Hugging Face's logo

Harshatheeswar
/
babylama-hidden_layers12

Text Generation
Transformers
TensorBoard
Safetensors
llama
Generated from Trainer
text-generation-inference
Model card Files
xet
 Metrics Community
Harshatheeswar commited on
Commit
e41bd54
·
verified ·
1 Parent(s): e8c284d

Training in progress, step 500

Browse files
Files changed (10) hide show
  1. added_tokens.json +3 -0
  2. config.json +31 -0
  3. merges.txt +0 -0
  4. model.safetensors +3 -0
  5. runs/Nov13_09-10-54_5b91a2bf3201/events.out.tfevents.1731489057.5b91a2bf3201.1016.0 +3 -0
  6. special_tokens_map.json +30 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +44 -0
  9. training_args.bin +3 -0
  10. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 16000
3
+ }
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Harshatheeswar/babylama-hidden_sizes768",
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
+ "head_dim": 96,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "max_position_embeddings": 256,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 8,
19
+ "num_hidden_layers": 12,
20
+ "num_key_value_heads": 8,
21
+ "pad_token_id": 0,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-06,
24
+ "rope_scaling": null,
25
+ "rope_theta": 10000.0,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.46.2",
29
+ "use_cache": true,
30
+ "vocab_size": 16000
31
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a65c78e2f41083171c8df91bacabdc48058450efdbf03a6c50241a2dad1b66e
3
+ size 551377944
runs/Nov13_09-10-54_5b91a2bf3201/events.out.tfevents.1731489057.5b91a2bf3201.1016.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01324175720d58875c499d4ea57bcd2411178309ac959050914639844f95b1e8
3
+ size 15680
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "16000": {
29
+ "content": "<|endoftext|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ }
36
+ },
37
+ "bos_token": "<s>",
38
+ "clean_up_tokenization_spaces": true,
39
+ "eos_token": "</s>",
40
+ "model_max_length": 128,
41
+ "pad_token": "<pad>",
42
+ "tokenizer_class": "GPT2Tokenizer",
43
+ "unk_token": "<|endoftext|>"
44
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fdda003a2a249f0c5312f4aefb7a367f653036d008aecd5d3ae6b185db2e78c
3
+ size 5304
vocab.json ADDED
The diff for this file is too large to render. See raw diff