Instructions to use ericpolewski/AIRIC-The-Intern with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ericpolewski/AIRIC-The-Intern with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="ericpolewski/AIRIC-The-Intern")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ericpolewski/AIRIC-The-Intern")
model = AutoModelForCausalLM.from_pretrained("ericpolewski/AIRIC-The-Intern")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ericpolewski/AIRIC-The-Intern with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ericpolewski/AIRIC-The-Intern"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ericpolewski/AIRIC-The-Intern",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ericpolewski/AIRIC-The-Intern

SGLang

How to use ericpolewski/AIRIC-The-Intern 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 "ericpolewski/AIRIC-The-Intern" \
    --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": "ericpolewski/AIRIC-The-Intern",
		"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 "ericpolewski/AIRIC-The-Intern" \
        --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": "ericpolewski/AIRIC-The-Intern",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ericpolewski/AIRIC-The-Intern with Docker Model Runner:
```
docker model run hf.co/ericpolewski/AIRIC-The-Intern
```

This is an instruct model. It's to test out the effects of my dataset on the InternLM model if you just change everything to say "Llama" instead of "InternLM" in the config files.

I had a theory that a lot of these models are just Llama models with extraneous loaders. This is to test that theory.

Trained at rank 256 for 1 epoch at constant learning rate.

Downloads last month: 66

Safetensors

Model size

20B params

Tensor type

F16