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

Libraries

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

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

pipe = pipeline("text-generation", model="infly/INF-34B-Chat", 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-Chat", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "infly/INF-34B-Chat"
# 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-Chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

How to use infly/INF-34B-Chat 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-Chat" \
    --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-Chat",
		"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-Chat" \
        --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-Chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

stgzr commited on Jul 21, 2024

Commit

f0c363f

verified ·

1 Parent(s): a78918e

update README.md

Browse files

Files changed (1) hide show

README.md +1 -4

README.md CHANGED Viewed

@@ -71,7 +71,7 @@ We evaluate our model on several academic benchmarks then compare with other sim
 | HellaSwag(0-shot) |     82.03      |     81.57     |    83.32    |
-**Note:** To facilitate reproduction, the results of common benchmarks are generated by [OpenCompass](https://github.com/open-compass/opencompass) except humaneval and mbpp as we experience code timeout and postprocess issues. Besides, Usmle and CFA is evaluated using internal evaluation scripts.
 ### Chat Model
@@ -85,9 +85,6 @@ We present the performance results of our chat model and other LLM on various st
 | Arena-Hard |     24.2      |     42.6     |    43.1    |
 | GSM8K |     81.42      |     79.45     |    84.04    |
 | MATH |     42.28      |     54.06     |    51.48   |
-| USMLE |     58.70     |     55.84     |    79.70    |
-| CFA 2.0 |     35.5      |     42.5     |    62.75    |
 ### Long Context

 | HellaSwag(0-shot) |     82.03      |     81.57     |    83.32    |
+**Note:** To facilitate reproduction, the results of common benchmarks are generated by [OpenCompass](https://github.com/open-compass/opencompass) except humaneval and mbpp as we experience code timeout and postprocess issues.
 ### Chat Model
 | Arena-Hard |     24.2      |     42.6     |    43.1    |
 | GSM8K |     81.42      |     79.45     |    84.04    |
 | MATH |     42.28      |     54.06     |    51.48   |
 ### Long Context