Instructions to use Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF 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 Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-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 Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-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 Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-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": "Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF:Q4_K_M

SGLang

How to use Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-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 "Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-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": "Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF",
		"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 "Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-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": "Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF with Ollama:
```
ollama run hf.co/Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF with Docker Model Runner:
```
docker model run hf.co/Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF:Q4_K_M
```

Lemonade

How to use Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF / README.md

Pinkstack

Update README.md

d412ccb verified over 1 year ago

preview code

Raw

History Blame Contribute Delete

8.93 kB

metadata

base_model:
  - Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - llama
  - gguf
  - code
  - phi3
  - cot
  - o1
  - reasoning
  - cot
license: mit
license_link: https://huggingface.co/microsoft/phi-4/resolve/main/LICENSE
language:
  - en
  - multilingual
pipeline_tag: text-generation
inference:
  parameters:
    temperature: 0.3
widget:
  - messages:
      - role: user
        content: How many R's in strawberry? Think step by step.
model-index:
  - name: SuperThoughts-CoT-14B-16k-o1-QwQ
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: IFEval (0-Shot)
          type: wis-k/instruction-following-eval
          split: train
          args:
            num_few_shot: 0
        metrics:
          - type: inst_level_strict_acc and prompt_level_strict_acc
            value: 5.15
            name: averaged accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Pinkstack%2FSuperThoughts-CoT-14B-16k-o1-QwQ
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: BBH (3-Shot)
          type: SaylorTwift/bbh
          split: test
          args:
            num_few_shot: 3
        metrics:
          - type: acc_norm
            value: 52.85
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Pinkstack%2FSuperThoughts-CoT-14B-16k-o1-QwQ
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MATH Lvl 5 (4-Shot)
          type: lighteval/MATH-Hard
          split: test
          args:
            num_few_shot: 4
        metrics:
          - type: exact_match
            value: 40.79
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Pinkstack%2FSuperThoughts-CoT-14B-16k-o1-QwQ
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GPQA (0-shot)
          type: Idavidrein/gpqa
          split: train
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 19.02
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Pinkstack%2FSuperThoughts-CoT-14B-16k-o1-QwQ
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MuSR (0-shot)
          type: TAUR-Lab/MuSR
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 21.79
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Pinkstack%2FSuperThoughts-CoT-14B-16k-o1-QwQ
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU-PRO (5-shot)
          type: TIGER-Lab/MMLU-Pro
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 47.43
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Pinkstack%2FSuperThoughts-CoT-14B-16k-o1-QwQ
          name: Open LLM Leaderboard

safetensors version: Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ Phi-4 Technical Report (SuperThoughts 14B is based on phi-4)

You must use this prompt format: https://huggingface.co/Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF#format

We are very proud to announce, SuperThoughts, but you can just call it o1 mini 😉

A reasoning ai model based on Phi-4, which is better that QwQ at everything but Ifeval, but at a smaller size, really good at math and answers step by step in multiple languages with any prompt as reasoning is built into the prompt format.

Please check the examples we provided: https://huggingface.co/Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ-GGUF#%F0%9F%A7%80-examples Beats qwen/qwq at MATH & MuSR & GPQA (MuSR being a reasoning benchmark) Evaluation:

Unlike previous models we've uploaded, this one is the best one we've published! Answers in two steps: Reasoning -> Final answer like o1 mini and other similar reasoning ai models.

🧀 Which quant is right for you? (all tested!)

Q3: This quant should be used on most high-end devices like rtx 2080TI's, Responses are very high quality, but its slightly slower than Q4. (Runs at ~1 tokens per second or less on a Samsung z fold 5 smartphone.)
Q4: This quant should be used on high-end modern devices like rtx 3080's or any GPU,TPU,CPU that is powerful enough and has at minimum 15gb of available memory, (On servers and high-end computers we personally use it.) reccomened.
Q8: This quant should be used on very high-end modern devices which can handle it's power, it is very powerful but q4 is more well rounded, not recommended.

Evaluation Results

Detailed results can be found here! Summarized results can be found here! Please note, the low IFEVAL results is probably due to it always reasoning, it does have issues with instruction following.

Metric	Value (%)
Average	31.17
IFEval (0-Shot)	5.15
BBH (3-Shot)	52.85
MATH Lvl 5 (4-Shot)	40.79
GPQA (0-shot)	19.02
MuSR (0-shot)	21.79
MMLU-PRO (5-shot)	47.43

Format

the model uses this prompt format: (modified phi-4 prompt)

{{ if .System }}<|system|>
{{ .System }}<|im_end|>
{{ end }}{{ if .Prompt }}<|user|>
{{ .Prompt }}<|im_end|>
{{ end }}<|assistant|>{{ .CoT }}<|CoT|>
{{ .Response }}<|FinalAnswer|><|im_end|>

It is recommended to use a system prompt like this one:

You are a helpful ai assistant. Make sure to put your finalanswer at the end.

🧀 Examples:

(q4_k_m, 10GB rtx 3080, 64GB memory, running inside of MSTY, all use "You are a friendly ai assistant." as the System prompt.) example 1: example 2: example 3: example 4:

All generated locally and pretty quickly too!

🧀 Information

⚠️ A low temperature must be used to ensure it won't fail at reasoning. we use 0.3 - 0.8!
⚠️ Due to the current prompt format, it may sometimes put <|FinalAnswer|> without providing a final answer at the end, you can ignore this or modify the prompt format.
this is out flagship model, with top-tier reasoning, rivaling gemini-flash-exp-2.0-thinking and o1 mini. results are overall similar to both of them, and it even beats QwQ at certain benchmarks.

Supported languages: Arabic, Chinese, Czech, Danish, Dutch, English, Finnish, French, German, Hebrew, Hungarian, Italian, Japanese, Korean, Norwegian, Polish, Portuguese, Russian, Spanish, Swedish, Thai, Turkish, Ukrainian

🧀 Uploaded model

Developed by: Pinkstack
License: MIT
Finetuned from model : Pinkstack/PARM-V1-phi-4-4k-CoT-pytorch

This Phi-4 model was trained with Unsloth and Huggingface's TRL library.