Text Generation
Safetensors
Transformers
LongCat-Flash-Lite-Sparse
longcat_flash_lite_sparse
heretic
uncensored
decensored
abliterated
conversational
custom_code
Instructions to use llmfan46/LongCat-Flash-Lite-Sparse-Uncensored-Heretic-Native-MTP-And-LSA-Preserved with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use llmfan46/LongCat-Flash-Lite-Sparse-Uncensored-Heretic-Native-MTP-And-LSA-Preserved with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="llmfan46/LongCat-Flash-Lite-Sparse-Uncensored-Heretic-Native-MTP-And-LSA-Preserved", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("llmfan46/LongCat-Flash-Lite-Sparse-Uncensored-Heretic-Native-MTP-And-LSA-Preserved", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use llmfan46/LongCat-Flash-Lite-Sparse-Uncensored-Heretic-Native-MTP-And-LSA-Preserved with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "llmfan46/LongCat-Flash-Lite-Sparse-Uncensored-Heretic-Native-MTP-And-LSA-Preserved" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "llmfan46/LongCat-Flash-Lite-Sparse-Uncensored-Heretic-Native-MTP-And-LSA-Preserved", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/llmfan46/LongCat-Flash-Lite-Sparse-Uncensored-Heretic-Native-MTP-And-LSA-Preserved
- SGLang
How to use llmfan46/LongCat-Flash-Lite-Sparse-Uncensored-Heretic-Native-MTP-And-LSA-Preserved 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 "llmfan46/LongCat-Flash-Lite-Sparse-Uncensored-Heretic-Native-MTP-And-LSA-Preserved" \ --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": "llmfan46/LongCat-Flash-Lite-Sparse-Uncensored-Heretic-Native-MTP-And-LSA-Preserved", "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 "llmfan46/LongCat-Flash-Lite-Sparse-Uncensored-Heretic-Native-MTP-And-LSA-Preserved" \ --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": "llmfan46/LongCat-Flash-Lite-Sparse-Uncensored-Heretic-Native-MTP-And-LSA-Preserved", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use llmfan46/LongCat-Flash-Lite-Sparse-Uncensored-Heretic-Native-MTP-And-LSA-Preserved with Docker Model Runner:
docker model run hf.co/llmfan46/LongCat-Flash-Lite-Sparse-Uncensored-Heretic-Native-MTP-And-LSA-Preserved
LongCat-Flash-Lite-Sparse-Uncensored-Heretic-Native-MTP-And-LSA-Preserved / model-00021-of-00031.safetensors
Download model-00021-of-00031.safetensors from llmfan46/LongCat-Flash-Lite-Sparse-Uncensored-Heretic-Native-MTP-And-LSA-Preserved: direct link, hf CLI and curl.
- Browser
- Download file 5.23 GB
-
https://huggingface.co/llmfan46/LongCat-Flash-Lite-Sparse-Uncensored-Heretic-Native-MTP-And-LSA-Preserved/resolve/main/model-00021-of-00031.safetensors
- Command line
-
hf download hf://llmfan46/LongCat-Flash-Lite-Sparse-Uncensored-Heretic-Native-MTP-And-LSA-Preserved/model-00021-of-00031.safetensors
-
curl -L -o model-00021-of-00031.safetensors https://huggingface.co/llmfan46/LongCat-Flash-Lite-Sparse-Uncensored-Heretic-Native-MTP-And-LSA-Preserved/resolve/main/model-00021-of-00031.safetensors
5.23 GB
- Xet hash:
- 6ac9dfe68293d91a01dfdb56f5d9f355e6401a47a00c94eff71affec092b1d82
- Size of remote file:
- 5.23 GB
- SHA256:
- 3ad0e9c3ae11c9981f7550ab87e4dac1969b071625481fcdd819f5ca7415977e
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.