Instructions to use IFM/AmberSafe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use IFM/AmberSafe with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="IFM/AmberSafe")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("IFM/AmberSafe") model = AutoModelForCausalLM.from_pretrained("IFM/AmberSafe", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use IFM/AmberSafe with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "IFM/AmberSafe" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "IFM/AmberSafe", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/IFM/AmberSafe
- SGLang
How to use IFM/AmberSafe 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/AmberSafe" \ --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/AmberSafe", "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/AmberSafe" \ --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/AmberSafe", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use IFM/AmberSafe with Docker Model Runner:
docker model run hf.co/IFM/AmberSafe
Commit ·
4ef118e
1
Parent(s): 843d8ac
Update README.md
Browse files
README.md
CHANGED
|
@@ -47,7 +47,7 @@ We present AmberSafe, an instruction following model finetuned from [LLM360/Ambe
|
|
| 47 |
- [Fully processed Amber pretraining data](https://huggingface.co/datasets/LLM360/AmberDatasets)
|
| 48 |
|
| 49 |
|
| 50 |
-
# Loading
|
| 51 |
|
| 52 |
```python
|
| 53 |
import torch
|
|
@@ -72,7 +72,7 @@ Alternatively, you may use [FastChat](https://github.com/lm-sys/FastChat):
|
|
| 72 |
python3 -m fastchat.serve.cli --model-path LLM360/AmberSafe
|
| 73 |
```
|
| 74 |
|
| 75 |
-
#
|
| 76 |
|
| 77 |
## DataMix
|
| 78 |
| Subset | Number of rows | License |
|
|
|
|
| 47 |
- [Fully processed Amber pretraining data](https://huggingface.co/datasets/LLM360/AmberDatasets)
|
| 48 |
|
| 49 |
|
| 50 |
+
# Loading AmberSafe
|
| 51 |
|
| 52 |
```python
|
| 53 |
import torch
|
|
|
|
| 72 |
python3 -m fastchat.serve.cli --model-path LLM360/AmberSafe
|
| 73 |
```
|
| 74 |
|
| 75 |
+
# AmberSafe Finetuning Details
|
| 76 |
|
| 77 |
## DataMix
|
| 78 |
| Subset | Number of rows | License |
|