Instructions to use infly/INF-34B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use infly/INF-34B-Base with Transformers:

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

pipe = pipeline("text-generation", model="infly/INF-34B-Base", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("infly/INF-34B-Base", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use infly/INF-34B-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "infly/INF-34B-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "infly/INF-34B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/infly/INF-34B-Base

SGLang

How to use infly/INF-34B-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 "infly/INF-34B-Base" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "infly/INF-34B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "infly/INF-34B-Base" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "infly/INF-34B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use infly/INF-34B-Base with Docker Model Runner:
```
docker model run hf.co/infly/INF-34B-Base
```

stgzr commited on Jul 25, 2024

Commit

0a5f7fb

verified ·

1 Parent(s): 4897769

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -2

README.md CHANGED Viewed

@@ -19,7 +19,7 @@ license_link: LICENSE
 </div>
 <p align="center">
-  <a href="https://www.infly.cn/en/research"><b>Paper Link</b></a>
 </p>
@@ -132,9 +132,11 @@ Motivated by the idea of first training on relatively large but less polished co
 ### Installation
-Install the dependencies for `Python >= 3.8` by running the following command:
 ```shell
 pip install -r requirements.txt
 ```

 </div>
 <p align="center">
+  <a href="https://s.infly.cn/f/img/pdf/inf_34b_tech_report.pdf"><b>Paper Link</b></a>
 </p>
 ### Installation
+Please clone our [GitHub](https://github.com/infly-ai/INF-LLM), and install the dependencies for `Python >= 3.8` by running the following command:
 ```shell
+git clone https://github.com/infly-ai/INF-LLM
+cd INF-LLM
 pip install -r requirements.txt
 ```