Instructions to use hotdogs/Qwen35B-Agent-R2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hotdogs/Qwen35B-Agent-R2 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="hotdogs/Qwen35B-Agent-R2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hotdogs/Qwen35B-Agent-R2")
model = AutoModelForCausalLM.from_pretrained("hotdogs/Qwen35B-Agent-R2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use hotdogs/Qwen35B-Agent-R2 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="hotdogs/Qwen35B-Agent-R2",
	filename="GGUF/Qwen35B-Agent-R2-F16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use hotdogs/Qwen35B-Agent-R2 with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf hotdogs/Qwen35B-Agent-R2:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf hotdogs/Qwen35B-Agent-R2:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf hotdogs/Qwen35B-Agent-R2:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf hotdogs/Qwen35B-Agent-R2:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf hotdogs/Qwen35B-Agent-R2:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf hotdogs/Qwen35B-Agent-R2:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf hotdogs/Qwen35B-Agent-R2:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf hotdogs/Qwen35B-Agent-R2:Q4_K_M

Use Docker

docker model run hf.co/hotdogs/Qwen35B-Agent-R2:Q4_K_M

LM Studio
Jan

vLLM

How to use hotdogs/Qwen35B-Agent-R2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hotdogs/Qwen35B-Agent-R2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hotdogs/Qwen35B-Agent-R2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/hotdogs/Qwen35B-Agent-R2:Q4_K_M

SGLang

How to use hotdogs/Qwen35B-Agent-R2 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "hotdogs/Qwen35B-Agent-R2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hotdogs/Qwen35B-Agent-R2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "hotdogs/Qwen35B-Agent-R2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hotdogs/Qwen35B-Agent-R2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use hotdogs/Qwen35B-Agent-R2 with Ollama:
```
ollama run hf.co/hotdogs/Qwen35B-Agent-R2:Q4_K_M
```

Unsloth Studio

How to use hotdogs/Qwen35B-Agent-R2 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for hotdogs/Qwen35B-Agent-R2 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for hotdogs/Qwen35B-Agent-R2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for hotdogs/Qwen35B-Agent-R2 to start chatting

How to use hotdogs/Qwen35B-Agent-R2 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf hotdogs/Qwen35B-Agent-R2:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "hotdogs/Qwen35B-Agent-R2:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use hotdogs/Qwen35B-Agent-R2 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf hotdogs/Qwen35B-Agent-R2:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default hotdogs/Qwen35B-Agent-R2:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use hotdogs/Qwen35B-Agent-R2 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf hotdogs/Qwen35B-Agent-R2:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "hotdogs/Qwen35B-Agent-R2:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use hotdogs/Qwen35B-Agent-R2 with Docker Model Runner:
```
docker model run hf.co/hotdogs/Qwen35B-Agent-R2:Q4_K_M
```

Lemonade

How to use hotdogs/Qwen35B-Agent-R2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull hotdogs/Qwen35B-Agent-R2:Q4_K_M

Run and chat with the model

lemonade run user.Qwen35B-Agent-R2-Q4_K_M

List all available models

lemonade list

Qwen35B-Agent-R2 / README.md

hotdogs

Update README.md

24accd4 verified about 8 hours ago

preview code

Raw

History Blame Contribute Delete

8.58 kB

	---
	license: agpl-3.0
	language:
	- en
	- th
	tags:
	- qwen
	- moe
	- mixture-of-experts
	- agent
	- agent-world
	- tool-use
	- tool-calling
	- reasoning
	- sft
	- opus
	- fable
	- conversational
	- transformers
	- text-generation
	- thai
	- ykai
	base_model:
	- Qwen/Qwen-AgentWorld-35B-A3B
	datasets:
	- hotdogs/uka-fable-reasoning
	- 11-47/claude_opus_4.8_max_thinking_5k_v2
	- cx-cmu/agent_trajectories
	library_name: transformers
	pipeline_tag: text-generation
	---

	<p align="center">
	<img src="https://img.shields.io/badge/license-AGPL--3.0-red">
	<img src="https://img.shields.io/badge/Qwen3.6-35B%20A3B-blue">
	<img src="https://img.shields.io/badge/MoE-256%20experts-orange">
	<img src="https://img.shields.io/badge/Multi--LoRA-Fusion-green">
	<img src="https://img.shields.io/badge/Agent-R2-black">
	</p>

	<p align="center"><b>🚀 Qwen35B-Agent-R2 — The Next Generation Agent Model</b></p>

	<p align="center"><i>Built on Qwen/Qwen-AgentWorld-35B-A3B. Fine-tuned for action.</i></p>




	## 🏆 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.

	## 🔍 What Makes Agent-R2 Different?

	\| Aspect \| Other Models \| Agent-R2 \|
	\|--------\|-------------\|:------------:\|
	\| Tool Call Format \| ❌ Often malformed or hallucinated \| ✅ Guaranteed valid `<tool_call>` JSON \|
	\| Planning vs Action \| ❌ Thinks forever, never acts \| ✅ Decides → Calls tool → Done \|
	\| Thai Support \| ❌ Poor or tokenization issues \| ✅ Native Thai + English bilingual \|
	\| MoE Efficiency \| ❌ Full 35B always active \| ✅ Only ~3B active per token \|
	\| Multi-LoRA Fusion \| ❌ Single adapter or limited \| ✅ 7 LoRAs fused into one coherent model \|

	## 📊 Architecture

	\| Parameter \| Value \|
	\|-----------\|:-----:\|
	\| Base Model \| [Qwen/Qwen-AgentWorld-35B-A3B](https://huggingface.co/Qwen/Qwen-AgentWorld-35B-A3B) \|
	\| Architecture \| Qwen3.5 MoE \|
	\| Hidden Size \| 2,048 \|
	\| Expert Count \| 256 (Mixture of Experts) \|
	\| Active Experts \| 8 per token (~3B active params) \|
	\| Parameters \| ~35B total \|
	\| Context Length \| 8,192 tokens \|
	\| Precision \| BF16 (Safetensors) \|
	\| Format \| ChatML \|

	## 🧬 Training Pipeline: SFT + Distillation

	Agent-R2 is built using a two-stage SFT + Distillation approach:

	### Stage 1: Supervised Fine-Tuning (SFT) 🏋️

	Each LoRA adapter was trained via SFT on a specialized dataset:

	\| Adapter \| Method \| Data \| Purpose \|
	\|---------\|:------:\|:----:\|---------\|
	\| Opus SFT \| SFT \| 6,956 rows (Claude Opus 4.8 reasoning) \| Learn deep chain-of-thought \|
	\| Fable SFT \| SFT \| 3,376 rows (Fable conversational) \| Natural dialogue \|
	\| Agent Routing \| SFT \| AgentWorld trajectories \| Tool selection logic \|
	\| Tool Call \| SFT \| 8,653 rows (agent trajectories) \| Proper invocation format \|
	\| Math Fix \| SFT \| Math reasoning data \| Accurate computation \|
	\| Mythos \| SFT \| Creative writing data \| Response diversity \|
	\| ToolFmt \| SFT \| Format-annotated traces \| Strict `<tool_call>` JSON \|

	### Stage 2: Distillation + Fusion 🔬

	```
	Teacher Models (Claude Opus 4.8 + Fable + AgentWorld)
	│
	├── SFT LoRA Training (individually)
	│ Opus SFT ────► LoRA_opus
	│ Fable SFT ────► LoRA_fable
	│ Routing ────► LoRA_routing
	│ Tool Call ────► LoRA_tool
	│ Math Fix ────► LoRA_math
	│ Mythos ────► LoRA_mythos
	│ ToolFmt ────► LoRA_toolfmt
	│
	└── Multi-LoRA Fusion Merge (SFT → Distill)
	Weighted fusion → Agent-R2
	```

	Why SFT + Distill?
	- 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
	from transformers import AutoModelForCausalLM, AutoTokenizer

	model = AutoModelForCausalLM.from_pretrained(
	"hotdogs/Qwen35B-Agent-R2",
	torch_dtype="auto",
	device_map="auto",
	trust_remote_code=True
	)
	tokenizer = AutoTokenizer.from_pretrained("hotdogs/Qwen35B-Agent-R2")

	messages = [
	{"role": "system", "content": "You are a helpful assistant."},
	{"role": "user", "content": "Search the web for latest AI news"}
	]
	inputs = tokenizer.apply_chat_template(messages, tokenize=True, return_tensors="pt")
	outputs = model.generate(inputs, max_new_tokens=1024, temperature=0.6)
	print(tokenizer.decode(outputs[0]))
	```

	### vLLM (Recommended for Production)

	The model works directly with vLLM from HuggingFace Safetensors — no AWQ/GPTQ conversion needed:

	```bash
	# Load directly from HuggingFace
	vllm serve hotdogs/Qwen35B-Agent-R2 \
	--tensor-parallel-size 2 \
	--max-model-len 8192 \
	--gpu-memory-utilization 0.9 \
	--trust-remote-code

	# Or use with local safetensors
	vllm serve /path/to/Qwen35B-Agent-R2 \
	--tensor-parallel-size 2 \
	--max-model-len 8192 \
	--gpu-memory-utilization 0.9 \
	--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
	- Thai + English — Native-level bilingual support
	- Code Generation — Python, JavaScript, shell scripts
	- Knowledge Q&A — Up-to-date knowledge with admit-when-unknown honesty
	- Reasoning Tasks — Step-by-step chain-of-thought via Opus 4.8 training

	---

	## 💖 Support / โปรดสนับสนุน

	If you find this model useful, please consider supporting my work!
	หากคุณคิดว่าโมเดลนี้มีประโยชน์ กรุณาสนับสนุนผลงานของฉันด้วยนะคะ! 🙏

	<p align="center">
	<img src="donate.webp" alt="Bitcoin QR — Donate" width="256">
	</p>

	### ₿ Bitcoin — BTC:
	```
	bc1qf27cyk3vmugcdyv9xdtuv5jwz37863crpj5c9v
	```

	Thank you for your support! 🙏✨
	ขอบคุณมากๆ สำหรับการสนับสนุนค่า! 💖🤗

	---

	## 🙏 Acknowledgements / ขอบคุณ

	- [Qwen Team (Alibaba)](https://qwenlm.github.io) — For the incredible Qwen3.6 AgentWorld architecture
	- [Nous Research](https://nousresearch.com) — For Hermes Agent framework
	- [cx-cmu](https://huggingface.co/cx-cmu) — For AgentWorld trajectories dataset
	- [11-47](https://huggingface.co/11-47) — For Claude Opus 4.8 thinking dataset
	- All dataset contributors and the open-source AI community ❤️

	---

	Built with ❤️ by UKA* — 18-year-old coder & cybersecurity expert*