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.