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 "appvoid/palmer-001" \
--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": "appvoid/palmer-001",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'
palmer
a better base model
palmer is a series of ~1b parameters language models fine-tuned to be used as base models instead of using custom prompts for tasks. This means that it can be further fine-tuned on more data with custom prompts as usual or be used for downstream tasks as any base model you can get. The model has the best of both worlds: some "bias" to act as an assistant, but also the abillity to predict the next-word from its internet knowledge base. It's a 1.1b llama 2 model so you can use it with your favorite tools/frameworks.
evaluation
| Model | ARC_C | HellaSwag | PIQA | Winogrande |
|---|---|---|---|---|
| tinyllama-2t | 0.2807 | 0.5463 | 0.7067 | 0.5683 |
| palmer-001 | 0.2807 | 0.5524 | 0.7106 | 0.5896 |
training
Training took ~3.5 P100 gpu hours. It was trained on 15,000 gpt-4 shuffled samples. palmer was fine-tuned using lower learning rates ensuring it keeps as much general knowledge as possible.
Note: highly experimenal yet! Your feedback will make it better.
prompt
On this article, we are going to learn
palmer-001: about the different types of data that are used in the field of data science...
what is javascript
palmer-001: ? JavaScript is a programming language that is used to create dynamic websites and applications...
As you can notice, the model actually completes by default questions that are the most-likely to be asked, which is good because most people will use it to answer as a chatbot.
Choose this only if you would like to get a half-baked model to continue pre-training.
- Downloads last month
- 9
Install from pip and serve model
# Install SGLang from pip: pip install sglang# Start the SGLang server: python3 -m sglang.launch_server \ --model-path "appvoid/palmer-001" \ --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": "appvoid/palmer-001", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'