epsilon": 1e-06,
18
- "model_type": "t5",
19
- "n_positions": 512,
20
- "num_decoder_layers": 12,
21
- "num_heads": 12,
22
- "num_layers": 12,
23
- "output_past": true,
24
- "pad_token_id": 0,
25
- "relative_attention_max_distance": 128,
26
- "relative_attention_num_buckets": 32,
27
- "task_specific_params": {
28
- "summarization": {
29
- "early_stopping": true,
30
- "length_penalty": 2.0,
31
- "max_length": 200,
32
- "min_length": 30,
33
- "no_repeat_ngram_size": 3,
34
- "num_beams": 4,
35
- "prefix": "summarize: "
36
- },
37
- "translation_en_to_de": {
38
- "early_stopping": true,
39
- "max_length": 300,
40
- "num_beams": 4,
41
- "prefix": "translate English to German: "
42
- },
43
- "translation_en_to_fr": {
44
- "early_stopping": true,
45
- "max_length": 300,
46
- "num_beams": 4,
47
- "prefix": "translate English to French: "
48
- },
49
- "translation_en_to_ro": {
50
- "early_stopping": true,
51
- "max_length": 300,
52
- "num_beams": 4,
53
- "prefix": "translate English to Romanian: "
54
- }
55
- },
56
- "torch_dtype": "float32",
57
- "transformers_version": "4.27.3",
58
  "use_cache": true,
59
- "vocab_size": 32128
60
  }
 
1
  {
2
+ "_name_or_path": "decapoda-research/llama-7b-hf",
3
  "architectures": [
4
+ "LlamaForCausalLM"
5
  ],
6
+ "bos_token_id": 0,
 
 
 
 
 
7
  "eos_token_id": 1,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 11008,
12
+ "max_sequence_length": 2048,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 32,
15
+ "num_hidden_layers": 32,
16
+ "pad_token_id": -1,
17
+ "rms_norm_eps": 1e-06,
18
+ "tie_word_embeddings": false,
19
+ "torch_dtype": "float16",
20
+ "transformers_version": "4.28.0.dev0",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21
  "use_cache": true,
22
+ "vocab_size": 32001
23
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f94e74a5c940137bc6ea86944caecd6fc7dde0069f3c5a31806e1e299d953b2
3
- size 891702929
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed1d42076ffb837b217984d27df3b1848d6c607243f0f6f83da183198e39aee4
3
+ size 7000956593
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac2d630e7bb220a9f247b645f6dbe90face56e1cbbaf005afd607328939bf792
3
- size 3707
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ef5484bcb296443be1055ab416c0c39923169d1e70dd9d08802a56dfa7da7eb
3
+ size 3771