Text Generation
Transformers
Safetensors
English
modern_llm
custom-architecture
rope
gqa
swiglu
rmsnorm
custom_code
Instructions to use devoppro/FastLLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use devoppro/FastLLM with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="devoppro/FastLLM", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("devoppro/FastLLM", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use devoppro/FastLLM with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "devoppro/FastLLM" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "devoppro/FastLLM", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/devoppro/FastLLM
- SGLang
How to use devoppro/FastLLM 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 "devoppro/FastLLM" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "devoppro/FastLLM", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "devoppro/FastLLM" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "devoppro/FastLLM", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use devoppro/FastLLM with Docker Model Runner:
docker model run hf.co/devoppro/FastLLM
Download last-checkpoint/scaler.pt from devoppro/FastLLM: direct link, hf CLI and curl.
- Browser
- Download file 1.38 kB
-
https://huggingface.co/devoppro/FastLLM/resolve/main/last-checkpoint/scaler.pt
- Command line
-
hf download hf://devoppro/FastLLM/last-checkpoint/scaler.pt
-
curl -L -o scaler.pt https://huggingface.co/devoppro/FastLLM/resolve/main/last-checkpoint/scaler.pt
1.38 kB
- Xet hash:
- 4560ece2a1a353a30c34e3a5aa592ceca664f37f80557df293854e27a17f6a02
- Size of remote file:
- 1.38 kB
- SHA256:
- 8377531a6924fec4658b9153d3ae4c11dbd3e0f08b336f91ff60fef0ac414eeb
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.