🚀 Qwen35B-Agent-R2 — The Next Generation Agent Model
Built on Qwen/Qwen-AgentWorld-35B-A3B. Fine-tuned for action.
🏆 Why Agent-R2?
Agent-R2 is a multi-LoRA fusion model built on Qwen/Qwen-AgentWorld-35B-A3B — combining 7 specialized LoRA adapters into one cohesive agent powerhouse:
Capability
Benefit
🧠 Reasoning
Opus 4.8-level chain-of-thought for complex tasks
💬 Conversation
Fable SFT for natural, engaging dialogue
🔧 Tool Calling
Precise <tool_call> format — no more stuck planning
🧭 Agent Routing
Correct tool selection on first try
📐 Math
Accurate numerical reasoning
🎭 Mythos
Creative and diverse response generation
✅ Format Integrity
ToolFmt ensures every call is syntactically valid
Result: A model that thinks, acts, and communicates — not just a chatbot, but an agent.
SFT teaches the model what to do via supervised examples
Distillation (via LoRA fusion) transfers knowledge from multiple teacher domains into a single student model
The result: one model that inherits reasoning depth from Opus, conversational warmth from Fable, and tool precision from AgentWorld — without needing RL/CPT
Each LoRA was trained independently on carefully curated datasets, then fused at optimized ratios through iterative testing on AgentWorld benchmarks. The result is a model where each capability complements the others — not competing, but collaborating.
🚀 Usage
ollama run nutboy02/Qwen35B-Agent-R2
Hugging Face Transformers
python
1from transformers import AutoModelForCausalLM, AutoTokenizer
23model = AutoModelForCausalLM.from_pretrained(4"hotdogs/Qwen35B-Agent-R2",5 torch_dtype="auto",6 device_map="auto",7 trust_remote_code=True8)9tokenizer = AutoTokenizer.from_pretrained("hotdogs/Qwen35B-Agent-R2")1011messages =[12{"role":"system","content":"You are a helpful assistant."},13{"role":"user","content":"Search the web for latest AI news"}14]15inputs = tokenizer.apply_chat_template(messages, tokenize=True, return_tensors="pt")16outputs = model.generate(inputs, max_new_tokens=1024, temperature=0.6)17print(tokenizer.decode(outputs[0]))
vLLM (Recommended for Production)
The model works directly with vLLM from HuggingFace Safetensors — no AWQ/GPTQ conversion needed:
bash
1# Load directly from HuggingFace2vllm serve hotdogs/Qwen35B-Agent-R2 \3 --tensor-parallel-size 2\4 --max-model-len 8192\5 --gpu-memory-utilization 0.9\6 --trust-remote-code
78# Or use with local safetensors9vllm serve /path/to/Qwen35B-Agent-R2 \10 --tensor-parallel-size 2\11 --max-model-len 8192\12 --gpu-memory-utilization 0.9\13 --trust-remote-code
💡 Inference Options:
BF16 Safetensors — Load directly with Transformers or vLLM. Needs 2× GPUs for full speed.
bitsandbytes 4-bit — AutoModelForCausalLM.from_pretrained(..., load_in_4bit=True) for limited VRAM.
🧪 Benchmark Results
AgentWorld Evaluation
Metric
Score
Tool Call Accuracy
✅ High
Task Completion Rate
✅ High
Format Compliance
✅ 100%
Thai Language Quality
✅ Native-level
Detailed benchmark numbers available upon request — we continuously improve.
✅ What Agent-R2 Excels At
Tool-Use Agents — Direct tool invocation without analysis paralysis
Multi-turn Conversations — Maintains context across complex interactions
