Instructions to use SparseLLM/ReluLLaMA-70B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SparseLLM/ReluLLaMA-70B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="SparseLLM/ReluLLaMA-70B")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("SparseLLM/ReluLLaMA-70B") model = AutoModelForCausalLM.from_pretrained("SparseLLM/ReluLLaMA-70B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use SparseLLM/ReluLLaMA-70B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "SparseLLM/ReluLLaMA-70B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SparseLLM/ReluLLaMA-70B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/SparseLLM/ReluLLaMA-70B
- SGLang
How to use SparseLLM/ReluLLaMA-70B 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 "SparseLLM/ReluLLaMA-70B" \ --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": "SparseLLM/ReluLLaMA-70B", "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 "SparseLLM/ReluLLaMA-70B" \ --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": "SparseLLM/ReluLLaMA-70B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use SparseLLM/ReluLLaMA-70B with Docker Model Runner:
docker model run hf.co/SparseLLM/ReluLLaMA-70B
Commit History
-
Update README.md
Yixin Song77ad0be -
Update README.md
Yixin Song9405b71 -
Update README.md
Yixin Songbc741ff -
Update README.md
Yixin Song1611c66 -
Create README.md
84e10ce
-
Upload model-00042-of-00061.safetensors with huggingface_hub
4fb6a80 -
Upload model-00028-of-00061.safetensors with huggingface_hub
c5c8393
-
Upload tokenizer_config.json with huggingface_hub
46400e8 -
Upload generation_config.json with huggingface_hub
0740655 -
Upload special_tokens_map.json with huggingface_hub
632ae0a -
Upload tokenizer.model with huggingface_hub
0d61f78 -
Upload model.safetensors.index.json with huggingface_hub
786675d -
Upload model-00009-of-00061.safetensors with huggingface_hub
a6fea6b -
Upload model-00008-of-00061.safetensors with huggingface_hub
7a05749 -
Upload model-00007-of-00061.safetensors with huggingface_hub
875c5e2 -
Upload model-00006-of-00061.safetensors with huggingface_hub
f216d2c -
Upload model-00005-of-00061.safetensors with huggingface_hub
c5c82ee -
Upload model-00004-of-00061.safetensors with huggingface_hub
5ead5d2 -
Upload model-00003-of-00061.safetensors with huggingface_hub
d50ae04 -
Upload model-00002-of-00061.safetensors with huggingface_hub
599080c -
Upload model-00001-of-00061.safetensors with huggingface_hub
184db9a
-
Upload model-00060-of-00061.safetensors with huggingface_hub
22e4b7a -
Upload model-00059-of-00061.safetensors with huggingface_hub
c5d898e -
Upload model-00058-of-00061.safetensors with huggingface_hub
13d9d81 -
Upload model-00057-of-00061.safetensors with huggingface_hub
790f913 -
Upload model-00056-of-00061.safetensors with huggingface_hub
f889b6d -
Upload model-00055-of-00061.safetensors with huggingface_hub
dc404dd -
Upload model-00054-of-00061.safetensors with huggingface_hub
d001122 -
Upload model-00053-of-00061.safetensors with huggingface_hub
d34db68 -
Upload model-00052-of-00061.safetensors with huggingface_hub
3f324ab -
Upload model-00051-of-00061.safetensors with huggingface_hub
25b346c -
Upload model-00050-of-00061.safetensors with huggingface_hub
c5718e0 -
Upload model-00049-of-00061.safetensors with huggingface_hub
a7d2130 -
Upload model-00048-of-00061.safetensors with huggingface_hub
b34cb42 -
Upload model-00047-of-00061.safetensors with huggingface_hub
34fb58c -
Upload model-00046-of-00061.safetensors with huggingface_hub
565296d -
Upload model-00045-of-00061.safetensors with huggingface_hub
3e98a19 -
Upload model-00044-of-00061.safetensors with huggingface_hub
93037c1 -
Upload model-00043-of-00061.safetensors with huggingface_hub
8d7263e -
Upload model-00041-of-00061.safetensors with huggingface_hub
7d510b3 -
Upload model-00040-of-00061.safetensors with huggingface_hub
f2b55ef -
Upload model-00039-of-00061.safetensors with huggingface_hub
0807ee4 -
Upload model-00038-of-00061.safetensors with huggingface_hub
bdd7a01 -
Upload model-00037-of-00061.safetensors with huggingface_hub
4787e2b -
Upload model-00036-of-00061.safetensors with huggingface_hub
74a79f0 -
Upload model-00035-of-00061.safetensors with huggingface_hub
659f51b -
Upload model-00034-of-00061.safetensors with huggingface_hub
db1ce18 -
Upload model-00033-of-00061.safetensors with huggingface_hub
a019078 -
Upload model-00032-of-00061.safetensors with huggingface_hub
649eb41 -
Upload model-00031-of-00061.safetensors with huggingface_hub
97ce188