lucifer-Hell commited on
Commit
9a5821e
1 Parent(s): 8de014c
Files changed (3) hide show
  1. README.md +21 -45
  2. adapter_model.bin +2 -2
  3. training_args.bin +2 -2
README.md CHANGED
@@ -1,52 +1,28 @@
1
  ---
2
- license: apache-2.0
3
- base_model: TheBloke/Mistral-7B-v0.1-GPTQ
4
- tags:
5
- - generated_from_trainer
6
- model-index:
7
- - name: msytral-db-ai
8
- results: []
9
  ---
10
-
11
- <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
- should probably proofread and complete it, then remove this comment. -->
13
-
14
- # msytral-db-ai
15
-
16
- This model is a fine-tuned version of [TheBloke/Mistral-7B-v0.1-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-v0.1-GPTQ) on an unknown dataset.
17
-
18
- ## Model description
19
-
20
- More information needed
21
-
22
- ## Intended uses & limitations
23
-
24
- More information needed
25
-
26
- ## Training and evaluation data
27
-
28
- More information needed
29
-
30
  ## Training procedure
31
 
32
- ### Training hyperparameters
33
-
34
- The following hyperparameters were used during training:
35
- - learning_rate: 5e-05
36
- - train_batch_size: 8
37
- - eval_batch_size: 8
38
- - seed: 42
39
- - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
- - lr_scheduler_type: linear
41
- - num_epochs: 3.0
42
-
43
- ### Training results
44
-
45
-
46
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  ### Framework versions
48
 
49
- - Transformers 4.34.0
50
- - Pytorch 2.0.1+cu118
51
- - Datasets 2.14.5
52
- - Tokenizers 0.14.1
 
1
  ---
2
+ library_name: peft
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  ## Training procedure
5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
 
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - quant_method: gptq
9
+ - bits: 4
10
+ - tokenizer: None
11
+ - dataset: None
12
+ - group_size: 128
13
+ - damp_percent: 0.1
14
+ - desc_act: True
15
+ - sym: True
16
+ - true_sequential: True
17
+ - use_cuda_fp16: False
18
+ - model_seqlen: None
19
+ - block_name_to_quantize: None
20
+ - module_name_preceding_first_block: None
21
+ - batch_size: 1
22
+ - pad_token_id: None
23
+ - disable_exllama: False
24
+ - max_input_length: None
25
  ### Framework versions
26
 
27
+
28
+ - PEFT 0.5.0
 
 
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7f1a8776e89ce643602e0354a6b86f0633183c27c59d8fe4453d53d88abed2d
3
- size 27372365
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a543e091968341fa23ff0878f3eb0ccdf7b6a0f7ea05ff6df2bdd05d8c9cd02b
3
+ size 27354957
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab5570faac5b35638087e7a5d47be9b84daf7141729fcbe3dfa4cac374e91726
3
- size 4027
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb47f4ec9dedc436643915b791eb491441742899ac2f4976c767db7fcbbc20f3
3
+ size 4091