Text Generation
Transformers
PyTorch
RefinedWeb
falcon-40b
rlhf
falcon
custom_code
text-generation-inference
Instructions to use lightonai/alfred-40b-0723 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lightonai/alfred-40b-0723 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="lightonai/alfred-40b-0723", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("lightonai/alfred-40b-0723", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use lightonai/alfred-40b-0723 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "lightonai/alfred-40b-0723" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "lightonai/alfred-40b-0723", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/lightonai/alfred-40b-0723
- SGLang
How to use lightonai/alfred-40b-0723 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 "lightonai/alfred-40b-0723" \ --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": "lightonai/alfred-40b-0723", "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 "lightonai/alfred-40b-0723" \ --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": "lightonai/alfred-40b-0723", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use lightonai/alfred-40b-0723 with Docker Model Runner:
docker model run hf.co/lightonai/alfred-40b-0723
Commit ·
feb92bd
1
Parent(s): e60fdf7
Update README.md
Browse files
README.md
CHANGED
|
@@ -125,7 +125,7 @@ Samples from each of the datasets have been programmatically formatted to chat,
|
|
| 125 |
| Clip Range Value | 0.2 |
|
| 126 |
| Whiten Advantages | `true` |
|
| 127 |
| Whiten Rewards | `false` |
|
| 128 |
-
|
|
| 129 |
| Max Steps | 200 |
|
| 130 |
| PPO steps/epoch | 1 |
|
| 131 |
| Value steps/epoch | 8 |
|
|
|
|
| 125 |
| Clip Range Value | 0.2 |
|
| 126 |
| Whiten Advantages | `true` |
|
| 127 |
| Whiten Rewards | `false` |
|
| 128 |
+
| Score on EOD | `true` |
|
| 129 |
| Max Steps | 200 |
|
| 130 |
| PPO steps/epoch | 1 |
|
| 131 |
| Value steps/epoch | 8 |
|