Hugging Face's logo

llm-wizard
/
sft_zephyr

PEFT
TensorBoard
Safetensors
trl
sft
generated_from_trainer
Model card Files Metrics Community
Chris Alexiuk commited on
Commit
a9e05fa
•
1 Parent(s): 2b9b742

llme2_sft_model_rlaif

Browse files
Files changed (8) hide show
  1. README.md +9 -5
  2. adapter_config.json +7 -3
  3. adapter_model.safetensors +1 -1
  4. runs/Jan30_22-19-14_fd46eea5b897/events.out.tfevents.1706653155.fd46eea5b897.923.0 +3 -0
  5. tokenizer.json +6 -1
  6. tokenizer.model +3 -0
  7. tokenizer_config.json +2 -0
  8. training_args.bin +2 -2
README.md CHANGED
@@ -1,8 +1,11 @@
1
  ---
2
  license: mit
3
- base_model: HuggingFaceH4/zephyr-7b-alpha
4
  tags:
 
 
5
  - generated_from_trainer
 
6
  model-index:
7
  - name: sft_zephyr
8
  results: []
@@ -46,7 +49,8 @@ The following hyperparameters were used during training:
46
 
47
  ### Framework versions
48
 
49
- - Transformers 4.35.2
50
- - Pytorch 2.1.0+cu118
51
- - Datasets 2.15.0
52
- - Tokenizers 0.15.0
 
 
1
  ---
2
  license: mit
3
+ library_name: peft
4
  tags:
5
+ - trl
6
+ - sft
7
  - generated_from_trainer
8
+ base_model: HuggingFaceH4/zephyr-7b-alpha
9
  model-index:
10
  - name: sft_zephyr
11
  results: []
 
49
 
50
  ### Framework versions
51
 
52
+ - PEFT 0.8.1
53
+ - Transformers 4.37.2
54
+ - Pytorch 2.1.0+cu121
55
+ - Datasets 2.16.1
56
+ - Tokenizers 0.15.1
adapter_config.json CHANGED
@@ -8,16 +8,20 @@
8
  "init_lora_weights": true,
9
  "layers_pattern": null,
10
  "layers_to_transform": null,
 
11
  "lora_alpha": 16,
12
  "lora_dropout": 0.1,
 
 
13
  "modules_to_save": null,
14
  "peft_type": "LORA",
15
  "r": 64,
16
  "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
19
- "v_proj",
20
- "q_proj"
21
  ],
22
- "task_type": "CAUSAL_LM"
 
23
  }
 
8
  "init_lora_weights": true,
9
  "layers_pattern": null,
10
  "layers_to_transform": null,
11
+ "loftq_config": {},
12
  "lora_alpha": 16,
13
  "lora_dropout": 0.1,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
  "modules_to_save": null,
17
  "peft_type": "LORA",
18
  "r": 64,
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
+ "q_proj",
23
+ "v_proj"
24
  ],
25
+ "task_type": "CAUSAL_LM",
26
+ "use_rslora": false
27
  }
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d038325d8d2f6680ee8c9302ec74107cca8a185bbecfd421cd6fc7017639eba0
3
  size 109069176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c26a2ba5c9b109b953f6155dd9cd69c970a42028dd8c6dae6e8fa227a3fe3bd
3
  size 109069176
runs/Jan30_22-19-14_fd46eea5b897/events.out.tfevents.1706653155.fd46eea5b897.923.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e2f19e03ac2b64e03473208ec9b29e8a5436e0120a14dadf1f5007fb4ef763b
3
+ size 5091
tokenizer.json CHANGED
@@ -1,6 +1,11 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Left",
5
+ "max_length": 2048,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
  "padding": null,
10
  "added_tokens": [
11
  {
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json CHANGED
@@ -1,4 +1,6 @@
1
  {
 
 
2
  "added_tokens_decoder": {
3
  "0": {
4
  "content": "<unk>",
 
1
  {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
  "added_tokens_decoder": {
5
  "0": {
6
  "content": "<unk>",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:095fc8eb570c7821109b5b43891161aeeef89ce935874d90a044aba098bf50f7
3
- size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5f773561928a8d3f3c150edd166c479514c419cf88681d90ad020965d863cbf
3
+ size 4728