The model was developed through sequential fine-tuning, followed by a Direct Preference Optimization (DPO) post-training stage to improve alignment, coherence, and reasoning accuracy.

Highlights

Post-trained with DPO using chosen/rejected pairs for better alignment
Excellent balance between tool use, code generation, and reasoning

🚀 Direct Use

Qwen3.5-4B-AgentCoder can be used directly for:

✅ Tool calling in complex reasoning tasks
✅ Code generation for Python, JS, and other languages
✅ Multi-domain reasoning (math, logic, Q&A)

⚠️ Out-of-Scope Use

❌ Highly sensitive or confidential data
❌ Domains requiring expert-level specialization
❌ Tasks where full explainability is mandatory

💻 Getting Started

python

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model_name = "br1-pist/Qwen3.5-4B-AgentCoder"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype="auto",
device_map="auto"
)
prompt = "Give me a short introduction to large language models."
messages = [{"role": "user", "content": prompt}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
generated_ids = model.generate(**model_inputs, max_new_tokens=1024)
output = tokenizer.decode(generated_ids[0], skip_special_tokens=True)
print(output)

🧠 Training Details

Training Procedure

Phase 1 — Post-Training - Direct Preference Optimization (DPO)

After sequential fine-tuning, the model underwent a DPO phase to enhance response alignment, reasoning robustness, and factual consistency.

Learning rate: 3e-6
Batch size: 1
Gradient accumulation: 4
Epochs: 1
Beta: 0.1
Loss type: sigmoid
Warmup steps: 27
Sequence length: ~2.5K tokens

DPO Data

~2.5K chosen/rejected response pairs
Rejected samples synthetically generated to represent poor or incoherent answers
Chosen samples tagged from real conversations

Objective

Encourage the model to prefer chosen completions
Improve clarity, correctness, and helpfulness
Reduce hallucinations and verbosity

🖥️ Technical Specifications

Model Architecture

Model type: Causal language model
Parameters: 4.0B
Context length: ~264K tokens
Thinking mode: Enabled

Compute Infrastructure

Hardware

GPU: NVIDIA H100 (80 GB VRAM)
System RAM: 2 TiB
Memory per vCPU: 10.67 GiB

Software

Python: 3.12
Transformers: 5.3.0
Libraries: bitsandbytes, safetensors, torch, trl, scikit-learn, tokenizers, psutil, py7zr

🧾 Citation

BibTeX

bibtex

@article{qwen3.5-4b-thinking-2507-toolcode,
  title={Qwen3.5-4B-AgentCoder: A Fine-Tuned Model for Enhanced Tool Calling, Code Generation, and Reasoning},
  author={Bruno Pistone},
  year={2025},
  journal={Hugging Face Model Hub}
}

APA

Bruno Pistone. (2026). Qwen3.5-4B-AgentCoder: A Fine-Tuned Model for Enhanced Tool Calling, Code Generation, and Reasoning. Hugging Face Model Hub. https://huggingface.co/br1-pist/Qwen3.5-4B-AgentCoder

🧭 Recommendations

Tool use accuracy depends on task complexity
Code generation may occasionally produce minor syntax issues
Reasoning strongest in structured, logical, and mathematical contexts
Avoid using this model for confidential or safety-critical applications

🧠 Qwen3.5-4B-AgentCoder — created by Bruno Pistone
Enhanced reasoning, tool calling, and code generation — refined with DPO alignment