Sumail commited on
Commit
1b2ed62
·
verified ·
1 Parent(s): 4071bcb

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. config.json +33 -23
  2. merges.txt +0 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +1 -0
  5. vocab.json +0 -0
config.json CHANGED
@@ -1,28 +1,38 @@
1
  {
2
- "_name_or_path": "/root/pretraining/local-models/training/2024-03-23_13-10-52",
 
3
  "architectures": [
4
- "LlamaForCausalLM"
5
  ],
6
- "attention_bias": false,
7
- "attention_dropout": 0.0,
8
- "bos_token_id": 1,
9
- "eos_token_id": 2,
10
- "hidden_act": "silu",
11
- "hidden_size": 2048,
 
12
  "initializer_range": 0.02,
13
- "intermediate_size": 6112,
14
- "max_position_embeddings": 1024,
15
- "model_type": "llama",
16
- "num_attention_heads": 32,
17
- "num_hidden_layers": 12,
18
- "num_key_value_heads": 4,
19
- "pretraining_tp": 1,
20
- "rms_norm_eps": 1e-05,
21
- "rope_scaling": null,
22
- "rope_theta": 10000.0,
23
- "tie_word_embeddings": false,
24
- "torch_dtype": "float32",
25
- "transformers_version": "4.38.0",
26
- "use_cache": true,
 
 
 
 
 
 
 
 
27
  "vocab_size": 50257
28
- }
 
1
  {
2
+ "_num_labels": 1,
3
+ "activation_function": "gelu_new",
4
  "architectures": [
5
+ "GPT2LMHeadModel"
6
  ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "id2label": {
12
+ "0": "LABEL_0"
13
+ },
14
  "initializer_range": 0.02,
15
+ "label2id": {
16
+ "LABEL_0": 0
17
+ },
18
+ "layer_norm_epsilon": 1e-05,
19
+ "model_type": "gpt2",
20
+ "n_ctx": 1024,
21
+ "n_embd": 768,
22
+ "n_head": 12,
23
+ "n_layer": 6,
24
+ "n_positions": 1024,
25
+ "resid_pdrop": 0.1,
26
+ "summary_activation": null,
27
+ "summary_first_dropout": 0.1,
28
+ "summary_proj_to_labels": true,
29
+ "summary_type": "cls_index",
30
+ "summary_use_proj": true,
31
+ "task_specific_params": {
32
+ "text-generation": {
33
+ "do_sample": true,
34
+ "max_length": 50
35
+ }
36
+ },
37
  "vocab_size": 50257
38
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"model_max_length": 1024}
vocab.json ADDED
The diff for this file is too large to render. See raw diff