FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth

This model is a fine-tuned version of FastContext-1.0-4B-SFT optimized for function calling using Unsloth for 2x faster training and 60% less VRAM.

Trained on the Salesforce/xlam-function-calling-60k dataset, which contains 60,000 function calling examples with queries, tool definitions, and structured answers.

Overview

Training Configuration

SFT + LoRA Settings

LoRA Configuration

Dataset

Hardware

Training Outcome

Usage

Quick Start (Transformers)

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

messages = [
    {"role": "user", "content": "Check if the numbers 8 and 1233 are powers of two."}
]

text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)

outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.7, do_sample=True)
response = tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)
print(response)

Using with Unsloth (Fastest)

from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained(
    "ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth",
    max_seq_length=2048,
    load_in_4bit=True,
)

4-bit Quantized Inference

from transformers import AutoModelForCausalLM, BitsAndBytesConfig
import torch

quantization_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_compute_dtype=torch.bfloat16,
    bnb_4bit_use_double_quant=True,
    bnb_4bit_quant_type="nf4",
)

model = AutoModelForCausalLM.from_pretrained(
    "ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth",
    quantization_config=quantization_config,
    device_map="auto",
)

GGUF Versions

Quantized GGUF versions for CPU and edge inference are available at: FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-GGUF

Using with Ollama

ollama pull hf.co/ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-GGUF:Q4_K_M
ollama run hf.co/ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-GGUF:Q4_K_M "Check if the numbers 8 and 1233 are powers of two."

Using with llama.cpp

./llama-cli -m FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-Q4_K_M.gguf -p "Check if the numbers 8 and 1233 are powers of two." -n 512

Limitations

• Language: Primarily trained on English data
• Knowledge Cutoff: Limited to base model's training data cutoff
• Hallucinations: May generate plausible-sounding but incorrect information
• Context Length: Fine-tuned with 2,048 token context window
• Safety: Not extensively safety-tuned; use with appropriate guardrails

Training Framework Versions

Citation

@misc{ermiaazarkhalili_fastcontext_4b_sft_base_function_calling_xlam_unsloth,
    author = {ermiaazarkhalili},
    title = {FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth: Fine-tuned FastContext-1.0-4B-SFT with Unsloth},
    year = {2026},
    publisher = {Hugging Face},
    howpublished = {\url{https://huggingface.co/ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth}}
}

Acknowledgments

• Unsloth for 2x faster fine-tuning
• Base model developers (microsoft)
• Hugging Face TRL Team for the training library
• Salesforce xLAM for the function calling dataset
• Compute Canada / DRAC for HPC resources