Update README.md
Browse files
README.md
CHANGED
|
@@ -43,8 +43,6 @@ Among its main features are:
|
|
| 43 |
|original(fxied batch infer)|192|1638.52 toekns/s|
|
| 44 |
|lyraChatGLM(current)|256|9082.60+ tokens/s|
|
| 45 |
|
| 46 |
-
|
| 47 |
-
|
| 48 |
### test on V100
|
| 49 |
|version|max_batch_size|max_speed|
|
| 50 |
|:-:|:-:|:-:|
|
|
@@ -52,12 +50,10 @@ Among its main features are:
|
|
| 52 |
|original(fxied batch infer)|128|992.20 toekns/s|
|
| 53 |
|lyraChatGLM(current)|192|3911.45+ tokens/s|
|
| 54 |
|
| 55 |
-
|
| 56 |
## Model Sources
|
| 57 |
|
| 58 |
- **Repository:** https://huggingface.co/THUDM/chatglm-6b
|
| 59 |
|
| 60 |
-
|
| 61 |
## Docker Environment
|
| 62 |
|
| 63 |
- **docker image available** at [https://hub.docker.com/repository/docker/bigmoyan/lyrallm/general], pull image by:
|
|
@@ -66,7 +62,6 @@ Among its main features are:
|
|
| 66 |
docker pull bigmoyan/lyrallm:v0.1
|
| 67 |
```
|
| 68 |
|
| 69 |
-
|
| 70 |
## Uses
|
| 71 |
|
| 72 |
```python
|
|
@@ -85,7 +80,6 @@ test_batch_size = 256
|
|
| 85 |
|
| 86 |
prompts = [prompt, ]
|
| 87 |
|
| 88 |
-
|
| 89 |
# If you want to get different output in same batch, you can set do_sample to True
|
| 90 |
output_texts = model.generate(prompts, output_length=max_output_length,top_k=30, top_p=0.85, temperature=0.35, repetition_penalty=1.2, do_sample=False)
|
| 91 |
|
|
@@ -106,7 +100,6 @@ print(output_texts)
|
|
| 106 |
|
| 107 |
3. 支持向量机(Support Vector Machine):支持向量机是一种监督学习方法,通常用于分类问题。它可以处理高维数据,并且具有较高的准确性。适用于需要对高维数据进行分类或回归的问题,例如图像识别、自然语言处理等。
|
| 108 |
|
| 109 |
-
|
| 110 |
## Citation
|
| 111 |
``` bibtex
|
| 112 |
@Misc{lyraChatGLM2023,
|
|
@@ -120,5 +113,3 @@ print(output_texts)
|
|
| 120 |
## Report bug
|
| 121 |
- start a discussion to report any bugs!--> https://huggingface.co/TMElyralab/lyraChatGLM/discussions
|
| 122 |
- report bug with a `[bug]` mark in the title.
|
| 123 |
-
|
| 124 |
-
|
|
|
|
| 43 |
|original(fxied batch infer)|192|1638.52 toekns/s|
|
| 44 |
|lyraChatGLM(current)|256|9082.60+ tokens/s|
|
| 45 |
|
|
|
|
|
|
|
| 46 |
### test on V100
|
| 47 |
|version|max_batch_size|max_speed|
|
| 48 |
|:-:|:-:|:-:|
|
|
|
|
| 50 |
|original(fxied batch infer)|128|992.20 toekns/s|
|
| 51 |
|lyraChatGLM(current)|192|3911.45+ tokens/s|
|
| 52 |
|
|
|
|
| 53 |
## Model Sources
|
| 54 |
|
| 55 |
- **Repository:** https://huggingface.co/THUDM/chatglm-6b
|
| 56 |
|
|
|
|
| 57 |
## Docker Environment
|
| 58 |
|
| 59 |
- **docker image available** at [https://hub.docker.com/repository/docker/bigmoyan/lyrallm/general], pull image by:
|
|
|
|
| 62 |
docker pull bigmoyan/lyrallm:v0.1
|
| 63 |
```
|
| 64 |
|
|
|
|
| 65 |
## Uses
|
| 66 |
|
| 67 |
```python
|
|
|
|
| 80 |
|
| 81 |
prompts = [prompt, ]
|
| 82 |
|
|
|
|
| 83 |
# If you want to get different output in same batch, you can set do_sample to True
|
| 84 |
output_texts = model.generate(prompts, output_length=max_output_length,top_k=30, top_p=0.85, temperature=0.35, repetition_penalty=1.2, do_sample=False)
|
| 85 |
|
|
|
|
| 100 |
|
| 101 |
3. 支持向量机(Support Vector Machine):支持向量机是一种监督学习方法,通常用于分类问题。它可以处理高维数据,并且具有较高的准确性。适用于需要对高维数据进行分类或回归的问题,例如图像识别、自然语言处理等。
|
| 102 |
|
|
|
|
| 103 |
## Citation
|
| 104 |
``` bibtex
|
| 105 |
@Misc{lyraChatGLM2023,
|
|
|
|
| 113 |
## Report bug
|
| 114 |
- start a discussion to report any bugs!--> https://huggingface.co/TMElyralab/lyraChatGLM/discussions
|
| 115 |
- report bug with a `[bug]` mark in the title.
|
|
|
|
|
|