Agnuxo/Phi-3.5-mini-instruct-python_coding_assistant-GGUF_8bit

🐍 Phi 3.5 Mini Instruct Python Coding Assistant Gguf 8Bit

Python code generation specialist. 66+ downloads. Fully local.

---

🎯 Python-First Design

Fine-tuned exclusively for Python code generation with:

• 50,000+ Python scripts from GitHub
• 200,000 Stack Overflow Q&A pairs
• 15,000 Jupyter notebooks
• PEP 8 compliant output
• Type hints and docstrings

---

🚀 Quick Start

Via Ollama

ollama run Agnuxo/Phi-3.5-mini-instruct-python_coding_assistant-GGUF_8bit

Via Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "Agnuxo/Phi-3.5-mini-instruct-python_coding_assistant-GGUF_8bit",
    torch_dtype="auto", device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("Agnuxo/Phi-3.5-mini-instruct-python_coding_assistant-GGUF_8bit")

prompt = "Write a Python function to parse JSON and validate schema"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.2)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

---

🔗 P2PCLAW Ecosystem

Component	Purpose	Link
CAJAL-9B	Scientific papers	HF Model
CAJAL-4B	Lightweight papers	HF Model
BenchClaw	Code evaluation	HF Space
P2PCLAW	Research network	Website

---

👤 Author

Francisco Angulo de Lafuente (Agnuxo1) · ORCID: 0009-0001-1634-7063

---

Built with 🔥 by the P2PCLAW Collective