Instructions to use avkr2502/mistral_7b_virtual_recruiter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use avkr2502/mistral_7b_virtual_recruiter with Transformers:

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

pipe = pipeline("text-generation", model="avkr2502/mistral_7b_virtual_recruiter")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("avkr2502/mistral_7b_virtual_recruiter")
model = AutoModelForCausalLM.from_pretrained("avkr2502/mistral_7b_virtual_recruiter", device_map="auto")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use avkr2502/mistral_7b_virtual_recruiter with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "avkr2502/mistral_7b_virtual_recruiter"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "avkr2502/mistral_7b_virtual_recruiter",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/avkr2502/mistral_7b_virtual_recruiter

SGLang

How to use avkr2502/mistral_7b_virtual_recruiter 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 "avkr2502/mistral_7b_virtual_recruiter" \
    --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": "avkr2502/mistral_7b_virtual_recruiter",
		"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 "avkr2502/mistral_7b_virtual_recruiter" \
        --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": "avkr2502/mistral_7b_virtual_recruiter",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use avkr2502/mistral_7b_virtual_recruiter with Docker Model Runner:
```
docker model run hf.co/avkr2502/mistral_7b_virtual_recruiter
```

Fine-Tuning , Adaptability and Status of Virtual Recruiter Model

by Sharoz01 - opened Jul 15, 2024

Discussion

Sharoz01

Jul 15, 2024

I came across your model on Hugging Face and I am considering using it for matching candidates with job openings on my platform. Before proceeding, I have a few questions to ensure it fits my use case and to understand its current status:

1.	What is the model fine-tuned to do specifically?

2.	How was the model fine-tuned?
•	What dataset(s) were used?

3. Is it easy to adapt the model to a slightly different task within the same domain, such as matching resumes with different types of job openings?

Do you think this model will be able to effectively assess candidates based on their resumes and match them with appropriate job openings based on their experiences and skills?

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