Hugging Face's logo

jan-hq
/
LlamaCorn-1.1B-Chat

Text Generation
Transformers
TensorBoard
Safetensors
llama
alignment-handbook
Generated from Trainer
trl
sft
conversational
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
jan-hq commited on
Commit
a0e75da
•
1 Parent(s): acc3c70

Training in progress, step 100

Browse files
Files changed (11) hide show
  1. config.json +28 -0
  2. model.safetensors +3 -0
  3. runs/Jan24_05-09-48_333df911e7ea/events.out.tfevents.1706073392.333df911e7ea.1925753.0 +3 -0
  4. runs/Jan24_05-18-30_333df911e7ea/events.out.tfevents.1706073558.333df911e7ea.1928884.0 +3 -0
  5. runs/Jan24_05-32-24_333df911e7ea/events.out.tfevents.1706074392.333df911e7ea.1932427.0 +3 -0
  6. runs/Jan24_05-52-24_333df911e7ea/events.out.tfevents.1706075592.333df911e7ea.1937124.0 +3 -0
  7. special_tokens_map.json +30 -0
  8. tokenizer.json +0 -0
  9. tokenizer.model +3 -0
  10. tokenizer_config.json +42 -0
  11. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/code/alignment-handbook_adjusted/data/llamacorn-sft",
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": 5632,
14
+ "max_position_embeddings": 2048,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 22,
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": "bfloat16",
25
+ "transformers_version": "4.36.2",
26
+ "use_cache": false,
27
+ "vocab_size": 32000
28
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d84a60f1fa8a7983c7ba64e594ffa262795857a20abacff850cff461cd3bfe8
3
+ size 2200119864
runs/Jan24_05-09-48_333df911e7ea/events.out.tfevents.1706073392.333df911e7ea.1925753.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de60286771ac0158a7875cb3b2b73cb6909ea21f3fdd2efddafc5c768f22eedc
3
+ size 4612
runs/Jan24_05-18-30_333df911e7ea/events.out.tfevents.1706073558.333df911e7ea.1928884.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4af3b4e1577a0408f11df4fed19d7b11bd8298458c9b22b0168d178ca01b6d29
3
+ size 5235
runs/Jan24_05-32-24_333df911e7ea/events.out.tfevents.1706074392.333df911e7ea.1932427.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:070716185620ac937cde4b9b86aa8e112935883d152c16a27ed7894b586a0a86
3
+ size 5235
runs/Jan24_05-52-24_333df911e7ea/events.out.tfevents.1706075592.333df911e7ea.1937124.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11c80505fe5e661ee5cc24ba10b545e7e5fc130598178755e4404d72dbd404a9
3
+ size 12192
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": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
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.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<s>",
31
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": false,
35
+ "model_max_length": 2048,
36
+ "pad_token": "</s>",
37
+ "padding_side": "right",
38
+ "sp_model_kwargs": {},
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d31be2c9fd7955f212a3c20df60d0a2097af035099a312bc537b9ab827003ee6
3
+ size 4856