Instructions to use IFM/Amber with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use IFM/Amber with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="IFM/Amber")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("IFM/Amber") model = AutoModelForCausalLM.from_pretrained("IFM/Amber", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use IFM/Amber with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "IFM/Amber" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "IFM/Amber", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/IFM/Amber
- SGLang
How to use IFM/Amber 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 "IFM/Amber" \ --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": "IFM/Amber", "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 "IFM/Amber" \ --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": "IFM/Amber", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use IFM/Amber with Docker Model Runner:
docker model run hf.co/IFM/Amber
Download pytorch_model-00001-of-00006.bin from IFM/Amber: direct link, hf CLI and curl.
- Browser
- Download file 4.84 GB
-
https://huggingface.co/IFM/Amber/resolve/refs%2Fpr%2F1/pytorch_model-00001-of-00006.bin
- Command line
-
hf download hf://IFM/Amber@refs/pr/1/pytorch_model-00001-of-00006.bin
-
curl -L -o pytorch_model-00001-of-00006.bin https://huggingface.co/IFM/Amber/resolve/refs%2Fpr%2F1/pytorch_model-00001-of-00006.bin
4.84 GB
- Xet hash:
- 364e8a391ebce4cab097af01bf0cf942f42476a8d49d17f5fe35932ecb2ec0e9
- Size of remote file:
- 4.84 GB
- SHA256:
- cc640b954d07c1a3bb13e4fb8355129d64bb2805b0625c9b800fde564e3f7692
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.