Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
---
|
4 |
+
This is exl2 format model.
|
5 |
+
|
6 |
+
### Yi-34b-Chat-Spicyboros-limarpv3-4bpw-hb6-exl2
|
7 |
+
|
8 |
+
- base model: [Yi-34B-Chat](https://huggingface.co/01-ai/Yi-34B-Chat) Yi-34B对话模型
|
9 |
+
- LoRA: [Yi-34B-Spicyboros-3.1-LoRA](https://huggingface.co/LoneStriker/Yi-34B-Spicyboros-3.1-LoRA) 非官方对话数据集
|
10 |
+
- LoRA: [limarpv3-yi-llama-34b-lora](https://huggingface.co/Doctor-Shotgun/limarpv3-yi-llama-34b-lora) 扮演类长回复
|
11 |
+
- Instruction template: ChatML
|
12 |
+
|
13 |
+
### description
|
14 |
+
|
15 |
+
- This is test for [exllamav2](https://github.com/turboderp/exllamav2) model
|
16 |
+
- 4.15bpw `python convert.py -i Yi-34b-Chat-Spicyboros-limarpv3 -c exl2/0000.parquet -o Yi-34b-Chat-Spicyboros-limarpv3-4bpw-hb6-exl2 -hb 6 -l 4096 -b 4.15`
|
17 |
+
- [convert doc](https://github.com/turboderp/exllamav2/blob/master/doc/convert.md)
|
18 |
+
- calibration dataset: [WikiText-2-v1](https://huggingface.co/datasets/wikitext/blob/refs%2Fconvert%2Fparquet/wikitext-2-v1/test/0000.parquet)
|