Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,57 @@
|
|
1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
library_name: peft
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
license: other
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: khanhdhq/finetune_vietcuna_3b_qlora_e1_lr0.0002
|
7 |
+
results: []
|
8 |
library_name: peft
|
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 |
+
# test_vietcuna_ep1_lr0.0005
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [vilm/vietcuna-3b](https://huggingface.co/vilm/vietcuna-3b) 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 |
+
|
33 |
+
The following `bitsandbytes` quantization config was used during training:
|
34 |
+
- load_in_8bit: False
|
35 |
+
- load_in_4bit: True
|
36 |
+
- llm_int8_threshold: 6.0
|
37 |
+
- llm_int8_skip_modules: None
|
38 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
39 |
+
- llm_int8_has_fp16_weight: False
|
40 |
+
- bnb_4bit_quant_type: nf4
|
41 |
+
- bnb_4bit_use_double_quant: True
|
42 |
+
- bnb_4bit_compute_dtype: bfloat16
|
43 |
+
### Training hyperparameters
|
44 |
+
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
|
47 |
+
### Training results
|
48 |
+
|
49 |
+
|
50 |
+
|
51 |
+
### Framework versions
|
52 |
+
|
53 |
+
- PEFT 0.4.0.dev0
|
54 |
+
- Transformers 4.31.0.dev0
|
55 |
+
- Pytorch 2.0.1+cu118
|
56 |
+
- Datasets 2.13.0
|
57 |
+
- Tokenizers 0.13.3
|