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") - Inference
- 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
Update README.md
Browse files
README.md
CHANGED
|
@@ -35,7 +35,9 @@ Amber is not a SOTA model. Amber is released to make LLM training knowledge acce
|
|
| 35 |
| [Checkpoint 355](https://huggingface.co/LLM360/Amber/tree/ckpt_355) | [Checkpoint 350](https://huggingface.co/LLM360/Amber/tree/ckpt_350) |
|
| 36 |
| [Checkpoint 354](https://huggingface.co/LLM360/Amber/tree/ckpt_354) | [Checkpoint 349](https://huggingface.co/LLM360/Amber/tree/ckpt_349) |
|
| 37 |
|
| 38 |
-
To downloading other checkpoints, change the branch from 'main' to the checkpoint you want (e.g. 'ckpt_000').
|
|
|
|
|
|
|
| 39 |
|
| 40 |
## 🟠 Loading Amber
|
| 41 |
|
|
|
|
| 35 |
| [Checkpoint 355](https://huggingface.co/LLM360/Amber/tree/ckpt_355) | [Checkpoint 350](https://huggingface.co/LLM360/Amber/tree/ckpt_350) |
|
| 36 |
| [Checkpoint 354](https://huggingface.co/LLM360/Amber/tree/ckpt_354) | [Checkpoint 349](https://huggingface.co/LLM360/Amber/tree/ckpt_349) |
|
| 37 |
|
| 38 |
+
To downloading other checkpoints, change the branch from 'main' to the checkpoint you want (e.g. 'ckpt_000').
|
| 39 |
+
|
| 40 |
+
This is completed on the 'Files and versions' tab (to the right of the Model Card).
|
| 41 |
|
| 42 |
## 🟠 Loading Amber
|
| 43 |
|