Instructions to use hotdogs/Qwen35b-agent-R2O3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hotdogs/Qwen35b-agent-R2O3 with Transformers:

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

pipe = pipeline("text-generation", model="hotdogs/Qwen35b-agent-R2O3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hotdogs/Qwen35b-agent-R2O3")
model = AutoModelForCausalLM.from_pretrained("hotdogs/Qwen35b-agent-R2O3")
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-R2O3 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="hotdogs/Qwen35b-agent-R2O3",
	filename="GGUF-MTP/Qwen35b-agent-R2O3-MTP.Q4_K_M.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-R2O3 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-R2O3:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf hotdogs/Qwen35b-agent-R2O3: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-R2O3:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf hotdogs/Qwen35b-agent-R2O3: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-R2O3:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf hotdogs/Qwen35b-agent-R2O3: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-R2O3:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf hotdogs/Qwen35b-agent-R2O3:Q4_K_M

Use Docker

docker model run hf.co/hotdogs/Qwen35b-agent-R2O3:Q4_K_M

LM Studio
Jan

vLLM

How to use hotdogs/Qwen35b-agent-R2O3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hotdogs/Qwen35b-agent-R2O3"
# 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-R2O3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/hotdogs/Qwen35b-agent-R2O3:Q4_K_M

SGLang

How to use hotdogs/Qwen35b-agent-R2O3 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-R2O3" \
    --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-R2O3",
		"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-R2O3" \
        --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-R2O3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use hotdogs/Qwen35b-agent-R2O3 with Ollama:
```
ollama run hf.co/hotdogs/Qwen35b-agent-R2O3:Q4_K_M
```

Unsloth Studio

How to use hotdogs/Qwen35b-agent-R2O3 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-R2O3 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-R2O3 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-R2O3 to start chatting

How to use hotdogs/Qwen35b-agent-R2O3 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-R2O3: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-R2O3:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use hotdogs/Qwen35b-agent-R2O3 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-R2O3: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-R2O3:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use hotdogs/Qwen35b-agent-R2O3 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-R2O3: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-R2O3: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-R2O3 with Docker Model Runner:
```
docker model run hf.co/hotdogs/Qwen35b-agent-R2O3:Q4_K_M
```

Lemonade

How to use hotdogs/Qwen35b-agent-R2O3 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull hotdogs/Qwen35b-agent-R2O3:Q4_K_M

Run and chat with the model

lemonade run user.Qwen35b-agent-R2O3-Q4_K_M

List all available models

lemonade list

Qwen35b-agent-R2O3 / README.md

hotdogs

Upload README.md with huggingface_hub

afbc377 verified 1 day ago

preview code

Raw

History Blame Contribute Delete

7.85 kB

	---
	license: agpl-3.0
	language:
	- en
	- th
	tags:
	- qwen
	- moe
	- mixture-of-experts
	- agent
	- agent-world
	- tool-use
	- tool-calling
	- reasoning
	- sft
	- distillation
	- svd
	- lora
	- weight-diff
	- ornith
	- transformers
	- text-generation
	- thai
	base_model:
	- hotdogs/Qwen35B-Agent-R2
	datasets:
	- deepreinforce-ai/Ornith-1.0-35B
	- 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/Qwen3.5-35B%20A3B-blue">
	<img src="https://img.shields.io/badge/MoE-256%20experts-orange">
	<img src="https://img.shields.io/badge/SVD-LoRA-ff69b4">
	<img src="https://img.shields.io/badge/Ornith-0.3-green">
	<img src="https://img.shields.io/badge/Agent-R2O3-black">
	</p>

	<p align="center"><b>🚀 Qwen35b-Agent-R2O3 — Agent-R2 + Ornith (α=0.3)</b></p>

	<p align="center"><i>Built on Qwen35B-Agent-R2 with SVD-extracted Ornith LoRA. The best of both worlds.</i></p>

	---

	## 🧬 How This Model Was Built

	```
	┌─────────────────────────────────────────────────────────────┐
	│ Qwen35b-Agent-R2O3 Construction │
	├─────────────────────────────────────────────────────────────┤
	│ │
	│ Qwen35B-Agent-R2 (Base) ────────── 70% weights kept │
	│ │ │
	│ ├── 7 LoRAs already fused: │
	│ │ Opus \| Fable \| Routing \| Tool \| Math \| Mythos │
	│ │ \| ToolFmt (all trained via SFT) │
	│ │ │
	│ └── + Ornith LoRA (α=0.3) ← SVD Weight-Diff │
	│ │
	│ Ornith-1.0-35B Qwen-AgentWorld │
	│ │ │ │
	│ └──────── Weight-Diff SVD ──────────────┘ │
	│ │ │
	│ ┌──────┴──────┐ │
	│ │ LoRA r=32 │ → Merged at α=0.3 │
	│ │ 422 tensors│ │
	│ └─────────────┘ │
	│ │
	└─────────────────────────────────────────────────────────────┘
	```

	### Step 1: SVD Weight-Diff Extraction

	We extract Ornith's unique knowledge by computing the weight difference between Ornith-1.0-35B and the shared Huihui-Qwen-AgentWorld base:

	```python
	delta = W_ornith - W_base # What Ornith learned
	U, S, Vh = torch.linalg.svd(delta) # Decompose
	lora_A = diag(S[:32].sqrt()) @ Vh[:32, :]
	lora_B = U[:, :32] @ diag(S[:32].sqrt())
	```

	422 tensors extracted across:
	- MLP layers (`gate_proj`, `up_proj`, `down_proj`) — knowledge execution
	- Expert weights (256 MoE experts) — specialized routing (3D tensor → flatten → SVD → reshape)
	- Shared expert — common computation
	- Norms + lm_head — output calibration
	- Attention layers skipped — R2 uses `linear_attn` vs Ornith's `self_attn` (incompatible architecture)

	### Step 2: Multi-LoRA Fusion

	The extracted Ornith LoRA (r=32, α=64) is merged into Qwen35B-Agent-R2 at scale α=0.3:

	```python
	merged = R2 * 0.7 + Ornith_LoRA * 0.3
	```

	This preserves 70% of R2's original capabilities (its 7 LoRAs) while adding 30% of Ornith's algorithm/reasoning strength.

	### Why α=0.3?

	\| Scale \| R2 Preserved \| Ornith Added \| Best For \|
	\|:-----:\|:------------:\|:------------:\|:---------\|
	\| 0.3 \| 70% \| 30% \| Balanced — general agent use \|
	\| 0.4 \| 60% \| 40% \| Algorithm-heavy tasks \|
	\| 0.5+ \| <50% \| >50% \|⚠️ May dilute tool-calling \|

	---

	## 🔬 Technique: SVD Weight-Diff for MoE

	MoE models (256 experts) require special handling for SVD extraction:

	\| Component \| Standard Approach \| MoE Adaptation \|
	\|:----------\|:-----------------:\|:---------------\|
	\| 2D tensors (MLP, norms) \| `SVD(delta)` — normal \| Same \|
	\| 3D expert tensors `[out, in, 256]` \| N/A \| `flatten → SVD → reshape` \|
	\| Attention mismatch \| Direct diff \| ❌ Skipped (R2 uses `linear_attn`) \|
	\| language_model prefix \| Exact match \| Strip prefix after loading \|

	Expert tensor handling:
	```python
	delta = W_a - W_b # [512, 2048, 256]
	delta_flat = delta.transpose(0,2).reshape(-1, delta.shape[1]) # [131072, 2048]
	U, S, Vh = torch.linalg.svd(delta_flat)
	lora_B = U[:, :32] @ diag(S[:32].sqrt()) # [131072, 32]

	# On merge: reconstruct
	delta = lora_B @ lora_A # [131072, 2048]
	delta = delta.reshape(512, 256, 2048).permute(0, 2, 1) # [512, 2048, 256]
	```

	---

	## 📊 What You Get

	\| Capability \| Source \| Retained \|
	\|:-----------\|:------:\|:--------:\|
	\| 🧠 Reasoning (Opus 4.8) \| R2 \| ✅ 100% \|
	\| 🔧 Tool Calling \| R2 \| ✅ 100% \|
	\| 🧭 Agent Routing \| R2 \| ✅ 100% \|
	\| 📐 Math \| R2 + Ornith \| ✅ Enhanced \|
	\| ⚡ Algorithm \| Ornith 🆕 \| ✅ +30% \|
	\| 💬 Conversation (Fable) \| R2 \| ✅ 100% \|
	\| 🎭 Creative (Mythos) \| R2 \| ✅ 100% \|

	---

	## 🏆 Why Agent-R2O3?

	\| Aspect \| Other Models \| Agent-R2O3 \|
	\|--------\|-------------\|:--------------:\|
	\| Tool Call Format \| ❌ Often malformed \| ✅ Guaranteed valid `<tool_call>` \|
	\| Algorithm Tasks \| ❌ Struggles on hard \| ✅ Orithm-enhanced \|
	\| Thai Support \| ❌ Poor tokenization \| ✅ Native Thai + English \|
	\| Knowledge \| ❌ Single source \| ✅ R2 (7 LoRAs) + Ornith \|

	---

	## 🚀 Usage

	```bash
	# llama.cpp
	./llama-cli -m Qwen35b-agent-R2O3.Q4_K_M.gguf \
	-p "Hello" -n 100 --temp 0.6

	# Full server with tool calling
	./llama-server \
	-m Qwen35b-agent-R2O3.Q4_K_M.gguf \
	--host 0.0.0.0 --port 8081 -c 262144 -ngl 99 \
	--cache-type-k bf16 --cache-type-v bf16 \
	--flash-attn on --tools all --cont-batching \
	--temp 0.6 --top-k 40 --top-p 0.9 \
	--min-p 0.05 --repeat-penalty 1.03 \
	--jinja
	```

	---

	## 📦 Downloads

	\| File \| Size \| Quant \|
	\|:-----\|:----:\|:-----:\|
	\| `Qwen35b-agent-R2O3.Q4_K_M.gguf` \| 20 GB \| Recommended \|
	\| `Qwen35b-agent-R2O3.Q6_K.gguf` \| 27 GB \| High quality \|
	\| `Qwen35b-agent-R2O3.f16.gguf` \| 65 GB \| Full precision \|

	---

	## 🙏 Acknowledgements

	\| Contribution \| Source \|
	\|:-------------\|:-------\|
	\| Base Agent Model \| [hotdogs/Qwen35B-Agent-R2](https://huggingface.co/hotdogs/Qwen35B-Agent-R2) \|
	\| Algorithm Knowledge \| [deepreinforce-ai/Ornith-1.0-35B](https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B) \|
	\| SVD Extraction Method \| Weight-Diff SVD (Universial Adapter Extraction) \|
	\| Infrastructure \| [Nous Research](https://nousresearch.com) — Hermes Agent \|

	---

	## 💖 Support

	<p align="center">
	<img src="https://huggingface.co/hotdogs/Qwen35B-Agent-R2/raw/main/donate.webp" alt="Bitcoin QR" width="256">
	</p>

	```
	bc1qf27cyk3vmugcdyv9xdtuv5jwz37863crpj5c9v
	```

	---

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