Text Generation
Transformers
Safetensors
qwen3_5
image-text-to-text
Merge
qwen3.5
reasoning
chain-of-thought
distillation
agentic
text-generation-inference
heretic
uncensored
decensored
abliterated
reproducible
conversational
Instructions to use xtools-at/Qwen3.5-4B-MultiDistill-Megamix-8xMerge-UNCENSORED-heretic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use xtools-at/Qwen3.5-4B-MultiDistill-Megamix-8xMerge-UNCENSORED-heretic with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="xtools-at/Qwen3.5-4B-MultiDistill-Megamix-8xMerge-UNCENSORED-heretic") 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)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("xtools-at/Qwen3.5-4B-MultiDistill-Megamix-8xMerge-UNCENSORED-heretic") model = AutoModelForMultimodalLM.from_pretrained("xtools-at/Qwen3.5-4B-MultiDistill-Megamix-8xMerge-UNCENSORED-heretic", device_map="auto") 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?"} ] }, ] inputs = processor.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=256) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use xtools-at/Qwen3.5-4B-MultiDistill-Megamix-8xMerge-UNCENSORED-heretic with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "xtools-at/Qwen3.5-4B-MultiDistill-Megamix-8xMerge-UNCENSORED-heretic" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "xtools-at/Qwen3.5-4B-MultiDistill-Megamix-8xMerge-UNCENSORED-heretic", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/xtools-at/Qwen3.5-4B-MultiDistill-Megamix-8xMerge-UNCENSORED-heretic
- SGLang
How to use xtools-at/Qwen3.5-4B-MultiDistill-Megamix-8xMerge-UNCENSORED-heretic 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 "xtools-at/Qwen3.5-4B-MultiDistill-Megamix-8xMerge-UNCENSORED-heretic" \ --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": "xtools-at/Qwen3.5-4B-MultiDistill-Megamix-8xMerge-UNCENSORED-heretic", "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 "xtools-at/Qwen3.5-4B-MultiDistill-Megamix-8xMerge-UNCENSORED-heretic" \ --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": "xtools-at/Qwen3.5-4B-MultiDistill-Megamix-8xMerge-UNCENSORED-heretic", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use xtools-at/Qwen3.5-4B-MultiDistill-Megamix-8xMerge-UNCENSORED-heretic with Docker Model Runner:
docker model run hf.co/xtools-at/Qwen3.5-4B-MultiDistill-Megamix-8xMerge-UNCENSORED-heretic
Upload reproduce/requirements.txt with huggingface_hub
Browse files- reproduce/requirements.txt +109 -0
reproduce/requirements.txt
ADDED
|
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
absl-py==1.4.0
|
| 2 |
+
accelerate==1.15.0
|
| 3 |
+
alembic==1.20.0
|
| 4 |
+
annotated-doc==0.0.5
|
| 5 |
+
annotated-types==0.8.0
|
| 6 |
+
anyio==4.15.1
|
| 7 |
+
bitsandbytes==0.50.2
|
| 8 |
+
certifi==2026.7.22
|
| 9 |
+
chardet==5.2.0
|
| 10 |
+
charset-normalizer==3.4.9
|
| 11 |
+
click==8.5.0
|
| 12 |
+
cloudpickle==3.1.2
|
| 13 |
+
colorama==0.4.6
|
| 14 |
+
colorlog==6.12.0
|
| 15 |
+
cuda-bindings==13.0.3
|
| 16 |
+
cuda-pathfinder==1.8.2
|
| 17 |
+
cuda-toolkit==13.0.2
|
| 18 |
+
dataproperty==1.1.1
|
| 19 |
+
datasets==5.1.0
|
| 20 |
+
dill==0.4.1
|
| 21 |
+
evaluate==0.4.6
|
| 22 |
+
filelock==4.0.7
|
| 23 |
+
fsspec==2025.12.0
|
| 24 |
+
h11==0.16.0
|
| 25 |
+
hf-xet==1.6.0
|
| 26 |
+
httpcore==1.0.9
|
| 27 |
+
httpx==0.28.1
|
| 28 |
+
huggingface-hub==1.33.0
|
| 29 |
+
idna==3.20
|
| 30 |
+
immutabledict==4.3.1
|
| 31 |
+
importlib-metadata==9.0.1
|
| 32 |
+
jinja2==3.1.6
|
| 33 |
+
joblib==1.6.0
|
| 34 |
+
langdetect==1.0.9
|
| 35 |
+
lm-eval==0.4.13
|
| 36 |
+
lxml==6.1.3
|
| 37 |
+
mako==1.3.2.dev0
|
| 38 |
+
markdown-it-py==4.2.0
|
| 39 |
+
markupsafe==3.0.3
|
| 40 |
+
mbstrdecoder==1.1.5
|
| 41 |
+
mdurl==0.1.2
|
| 42 |
+
more-itertools==10.8.0
|
| 43 |
+
mpmath==1.3.0
|
| 44 |
+
multiprocess==0.70.19
|
| 45 |
+
networkx==3.7
|
| 46 |
+
nltk==3.9.1
|
| 47 |
+
numpy==2.5.4
|
| 48 |
+
nvidia-cublas==13.1.0.3
|
| 49 |
+
nvidia-cudnn-cu13==9.19.0.56
|
| 50 |
+
nvidia-cusparselt-cu13==0.8.0
|
| 51 |
+
nvidia-nccl-cu13==2.28.9
|
| 52 |
+
nvidia-nvshmem-cu13==3.4.5
|
| 53 |
+
optuna==5.0.0
|
| 54 |
+
packaging==26.3
|
| 55 |
+
pandas==2.2.3
|
| 56 |
+
pathvalidate==3.3.1
|
| 57 |
+
peft==0.21.1
|
| 58 |
+
pillow==11.3.0
|
| 59 |
+
portalocker==4.4.0
|
| 60 |
+
prompt-toolkit==3.0.53
|
| 61 |
+
psutil==7.2.2
|
| 62 |
+
py-cpuinfo==9.0.0
|
| 63 |
+
pyarrow==26.0.0
|
| 64 |
+
pydantic==2.13.5
|
| 65 |
+
pydantic-core==2.46.5
|
| 66 |
+
pydantic-settings==2.16.0
|
| 67 |
+
pygments==2.21.0
|
| 68 |
+
pytablewriter==1.2.1
|
| 69 |
+
python-dateutil==2.9.0.post0
|
| 70 |
+
python-dotenv==1.2.3
|
| 71 |
+
pytz==2025.2
|
| 72 |
+
pyyaml==6.0.3
|
| 73 |
+
questionary==2.1.1
|
| 74 |
+
regex==2025.11.3
|
| 75 |
+
requests==2.32.4
|
| 76 |
+
rich==15.0.0
|
| 77 |
+
rouge-score==0.1.2
|
| 78 |
+
sacrebleu==2.6.0
|
| 79 |
+
safetensors==0.8.0
|
| 80 |
+
scikit-learn==1.6.1
|
| 81 |
+
scipy==1.16.3
|
| 82 |
+
setuptools==80.10.2
|
| 83 |
+
shellingham==1.5.4
|
| 84 |
+
six==1.17.0
|
| 85 |
+
sqlalchemy==2.1.1
|
| 86 |
+
sqlitedict==2.1.0
|
| 87 |
+
sympy==1.14.0
|
| 88 |
+
tabledata==1.3.5
|
| 89 |
+
tabulate==0.9.0
|
| 90 |
+
tcolorpy==0.1.7
|
| 91 |
+
threadpoolctl==3.7.0
|
| 92 |
+
tokenizers==0.23.2
|
| 93 |
+
tomli-w==1.2.0
|
| 94 |
+
torch==2.11.0
|
| 95 |
+
torchaudio==2.11.0
|
| 96 |
+
torchvision==0.26.0
|
| 97 |
+
tqdm==4.70.1
|
| 98 |
+
transformers==5.18.0
|
| 99 |
+
triton==3.6.0
|
| 100 |
+
typepy==1.3.5
|
| 101 |
+
typer==0.27.2
|
| 102 |
+
typing-extensions==4.16.0
|
| 103 |
+
typing-inspection==0.4.4
|
| 104 |
+
tzdata==2026.4
|
| 105 |
+
urllib3==2.5.0
|
| 106 |
+
wcwidth==0.9.1
|
| 107 |
+
word2number==1.1
|
| 108 |
+
xxhash==4.0.1
|
| 109 |
+
zipp==4.1.0
|