Instructions to use hpcai-tech/Colossal-LLaMA-2-7b-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hpcai-tech/Colossal-LLaMA-2-7b-base with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="hpcai-tech/Colossal-LLaMA-2-7b-base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hpcai-tech/Colossal-LLaMA-2-7b-base")
model = AutoModelForCausalLM.from_pretrained("hpcai-tech/Colossal-LLaMA-2-7b-base", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use hpcai-tech/Colossal-LLaMA-2-7b-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hpcai-tech/Colossal-LLaMA-2-7b-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hpcai-tech/Colossal-LLaMA-2-7b-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/hpcai-tech/Colossal-LLaMA-2-7b-base

SGLang

How to use hpcai-tech/Colossal-LLaMA-2-7b-base with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "hpcai-tech/Colossal-LLaMA-2-7b-base" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hpcai-tech/Colossal-LLaMA-2-7b-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "hpcai-tech/Colossal-LLaMA-2-7b-base" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hpcai-tech/Colossal-LLaMA-2-7b-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use hpcai-tech/Colossal-LLaMA-2-7b-base with Docker Model Runner:
```
docker model run hf.co/hpcai-tech/Colossal-LLaMA-2-7b-base
```

Camille7777 commited on Sep 24, 2023

Commit

fbf819d

1 Parent(s): 0fed5a1

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -18,7 +18,7 @@ language:
 </div>
 <div align="center">
-  ｜<a href="https://github.com/hpcaitech/Colossal-LLaMA-2/" target="_blank">🔥 GitHub </a> |
   <a href="https://github.com/baichuan-inc/Baichuan-7B/blob/main/media/wechat.jpeg?raw=true" target="_blank">😊 Slack</a>｜
   <a href="https://github.com/baichuan-inc/Baichuan-7B/blob/main/media/wechat.jpeg?raw=true" target="_blank">💬 WeChat</a>｜
 </div>
@@ -193,7 +193,7 @@ Our experiments have revealed that the distributions within the training dataset
 In an effort to achieve a more balanced distribution and exert control over the dataset's ordering, we have adopted a method where we divide each sub-dataset into discrete bins. These bins are then combined to construct individual data buckets, with one bin contributed by each sub-dataset.
-For more details, please refer to our [Github](https://github.com/hpcaitech/Colossal-LLaMA-2).
 # Limitations

 </div>
 <div align="center">
+  ｜<a href="https://github.com/hpcaitech/ColossalAI/tree/main/applications/Colossal-LLaMA-2" target="_blank">🔥 GitHub </a> |
   <a href="https://github.com/baichuan-inc/Baichuan-7B/blob/main/media/wechat.jpeg?raw=true" target="_blank">😊 Slack</a>｜
   <a href="https://github.com/baichuan-inc/Baichuan-7B/blob/main/media/wechat.jpeg?raw=true" target="_blank">💬 WeChat</a>｜
 </div>
 In an effort to achieve a more balanced distribution and exert control over the dataset's ordering, we have adopted a method where we divide each sub-dataset into discrete bins. These bins are then combined to construct individual data buckets, with one bin contributed by each sub-dataset.
+For more details, please refer to our [Github](https://github.com/hpcaitech/ColossalAI/tree/main/applications/Colossal-LLaMA-2).
 # Limitations