Instructions to use jhghar/jh-xlam-2-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jhghar/jh-xlam-2-8b with Transformers:

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

pipe = pipeline("text-generation", model="jhghar/jh-xlam-2-8b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jhghar/jh-xlam-2-8b")
model = AutoModelForCausalLM.from_pretrained("jhghar/jh-xlam-2-8b", 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 jhghar/jh-xlam-2-8b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jhghar/jh-xlam-2-8b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jhghar/jh-xlam-2-8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jhghar/jh-xlam-2-8b

SGLang

How to use jhghar/jh-xlam-2-8b 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 "jhghar/jh-xlam-2-8b" \
    --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": "jhghar/jh-xlam-2-8b",
		"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 "jhghar/jh-xlam-2-8b" \
        --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": "jhghar/jh-xlam-2-8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jhghar/jh-xlam-2-8b with Docker Model Runner:
```
docker model run hf.co/jhghar/jh-xlam-2-8b
```

Merged XLAM-2-8b with Function Calling LoRA

This model is a merged version of Salesforce/Llama-xLAM-2-8b-fc-r with a custom LoRA adapter trained for function calling capabilities.

Model Details

Base Model: Salesforce/Llama-xLAM-2-8b-fc-r
Architecture: LlamaForCausalLM
Task: Function Calling
Training Type: LoRA Fine-tuning (merged)

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load the model and tokenizer
model = AutoModelForCausalLM.from_pretrained("jhghar/jh-xlam-2-8b")
tokenizer = AutoTokenizer.from_pretrained("jhghar/jh-xlam-2-8b")

# Example usage
prompt = "Your prompt here"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)

Training Details

Training Framework: PEFT (Parameter-Efficient Fine-Tuning)
Method: LoRA (Low-Rank Adaptation)
Dataset: Custom function calling dataset
Hardware: A100 GPUs

Limitations and Bias

This model inherits the limitations and biases from its base model (Salesforce/Llama-xLAM-2-8b-fc-r). Users should be aware of potential biases and evaluate the model's outputs accordingly.

Citation

If you use this model, please cite both the original Salesforce XLAM model and this adaptation.

License

This model is released under the Apache License, Version 2.0. See the LICENSE file for more details.

Downloads last month: 14

Model tree for jhghar/jh-xlam-2-8b

Adapters

1 model