Instructions to use hotdogs/qwen27b-agent-R2-preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hotdogs/qwen27b-agent-R2-preview with Transformers:

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

pipe = pipeline("text-generation", model="hotdogs/qwen27b-agent-R2-preview")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hotdogs/qwen27b-agent-R2-preview")
model = AutoModelForCausalLM.from_pretrained("hotdogs/qwen27b-agent-R2-preview")
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/qwen27b-agent-R2-preview with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="hotdogs/qwen27b-agent-R2-preview",
	filename="GGUF/Qwen3.6-27B-mmproj-BF16.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/qwen27b-agent-R2-preview 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/qwen27b-agent-R2-preview:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf hotdogs/qwen27b-agent-R2-preview: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/qwen27b-agent-R2-preview:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf hotdogs/qwen27b-agent-R2-preview: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/qwen27b-agent-R2-preview:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf hotdogs/qwen27b-agent-R2-preview: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/qwen27b-agent-R2-preview:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf hotdogs/qwen27b-agent-R2-preview:Q4_K_M

Use Docker

docker model run hf.co/hotdogs/qwen27b-agent-R2-preview:Q4_K_M

LM Studio
Jan

vLLM

How to use hotdogs/qwen27b-agent-R2-preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hotdogs/qwen27b-agent-R2-preview"
# 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/qwen27b-agent-R2-preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/hotdogs/qwen27b-agent-R2-preview:Q4_K_M

SGLang

How to use hotdogs/qwen27b-agent-R2-preview 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/qwen27b-agent-R2-preview" \
    --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/qwen27b-agent-R2-preview",
		"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/qwen27b-agent-R2-preview" \
        --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/qwen27b-agent-R2-preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use hotdogs/qwen27b-agent-R2-preview with Ollama:
```
ollama run hf.co/hotdogs/qwen27b-agent-R2-preview:Q4_K_M
```

Unsloth Studio

How to use hotdogs/qwen27b-agent-R2-preview 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/qwen27b-agent-R2-preview 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/qwen27b-agent-R2-preview to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for hotdogs/qwen27b-agent-R2-preview to start chatting

How to use hotdogs/qwen27b-agent-R2-preview with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf hotdogs/qwen27b-agent-R2-preview: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/qwen27b-agent-R2-preview:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use hotdogs/qwen27b-agent-R2-preview 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/qwen27b-agent-R2-preview: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/qwen27b-agent-R2-preview:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use hotdogs/qwen27b-agent-R2-preview with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf hotdogs/qwen27b-agent-R2-preview: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/qwen27b-agent-R2-preview: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/qwen27b-agent-R2-preview with Docker Model Runner:
```
docker model run hf.co/hotdogs/qwen27b-agent-R2-preview:Q4_K_M
```

Lemonade

How to use hotdogs/qwen27b-agent-R2-preview with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull hotdogs/qwen27b-agent-R2-preview:Q4_K_M

Run and chat with the model

lemonade run user.qwen27b-agent-R2-preview-Q4_K_M

List all available models

lemonade list

qwen27b-agent-R2-preview / README.md

hotdogs

Upload README.md with huggingface_hub

8984017 verified 1 day ago

preview code

Raw

History Blame Contribute Delete

9.69 kB

	---
	license: agpl-3.0
	language:
	- en
	- th
	tags:
	- qwen
	- agent
	- tool-call
	- tool-use
	- function-calling
	- reasoning
	- opus
	- fable
	- conversational
	- mtp
	- multi-token-prediction
	- transformers
	- text-generation
	- thai
	- speculative-decoding
	- preview
	base_model:
	- Qwen/Qwen3.6-27B
	datasets:
	- hotdogs/uka-fable-reasoning
	- NousResearch/hermes-function-calling-v1
	- 11-47/claude_opus_4.8_max_thinking_5k_v2
	library_name: transformers
	pipeline_tag: text-generation
	---

	<h1 align="center">🐉 qwen27b-agent-R2-preview</h1>

	<p align="center">
	<b>27B Agent Model — MTP · Tool-Calling · Multi-LoRA Fusion</b>
	</p>

	<p align="center">
	<img src="https://img.shields.io/badge/license-AGPL--3.0-red">
	<img src="https://img.shields.io/badge/Qwen3.6-27B-blue">
	<img src="https://img.shields.io/badge/MTP-Draft--2--token-brightgreen">
	<img src="https://img.shields.io/badge/Multi--LoRA-Fusion-orange">
	<img src="https://img.shields.io/badge/Preview-v0.1-yellow">
	</p>

	<br>

	> Preview release — Built on Qwen3.6-27B with multi-LoRA fusion. Features Multi-Token Prediction (MTP) for speculative decoding, tool-calling, and Opus + Fable reasoning. Standard (non-abliterated) version.

	---

	## ✨ Key Features

	\| Capability \| Description \|
	\|------------\|-------------\|
	\| ⚡ MTP Speculative Decoding \| Draft 2 tokens at a time — up to +85% decode TPS on single GPU \|
	\| 🔧 Tool Calling \| Hermes/Qwen function-calling format via llama.cpp `--tools all` \|
	\| 🧠 Reasoning \| Opus 4.8 + Fable-style reasoning with step-by-step CoT \|
	\| 🌏 Thai + English \| Native bilingual support \|
	\| 💻 Code \| Python, shell, system tasks \|

	---

	## 🚀 Usage

	### llama.cpp (Recommended)

	```bash
	# Quick test
	./llama-cli -m qwen27b-agent-R2-preview.Q4_K_M.gguf \
	-p "Hello" -n 100 --temp 0.6

	# Full agent server with tool calling + MTP speculative decoding
	./llama-server \
	-m qwen27b-agent-R2-preview.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 \
	--dry-multiplier 0 \
	--verbose \
	-n -1 \
	--parallel 1 \
	--jinja \
	--dry-sequence-breaker none \
	--spec-type draft-mtp \
	--spec-draft-n-max 2
	```

	\| Parameter \| Purpose \|
	\|-----------\|---------\|
	\| `--cache-type-k bf16` / `--cache-type-v bf16` \| BF16 KV cache for quality \|
	\| `--flash-attn on` \| Flash attention for speed \|
	\| `--tools all` \| Enable tool/function calling \|
	\| `--spec-type draft-mtp` \| MTP speculative decoding (draft 2 tokens) \|
	\| `--spec-draft-n-max 2` \| Max 2 draft tokens per step \|
	\| `--cont-batching` \| Continuous batching for multi-turn \|
	\| `--jinja` \| Use Jinja2 chat template from GGUF \|

	### Python (Transformers)

	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer

	model = AutoModelForCausalLM.from_pretrained(
	"hotdogs/qwen27b-agent-R2-preview",
	torch_dtype="auto",
	device_map="auto",
	trust_remote_code=True
	)
	tokenizer = AutoTokenizer.from_pretrained("hotdogs/qwen27b-agent-R2-preview")

	messages = [{"role": "user", "content": "Hello"}]
	inputs = tokenizer.apply_chat_template(messages, tokenize=True, return_tensors="pt")
	outputs = model.generate(inputs, max_new_tokens=256, temperature=0.6)
	print(tokenizer.decode(outputs[0]))
	```

	---

	## 📦 Downloads

	\| File \| Size \| Quant \| Description \|
	\|------\|:----:\|:-----:\|-------------\|
	\| `qwen27b-agent-R2-preview.Q4_K_M.gguf` \| 16 GB \| Q4_K_M \| Recommended — balanced quality/speed \|
	\| `qwen27b-agent-R2-preview.Q6_K.gguf` \| 21 GB \| Q6_K \| Higher quality, slightly slower \|
	\| `qwen27b-agent-R2-preview.f16.gguf` \| 51 GB \| f16 \| Full precision \|

	> 🎯 Q4_K_M is recommended for most users — good quality with 16 GB VRAM usage.

	### 📷 Multimodal Projector (mmproj)

	For vision support, pair this model with the mmproj from `Qwen/Qwen3.6-27B`:

	```bash
	# Extract mmproj from Qwen3.6-27B vision model
	python3 ./llama.cpp/convert_hf_to_gguf.py \
	--mmproj Qwen/Qwen3.6-27B \
	--outfile mmproj-qwen3.6-27b.gguf

	# Use with llama-server for vision + tool calling
	./llama-server \
	-m qwen27b-agent-R2-preview.Q4_K_M.gguf \
	--mmproj mmproj-qwen3.6-27b.gguf
	```

	---

	## 🧬 Architecture

	\| Parameter \| Value \|
	\|-----------\|:-----:\|
	\| Base \| [Qwen/Qwen3.6-27B](https://huggingface.co/Qwen/Qwen3.6-27B) \|
	\| Parameters \| ~27B \|
	\| Hidden Size \| 5,120 \|
	\| Attention \| Linear + Standard hybrid \|
	\| Context \| 8,192 tokens (extendable) \|
	\| Precision \| BF16 / GGUF quantized \|
	\| Format \| ChatML (Jinja2 template) \|
	\| MTP Head \| ✅ 1 extra layer (draft 2 tokens) \|

	---

	## 🧬 How This Model Was Built

	```
	┌──────────────────────────────────────────────────────────────┐
	│ qwen27b-agent-R2-preview Construction │
	├──────────────────────────────────────────────────────────────┤
	│ │
	│ Qwen/Qwen3.6-27B (Base) │
	│ │ │
	│ ├── Multi-LoRA Fusion (4 LoRAs): │
	│ │ ┌──────────────────────────────────┐ │
	│ │ │ LoRa │ Source │ │
	│ │ ├──────────────┼─────────────┤ │
	│ │ │ Opus SFT │ SFT on │ │
	│ │ │ │ Opus 4.8 │ │
	│ │ ├──────────────┼─────────────┤ │
	│ │ │ CxCMU Agent │ AgentWorld │ │
	│ │ │ │ trajectories │ │
	│ │ ├──────────────┼─────────────┤ │
	│ │ │ General SFT │ Reasoning │ │
	│ │ │ │ + Hermes FC │ │
	│ │ ├──────────────┼─────────────┤ │
	│ │ │ Tachibana │ Coding agent │ │
	│ │ │ Agent │ dataset │ │
	│ │ └──────────────┴─────────────┘ │
	│ │ │
	│ └── + MTP Head (15 tensors) │
	│ └── From huihui-ai/Huihui-Qwen3.6-27B-abliterated │
	│ │
	│ Result: 866 tensors, MTP=1, 16.8 GB (Q4_K_M) │
	│ │
	└──────────────────────────────────────────────────────────────┘
	```

	### Training Details

	Each LoRA was trained independently via SFT on specialized datasets. Then all 4 were fused into the base model at their respective scales. The low scales (0.15-0.4) ensure no single LoRA overpowers the model — creating a balanced agent.

	### MTP Tensor Injection

	The Multi-Token Prediction head (15 tensors) was injected from `huihui-ai/Huihui-Qwen3.6-27B-abliterated` to enable speculative decoding:

	```python
	# MTP head adds blk.64.* tensors for draft-2-token prediction
	--spec-type draft-mtp # Enables in llama.cpp
	--spec-draft-n-max 2 # Max draft tokens
	```

	---

	## ⚡ MTP Speculative Decoding

	Multi-Token Prediction enables speculative decoding:

	```
	Standard: [token₁] → [token₂] → [token₃] → ... (~36 TPS)
	MTP: [token₁ token₂] → [token₃ token₄] → ... (~66 TPS)
	```

	- MTP head adds ~849 MB to model size
	- Uses `--spec-type draft-mtp` in llama.cpp
	- Best for single-user agent workloads
	- ~1.2–1.8× decode speedup

	---

	## 💖 Support / โปรดสนับสนุน

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

	<p align="center">
	<img src="https://huggingface.co/hotdogs/Qwen35B-Agent-R2/raw/main/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 Qwen3.6 architecture
	- [Nous Research](https://nousresearch.com) — For Hermes Agent framework
	- [huihui-ai](https://huggingface.co/huihui-ai) — For MTP tensor support
	- All dataset contributors and the open-source AI community ❤️

	---

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