Instructions to use FritzStack/COGN-QWEN8B-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FritzStack/COGN-QWEN8B-4bit with Transformers:

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

pipe = pipeline("text-generation", model="FritzStack/COGN-QWEN8B-4bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FritzStack/COGN-QWEN8B-4bit")
model = AutoModelForCausalLM.from_pretrained("FritzStack/COGN-QWEN8B-4bit")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FritzStack/COGN-QWEN8B-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FritzStack/COGN-QWEN8B-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FritzStack/COGN-QWEN8B-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FritzStack/COGN-QWEN8B-4bit

SGLang

How to use FritzStack/COGN-QWEN8B-4bit 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 "FritzStack/COGN-QWEN8B-4bit" \
    --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": "FritzStack/COGN-QWEN8B-4bit",
		"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 "FritzStack/COGN-QWEN8B-4bit" \
        --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": "FritzStack/COGN-QWEN8B-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use FritzStack/COGN-QWEN8B-4bit 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 FritzStack/COGN-QWEN8B-4bit 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 FritzStack/COGN-QWEN8B-4bit to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for FritzStack/COGN-QWEN8B-4bit to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="FritzStack/COGN-QWEN8B-4bit",
    max_seq_length=2048,
)

Docker Model Runner
How to use FritzStack/COGN-QWEN8B-4bit with Docker Model Runner:
```
docker model run hf.co/FritzStack/COGN-QWEN8B-4bit
```

FritzStack commited on Apr 3

Commit

5e63db1

verified ·

1 Parent(s): ad88dfa

Update README.md

Browse files

Files changed (1) hide show

README.md +14 -6

README.md CHANGED Viewed

@@ -10,12 +10,20 @@ language:
 - en
 ---
-# Uploaded finetuned  model
-- **Developed by:** FritzStack
-- **License:** apache-2.0
-- **Finetuned from model :** unsloth/Qwen3-8B-unsloth-bnb-4bit
-This qwen3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

 - en
 ---
+```bash
+!pip install git+https://github.com/Fede-stack/TONYpy.git
+```
+```python
+from TONY.COGNITIVE import CognitivePredictor, CognitivePredictor_mlx
+text = 'I keep thinking about how I messed up in college. I should have studied harder and done more with my life.'
+cogn = CognitivePredictor(model_name='FritzStack/COGN-QWEN8B-4bit')
+cogn.predict_cognitive_features(text)
+# Output:
+# Attention Bias: Negative
+# Interpretation Bias: Negative
+# Memory Bias: Negative
+# Rumination: Brooding
+```