Update README.md
Browse files
README.md
CHANGED
|
@@ -7,6 +7,7 @@ tags:
|
|
| 7 |
- wizardlm
|
| 8 |
- uncensored
|
| 9 |
- gptq
|
|
|
|
| 10 |
- auto-gptq
|
| 11 |
- 7b
|
| 12 |
- llama
|
|
@@ -15,6 +16,8 @@ tags:
|
|
| 15 |
|
| 16 |
# Get Started
|
| 17 |
This model should use [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ) so you need to use `auto-gptq`
|
|
|
|
|
|
|
| 18 |
|
| 19 |
```py
|
| 20 |
from transformers import AutoTokenizer, pipeline, AutoModelForCausalLM, LlamaForCausalLM, LlamaTokenizer, StoppingCriteria, PreTrainedTokenizerBase
|
|
|
|
| 7 |
- wizardlm
|
| 8 |
- uncensored
|
| 9 |
- gptq
|
| 10 |
+
- quantization
|
| 11 |
- auto-gptq
|
| 12 |
- 7b
|
| 13 |
- llama
|
|
|
|
| 16 |
|
| 17 |
# Get Started
|
| 18 |
This model should use [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ) so you need to use `auto-gptq`
|
| 19 |
+
- `no-act-order` model
|
| 20 |
+
- 4bit model quantization
|
| 21 |
|
| 22 |
```py
|
| 23 |
from transformers import AutoTokenizer, pipeline, AutoModelForCausalLM, LlamaForCausalLM, LlamaTokenizer, StoppingCriteria, PreTrainedTokenizerBase
|