rchow93/crewai-qwen3-8b-gguf
056
CrewAI Code Generation - Qwen3 8B (GGUF)
Fine-tuned Qwen3-8B models for generating CrewAI multi-agent code from natural language descriptions.
Models Available
V2 Thinking Models (Recommended)
V2 Improvements:
- Native Qwen3 chat template (ChatML format)
- Higher LoRA rank (r=32 vs r=16)
- Thinking mode with reasoning tags
- Better structured outputs
V1 Models (Legacy)
Usage with Ollama
- Download the GGUF file
- Create a Modelfile:
FROM ./crewai-qwen3-8b-thinking-v2-q4_k_m.gguf
TEMPLATE """{{- if .System }}
<|im_start|>system
{{ .System }}<|im_end|>
{{ end }}
<|im_start|>user
{{ .Prompt }}<|im_end|>
<|im_start|>assistant
"""
SYSTEM """You are a CrewAI code generation expert. When given a task description and required inputs, generate complete, working CrewAI Python code that includes:
- All necessary imports (crewai, crewai_tools)
- Agent definitions with roles, goals, backstories, and tools
- Task definitions with proper context dependencies
- Crew instantiation with appropriate process type
- Kickoff code with the provided inputs
Think through the problem step by step before generating code."""
PARAMETER temperature 0.7
PARAMETER top_p 0.9
PARAMETER num_ctx 8192
PARAMETER stop "<|im_end|>"
PARAMETER stop "<|im_start|>"- Create and run:
ollama create crewai-qwen3-8b -f Modelfile
ollama run crewai-qwen3-8bExample Prompt
Create a CrewAI crew for analyzing competitor websites.
Required inputs:
- competitor_urls: list of URLs to analyze
- analysis_focus: what aspects to focus onTraining Details
- Base Model: Qwen/Qwen3-8B
- Fine-tuning: Unsloth + QLoRA (r=32, alpha=32)
- Dataset: 2,500 CrewAI code examples
- Training: 3 epochs on RTX 4090
License
Apache 2.0 (same as base Qwen3 model)
