Instructions to use ChaoticNeutrals/Pasta-Lake-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ChaoticNeutrals/Pasta-Lake-7b with Transformers:

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

pipe = pipeline("text-generation", model="ChaoticNeutrals/Pasta-Lake-7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ChaoticNeutrals/Pasta-Lake-7b")
model = AutoModelForCausalLM.from_pretrained("ChaoticNeutrals/Pasta-Lake-7b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ChaoticNeutrals/Pasta-Lake-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ChaoticNeutrals/Pasta-Lake-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ChaoticNeutrals/Pasta-Lake-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ChaoticNeutrals/Pasta-Lake-7b

SGLang

How to use ChaoticNeutrals/Pasta-Lake-7b 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 "ChaoticNeutrals/Pasta-Lake-7b" \
    --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": "ChaoticNeutrals/Pasta-Lake-7b",
		"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 "ChaoticNeutrals/Pasta-Lake-7b" \
        --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": "ChaoticNeutrals/Pasta-Lake-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ChaoticNeutrals/Pasta-Lake-7b with Docker Model Runner:
```
docker model run hf.co/ChaoticNeutrals/Pasta-Lake-7b
```

Pasta-Lake-7b

Commit History

Adding Evaluation Results (#2)

51b7863
verified

Nitral

leaderboard-pr-bot commited on Mar 4, 2024

Update README.md

47d6443
verified

Nitral commited on Feb 25, 2024

Update README.md

d9a3a92
verified

Nitral commited on Feb 25, 2024

Update README.md

4c0ea3e
verified

Nitral commited on Feb 23, 2024

Delete ST PRESETS/Nitral's Smooth Brain Sampling - Pasta.json

341182d
verified

Nitral commited on Feb 19, 2024

Upload 2 files

a6d0490
verified

Nitral commited on Feb 19, 2024

Update README.md

4133ce1
verified

Nitral commited on Feb 15, 2024

Update README.md

fbb010c
verified

Nitral commited on Feb 15, 2024

Delete ST PRESETS/ChatML pasta instruct.json

8632b18
verified

Nitral commited on Feb 10, 2024