Xlam 2 3b Fc R GGUF

🚀 xLAM-2-3b-fc-r GGUF Models

This project offers xLAM-2-3b-fc-r GGUF models. These models are designed for text generation tasks, with features like function calling and tool use, and are based on advanced techniques and frameworks.

🚀 Quick Start

Prerequisites

• Transformers 4.46.1 (or later)
• PyTorch 2.5.1+cu124 (or later)
• Datasets 3.1.0 (or later)
• Tokenizers 0.20.3 (or later)

Basic Usage with Huggingface Chat Template

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("Salesforce/Llama-xLAM-2-3b-fc-r")
model = AutoModelForCausalLM.from_pretrained("Salesforce/Llama-xLAM-2-3b-fc-r", torch_dtype=torch.bfloat16, device_map="auto")

# Example conversation with a tool call
messages = [
    {"role": "user", "content": "Hi, how are you?"},
    {"role": "assistant", "content": "Thanks. I am doing well. How can I help you?"},
    {"role": "user", "content": "What's the weather like in London?"},
]

tools = [
    {
        "name": "get_weather",
        "description": "Get the current weather for a location",
        "parameters": {
            "type": "object",
            "properties": {
                "location": {"type": "string", "description": "The city and state, e.g. San Francisco, CA"},
                "unit": {"type": "string", "enum": ["celsius", "fahrenheit"], "description": "The unit of temperature to return"}
            },
            "required": ["location"]
        }
    }
]

print("====== prompt after applying chat template ======")
print(tokenizer.apply_chat_template(messages, tools=tools, add_generation_prompt=True, tokenize=False))

inputs = tokenizer.apply_chat_template(messages, tools=tools, add_generation_prompt=True, return_dict=True, return_tensors="pt")
input_ids_len = inputs["input_ids"].shape[-1] # Get the length of the input tokens
inputs = {k: v.to(model.device) for k, v in inputs.items()}
print("====== model response ======")
outputs = model.generate(**inputs, max_new_tokens=256)
generated_tokens = outputs[:, input_ids_len:] # Slice the output to get only the newly generated tokens
print(tokenizer.decode(generated_tokens[0], skip_special_tokens=True))

Using vLLM for Inference

Setup and Serving

1. Install vLLM with the required version:

pip install "vllm>=0.6.5"

2. Download the tool parser plugin to your local path:

wget https://huggingface.co/Salesforce/xLAM-2-1b-fc-r/raw/main/xlam_tool_call_parser.py

3. Start the OpenAI API-compatible endpoint:

vllm serve Salesforce/xLAM-2-1b-fc-r \
  --enable-auto-tool-choice \
  --tool-parser-plugin ./xlam_tool_call_parser.py \
  --tool-call-parser xlam \
  --tensor-parallel-size 1

Testing with OpenAI API

import openai
import json

# Configure the client to use your local vLLM endpoint
client = openai.OpenAI(
    base_url="http://localhost:8000/v1",  # Default vLLM server URL
    api_key="empty"  # Can be any string
)

# Define a tool/function
tools = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get the current weather for a location",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {
                        "type": "string",
                        "description": "The city and state, e.g. San Francisco, CA"
                    },
                    "unit": {
                        "type": "string",
                        "enum": ["celsius", "fahrenheit"],
                        "description": "The unit of temperature to return"
                    }
                },
                "required": ["location"]
            }
        }
    }
]

# Create a chat completion
response = client.chat.completions.create(
    model="Salesforce/xLAM-2-1b-fc-r",  # Model name doesn't matter, vLLM uses the served model
    messages=[
        {"role": "system", "content": "You are a helpful assistant that can use tools."},
        {"role": "user", "content": "What's the weather like in San Francisco?"}
    ],
    tools=tools,
    tool_choice="auto"
)

# Print the response
print("Assistant's response:")
print(json.dumps(response.model_dump(), indent=2))

✨ Features

• Function Calling: The models are fine-tuned for function calling tasks, enabling interaction with live network services.
• Multi-turn Conversation: Capable of handling multi-turn conversations, providing a more natural and intuitive user experience.
• Tool Use: Can utilize various tools, such as performing Nmap security scans, quantum-readiness checks, and network monitoring tasks.
• High Performance: Achieves state-of-the-art performance on benchmarks like BFCL and œÑ-bench, outperforming many frontier models.

📦 Installation

Framework versions

• Transformers 4.46.1 (or later)
• PyTorch 2.5.1+cu124 (or later)
• Datasets 3.1.0 (or later)
• Tokenizers 0.20.3 (or later)

💻 Usage Examples

Basic Usage with Huggingface Chat Template

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("Salesforce/Llama-xLAM-2-3b-fc-r")
model = AutoModelForCausalLM.from_pretrained("Salesforce/Llama-xLAM-2-3b-fc-r", torch_dtype=torch.bfloat16, device_map="auto")

# Example conversation with a tool call
messages = [
    {"role": "user", "content": "Hi, how are you?"},
    {"role": "assistant", "content": "Thanks. I am doing well. How can I help you?"},
    {"role": "user", "content": "What's the weather like in London?"},
]

tools = [
    {
        "name": "get_weather",
        "description": "Get the current weather for a location",
        "parameters": {
            "type": "object",
            "properties": {
                "location": {"type": "string", "description": "The city and state, e.g. San Francisco, CA"},
                "unit": {"type": "string", "enum": ["celsius", "fahrenheit"], "description": "The unit of temperature to return"}
            },
            "required": ["location"]
        }
    }
]

print("====== prompt after applying chat template ======")
print(tokenizer.apply_chat_template(messages, tools=tools, add_generation_prompt=True, tokenize=False))

inputs = tokenizer.apply_chat_template(messages, tools=tools, add_generation_prompt=True, return_dict=True, return_tensors="pt")
input_ids_len = inputs["input_ids"].shape[-1] # Get the length of the input tokens
inputs = {k: v.to(model.device) for k, v in inputs.items()}
print("====== model response ======")
outputs = model.generate(**inputs, max_new_tokens=256)
generated_tokens = outputs[:, input_ids_len:] # Slice the output to get only the newly generated tokens
print(tokenizer.decode(generated_tokens[0], skip_special_tokens=True))

Using vLLM for Inference

Setup and Serving

pip install "vllm>=0.6.5"
wget https://huggingface.co/Salesforce/xLAM-2-1b-fc-r/raw/main/xlam_tool_call_parser.py
vllm serve Salesforce/xLAM-2-1b-fc-r \
  --enable-auto-tool-choice \
  --tool-parser-plugin ./xlam_tool_call_parser.py \
  --tool-call-parser xlam \
  --tensor-parallel-size 1

Testing with OpenAI API

import openai
import json

# Configure the client to use your local vLLM endpoint
client = openai.OpenAI(
    base_url="http://localhost:8000/v1",  # Default vLLM server URL
    api_key="empty"  # Can be any string
)

# Define a tool/function
tools = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get the current weather for a location",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {
                        "type": "string",
                        "description": "The city and state, e.g. San Francisco, CA"
                    },
                    "unit": {
                        "type": "string",
                        "enum": ["celsius", "fahrenheit"],
                        "description": "The unit of temperature to return"
                    }
                },
                "required": ["location"]
            }
        }
    }
]

# Create a chat completion
response = client.chat.completions.create(
    model="Salesforce/xLAM-2-1b-fc-r",  # Model name doesn't matter, vLLM uses the served model
    messages=[
        {"role": "system", "content": "You are a helpful assistant that can use tools."},
        {"role": "user", "content": "What's the weather like in San Francisco?"}
    ],
    tools=tools,
    tool_choice="auto"
)

# Print the response
print("Assistant's response:")
print(json.dumps(response.model_dump(), indent=2))

📚 Documentation

Model Generation Details

This model was generated using llama.cpp at commit 6adc3c3e.

Quantization Beyond the IMatrix

The author has been experimenting with a new quantization approach that selectively elevates the precision of key layers beyond what the default IMatrix configuration provides. By using the --tensor-type option in llama.cpp to manually "bump" important layers to higher precision, it significantly improves precision for a given quantization level, although it does increase model file size. You can see the implementation here: Layer bumping with llama.cpp

Model Series

*Note: The default context length for Qwen-2.5-based models is 32k, but you can use techniques like YaRN (Yet Another Recursive Network) to achieve maximum 128k context length. Please refer to here for more details.

Benchmark Results

Berkeley Function-Calling Leaderboard (BFCL v3)

Performance comparison of different models on BFCL leaderboard. The rank is based on the overall accuracy, which is a weighted average of different evaluation categories. "FC" stands for function-calling mode in contrast to using a customized "prompt" to extract the function calls.

τ-bench Benchmark

Success Rate (pass@1) on τ-bench benchmark averaged across at least 5 trials. Our xLAM-2-70b-fc-r model achieves an overall success rate of 56.2% on τ-bench, significantly outperforming the base Llama 3.1 70B Instruct model (38.2%) and other open-source models like DeepSeek v3 (40.6%). Notably, our best model even outperforms proprietary models such as GPT-4o (52.9%) and approaches the performance of more recent models like Claude 3.5 Sonnet (new) (60.1%).

Pass^k curves measuring the probability that all 5 independent trials succeed for a given task, averaged across all tasks for τ-retail (left) and τ-airline (right) domains. Higher values indicate better consistency of the models.

Ethical Considerations

This release is for research purposes only in support of an academic paper. Our models, datasets, and code are not specifically designed or evaluated for all downstream purposes. We strongly recommend users evaluate and address potential concerns related to accuracy, safety, and fairness before deploying this model. We encourage users to consider the common limitations of AI, comply with applicable laws, and leverage best practices when selecting use cases, particularly for high-risk scenarios where errors or misuse could significantly impact people's lives, rights, or safety. For further guidance on use cases, refer to our AUP and AI AUP.

Model Licenses

For all Llama relevant models, please also follow corresponding Llama license and terms. Meta Llama 3 is licensed under the Meta Llama 3 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.

Citation

If you use our model or dataset in your work, please cite our paper:

@article{prabhakar2025apigen,
  title={APIGen-MT: Agentic PIpeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay},
  author={Prabhakar, Akshara and Liu, Zuxin and Zhu, Ming and Zhang, Jianguo and Awalgaonkar, Tulika and Wang, Shiyu and Liu, Zhiwei and Chen, Haolin and Hoang, Thai and others},
  journal={arXiv preprint arXiv:2504.03601},
  year={2025}
}

Additionally, please check our other awesome related works regarding xLAM series and consider citing them as well:

@article{zhang2025actionstudio,
  title={ActionStudio: A Lightweight Framework for Data and Training of Action Models},
  author={Zhang, Jianguo and Hoang, Thai and Zhu, Ming and Liu, Zuxin and Wang, Shiyu and Awalgaonkar, Tulika and Prabhakar, Akshara and Chen, Haolin and Yao, Weiran and Liu, Zhiwei and others},
  journal={arXiv preprint arXiv:2503.22673},
  year={2025}
}

@article{zhang2024xlam,
  title={xLAM: A Family of Large Action Models to Empower AI Agent Systems},
  author={Zhang, Jianguo and Lan, Tian and Zhu, Ming and Liu, Zuxin and Hoang, Thai and Kokane, Shirley and Yao, Weiran and Tan, Juntao and Prabhakar, Akshara and Chen, Haolin and others},
  journal={arXiv preprint arXiv:2409.03215},
  year={2024}
}

@article{liu2024apigen,
  title={Apigen: Automated pipeline for generating verifiable and diverse function-calling datasets},
  author={Liu, Zuxin and Hoang, Thai and Zhang, Jianguo and Zhu, Ming and Lan, Tian and Tan, Juntao and Yao, Weiran and Liu, Zhiwei and Feng, Yihao and RN, Rithesh and others},
  journal={Advances in Neural Information Processing Systems},
  volume={37},
  pages={54463--54482},
  year={2024}
}

@article{zhang2024agentohana,
  title={AgentOhana: Design Unified Data and Training Pipeline for Effective Agent Learning},
  author={Zhang, Jianguo and Lan, Tian and Murthy, Rithesh and Liu, Zhiwei and Yao, Weiran and Tan, Juntao and Hoang, Thai and Yang, Liangwei and Feng, Yihao and Liu, Zuxin and others},
  journal={arXiv preprint arXiv:2402.15506},
  year={2024}
}

🔧 Technical Details

Model Generation

This model was generated using llama.cpp at commit 6adc3c3e.

Quantization

The author has been experimenting with a new quantization approach that selectively elevates the precision of key layers beyond what the default IMatrix configuration provides. By using the --tensor-type option in llama.cpp to manually "bump" important layers to higher precision, it significantly improves precision for a given quantization level, although it does increase model file size. You can see the implementation here: Layer bumping with llama.cpp

📄 License

The model is licensed under the cc-by-nc-4.0 license. For all Llama relevant models, please also follow corresponding Llama license and terms. Meta Llama 3 is licensed under the Meta Llama 3 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.