Instructions to use linjc16/Panacea-7B-Chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use linjc16/Panacea-7B-Chat with Transformers:

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

pipe = pipeline("text-generation", model="linjc16/Panacea-7B-Chat")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("linjc16/Panacea-7B-Chat")
model = AutoModelForCausalLM.from_pretrained("linjc16/Panacea-7B-Chat")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use linjc16/Panacea-7B-Chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "linjc16/Panacea-7B-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": "linjc16/Panacea-7B-Chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/linjc16/Panacea-7B-Chat

SGLang

How to use linjc16/Panacea-7B-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 "linjc16/Panacea-7B-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": "linjc16/Panacea-7B-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 "linjc16/Panacea-7B-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": "linjc16/Panacea-7B-Chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use linjc16/Panacea-7B-Chat with Docker Model Runner:
```
docker model run hf.co/linjc16/Panacea-7B-Chat
```

TypeError when trying to run model with Transformers

by afmelani - opened Sep 27, 2024

Discussion

afmelani

Sep 27, 2024

Hi!
I am trying to use this model with the transformers library but even with just using the code snippet provided I have not been able to get it working. I keep getting the following error:

TypeError: stat: path should be string, bytes, os.PathLike or integer, not NoneType.

I have tried upgrading libraries but it has not been possible to find a solution. I would appreciate if someone could give me some clue on what could be happening.

Thanks in advance!

linjc16

Owner Sep 27, 2024

•

edited Sep 27, 2024

Hi!

You could try the following code to load the model.

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = 'linjc16/Panacea-7B-Chat'

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_id)

HSinghHuggingFace

Mar 26, 2025

Panacea has TrialPanorama for benchmarking.
Has anyone tried it for any other model to evaluate the metrics?

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment