Instructions to use prithivMLmods/Open-R1-Mini-Experimental-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use prithivMLmods/Open-R1-Mini-Experimental-GGUF with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="prithivMLmods/Open-R1-Mini-Experimental-GGUF") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("prithivMLmods/Open-R1-Mini-Experimental-GGUF", dtype="auto") - llama-cpp-python
How to use prithivMLmods/Open-R1-Mini-Experimental-GGUF with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="prithivMLmods/Open-R1-Mini-Experimental-GGUF", filename="Open-R1-Mini-Experimental-f16.gguf", )
llm.create_chat_completion( messages = [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] ) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use prithivMLmods/Open-R1-Mini-Experimental-GGUF with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf prithivMLmods/Open-R1-Mini-Experimental-GGUF:Q4_K_M # Run inference directly in the terminal: llama-cli -hf prithivMLmods/Open-R1-Mini-Experimental-GGUF:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf prithivMLmods/Open-R1-Mini-Experimental-GGUF:Q4_K_M # Run inference directly in the terminal: llama-cli -hf prithivMLmods/Open-R1-Mini-Experimental-GGUF: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 prithivMLmods/Open-R1-Mini-Experimental-GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf prithivMLmods/Open-R1-Mini-Experimental-GGUF: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 prithivMLmods/Open-R1-Mini-Experimental-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf prithivMLmods/Open-R1-Mini-Experimental-GGUF:Q4_K_M
Use Docker
docker model run hf.co/prithivMLmods/Open-R1-Mini-Experimental-GGUF:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use prithivMLmods/Open-R1-Mini-Experimental-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "prithivMLmods/Open-R1-Mini-Experimental-GGUF" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "prithivMLmods/Open-R1-Mini-Experimental-GGUF", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/prithivMLmods/Open-R1-Mini-Experimental-GGUF:Q4_K_M
- SGLang
How to use prithivMLmods/Open-R1-Mini-Experimental-GGUF 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 "prithivMLmods/Open-R1-Mini-Experimental-GGUF" \ --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": "prithivMLmods/Open-R1-Mini-Experimental-GGUF", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'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 "prithivMLmods/Open-R1-Mini-Experimental-GGUF" \ --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": "prithivMLmods/Open-R1-Mini-Experimental-GGUF", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Ollama
How to use prithivMLmods/Open-R1-Mini-Experimental-GGUF with Ollama:
ollama run hf.co/prithivMLmods/Open-R1-Mini-Experimental-GGUF:Q4_K_M
- Unsloth Studio new
How to use prithivMLmods/Open-R1-Mini-Experimental-GGUF 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 prithivMLmods/Open-R1-Mini-Experimental-GGUF 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 prithivMLmods/Open-R1-Mini-Experimental-GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for prithivMLmods/Open-R1-Mini-Experimental-GGUF to start chatting
- Docker Model Runner
How to use prithivMLmods/Open-R1-Mini-Experimental-GGUF with Docker Model Runner:
docker model run hf.co/prithivMLmods/Open-R1-Mini-Experimental-GGUF:Q4_K_M
- Lemonade
How to use prithivMLmods/Open-R1-Mini-Experimental-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull prithivMLmods/Open-R1-Mini-Experimental-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.Open-R1-Mini-Experimental-GGUF-Q4_K_M
List all available models
lemonade list
Update README.md
Browse files
README.md
CHANGED
|
@@ -11,4 +11,119 @@ tags:
|
|
| 11 |
- open
|
| 12 |
- r1
|
| 13 |
- explainer
|
| 14 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
- open
|
| 12 |
- r1
|
| 13 |
- explainer
|
| 14 |
+
---
|
| 15 |
+

|
| 16 |
+
|
| 17 |
+
# **Open-R1-Mini-Experimental-GGUF**
|
| 18 |
+
|
| 19 |
+
The **Open-R1-Mini-Experimental-GGUF** model is a fine-tuned version of **Qwen/Qwen2-VL-2B-Instruct**, specifically designed for **reasoning tasks**, **context reasoning**, and **multi-modal understanding** based on the **R1 reasoning logits data**. This model integrates a conversational approach with deep reasoning capabilities to handle complex multi-modal tasks efficiently.
|
| 20 |
+
|
| 21 |
+
#### Key Enhancements:
|
| 22 |
+
|
| 23 |
+
* **Advanced Contextual Reasoning**: Open-R1-Mini-Experimental-GGUF achieves state-of-the-art performance in reasoning tasks by leveraging R1 reasoning logits data, enhancing logical inference and decision-making.
|
| 24 |
+
|
| 25 |
+
* **Understanding images of various resolution & ratio**: The model excels at visual understanding benchmarks, including MathVista, DocVQA, RealWorldQA, MTVQA, etc.
|
| 26 |
+
|
| 27 |
+
* **Long-Context Video Understanding**: Capable of processing and reasoning over videos of 20 minutes or more for high-quality video-based question answering, content creation, and dialogue.
|
| 28 |
+
|
| 29 |
+
* **Device Integration**: With strong reasoning and decision-making abilities, the model can be integrated into mobile devices, robots, and automation systems for real-time operation based on both visual and textual input.
|
| 30 |
+
|
| 31 |
+
* **Multilingual Support**: Supports text understanding in various languages within images, including English, Chinese, Japanese, Korean, Arabic, most European languages, and Vietnamese.
|
| 32 |
+
|
| 33 |
+
### Sample Inference
|
| 34 |
+
|
| 35 |
+

|
| 36 |
+
|
| 37 |
+
`Demo:` https://huggingface.co/prithivMLmods/Open-R1-Mini-Experimental/blob/main/open-r1-reasoner-doc-py/open-r1-exp.ipynb
|
| 38 |
+
|
| 39 |
+
### How to Use
|
| 40 |
+
|
| 41 |
+
```python
|
| 42 |
+
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
|
| 43 |
+
from qwen_vl_utils import process_vision_info
|
| 44 |
+
|
| 45 |
+
# Load the model with automatic device placement
|
| 46 |
+
model = Qwen2VLForConditionalGeneration.from_pretrained(
|
| 47 |
+
"prithivMLmods/Open-R1-Mini-Experimental", torch_dtype="auto", device_map="auto"
|
| 48 |
+
)
|
| 49 |
+
|
| 50 |
+
# Recommended: Enable flash_attention_2 for better performance in multi-image and video tasks
|
| 51 |
+
# model = Qwen2VLForConditionalGeneration.from_pretrained(
|
| 52 |
+
# "prithivMLmods/Open-R1-Mini-Experimental",
|
| 53 |
+
# torch_dtype=torch.bfloat16,
|
| 54 |
+
# attn_implementation="flash_attention_2",
|
| 55 |
+
# device_map="auto",
|
| 56 |
+
# )
|
| 57 |
+
|
| 58 |
+
# Load processor
|
| 59 |
+
processor = AutoProcessor.from_pretrained("prithivMLmods/Open-R1-Mini-Experimental-GGUF")
|
| 60 |
+
|
| 61 |
+
# Adjust visual token range for optimized memory usage
|
| 62 |
+
# min_pixels = 256*28*28
|
| 63 |
+
# max_pixels = 1280*28*28
|
| 64 |
+
# processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-2B-Instruct", min_pixels=min_pixels, max_pixels=max_pixels)
|
| 65 |
+
|
| 66 |
+
messages = [
|
| 67 |
+
{
|
| 68 |
+
"role": "user",
|
| 69 |
+
"content": [
|
| 70 |
+
{
|
| 71 |
+
"type": "image",
|
| 72 |
+
"image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
|
| 73 |
+
},
|
| 74 |
+
{"type": "text", "text": "Analyze the context of this image."},
|
| 75 |
+
],
|
| 76 |
+
}
|
| 77 |
+
]
|
| 78 |
+
|
| 79 |
+
# Prepare input
|
| 80 |
+
text = processor.apply_chat_template(
|
| 81 |
+
messages, tokenize=False, add_generation_prompt=True
|
| 82 |
+
)
|
| 83 |
+
image_inputs, video_inputs = process_vision_info(messages)
|
| 84 |
+
inputs = processor(
|
| 85 |
+
text=[text],
|
| 86 |
+
images=image_inputs,
|
| 87 |
+
videos=video_inputs,
|
| 88 |
+
padding=True,
|
| 89 |
+
return_tensors="pt",
|
| 90 |
+
)
|
| 91 |
+
inputs = inputs.to("cuda")
|
| 92 |
+
|
| 93 |
+
# Inference
|
| 94 |
+
generated_ids = model.generate(**inputs, max_new_tokens=128)
|
| 95 |
+
generated_ids_trimmed = [
|
| 96 |
+
out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
|
| 97 |
+
]
|
| 98 |
+
output_text = processor.batch_decode(
|
| 99 |
+
generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
|
| 100 |
+
)
|
| 101 |
+
print(output_text)
|
| 102 |
+
```
|
| 103 |
+
### Buffer Handling
|
| 104 |
+
```python
|
| 105 |
+
buffer = ""
|
| 106 |
+
for new_text in streamer:
|
| 107 |
+
buffer += new_text
|
| 108 |
+
buffer = buffer.replace("<|im_end|>", "")
|
| 109 |
+
yield buffer
|
| 110 |
+
```
|
| 111 |
+
### **Key Features**
|
| 112 |
+
|
| 113 |
+
1. **Advanced Contextual Reasoning:**
|
| 114 |
+
- Optimized for **context-aware problem-solving** and **logical inference** based on R1 reasoning logits.
|
| 115 |
+
|
| 116 |
+
2. **Optical Character Recognition (OCR):**
|
| 117 |
+
- Extracts and processes text from images with exceptional accuracy.
|
| 118 |
+
|
| 119 |
+
3. **Mathematical and Logical Problem Solving:**
|
| 120 |
+
- Supports complex reasoning and outputs equations in **LaTeX format**.
|
| 121 |
+
|
| 122 |
+
4. **Conversational and Multi-Turn Interaction:**
|
| 123 |
+
- Handles **multi-turn dialogue** with enhanced memory retention and response coherence.
|
| 124 |
+
|
| 125 |
+
5. **Multi-Modal Inputs & Outputs:**
|
| 126 |
+
- Processes images, text, and combined inputs to generate insightful analyses.
|
| 127 |
+
|
| 128 |
+
6. **Secure and Efficient Model Loading:**
|
| 129 |
+
- Uses **Safetensors** for faster and more secure model weight handling.
|