Instructions to use Kooten/Pasta-Lake-7b-6bpw-exl2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kooten/Pasta-Lake-7b-6bpw-exl2 with Transformers:

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

pipe = pipeline("text-generation", model="Kooten/Pasta-Lake-7b-6bpw-exl2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Kooten/Pasta-Lake-7b-6bpw-exl2")
model = AutoModelForMultimodalLM.from_pretrained("Kooten/Pasta-Lake-7b-6bpw-exl2")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Kooten/Pasta-Lake-7b-6bpw-exl2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Kooten/Pasta-Lake-7b-6bpw-exl2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kooten/Pasta-Lake-7b-6bpw-exl2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Kooten/Pasta-Lake-7b-6bpw-exl2

SGLang

How to use Kooten/Pasta-Lake-7b-6bpw-exl2 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 "Kooten/Pasta-Lake-7b-6bpw-exl2" \
    --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": "Kooten/Pasta-Lake-7b-6bpw-exl2",
		"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 "Kooten/Pasta-Lake-7b-6bpw-exl2" \
        --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": "Kooten/Pasta-Lake-7b-6bpw-exl2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Kooten/Pasta-Lake-7b-6bpw-exl2 with Docker Model Runner:
```
docker model run hf.co/Kooten/Pasta-Lake-7b-6bpw-exl2
```

Kooten commited on Feb 10, 2024

Commit

0e5eb71

verified ·

1 Parent(s): fa3b4a2

Update README.md

Browse files

Files changed (1) hide show

README.md +7 -9

README.md CHANGED Viewed

@@ -16,17 +16,15 @@ Exllama quant of [Test157t/Pasta-Lake-7b](https://huggingface.co/Test157t/Pasta-
 EXL2: [8bpw](https://huggingface.co/Kooten/Pasta-Lake-7b-8bpw-exl2), [6bpw](https://huggingface.co/Kooten/Pasta-Lake-7b-6bpw-exl2), [5bpw](https://huggingface.co/Kooten/Pasta-Lake-7b-5bpw-exl2), [4bpw](https://huggingface.co/Kooten/Pasta-Lake-7b-4bpw-exl2)
-## Prompt Format: ChatML
-The merge contains multiple formats, alpaca, mistral and chatml however chatml should be a good place to start.
-[SillyTavern Presets](https://huggingface.co/Kooten/Pasta-Lake-7b-6bpw-exl2/tree/main/Presets)
 ```
-<|im_start|>system<|im_end|>
-<|im_start|>user <|im_end|>
-<|im_start|>assistant
 ```
 ## Contact

 EXL2: [8bpw](https://huggingface.co/Kooten/Pasta-Lake-7b-8bpw-exl2), [6bpw](https://huggingface.co/Kooten/Pasta-Lake-7b-6bpw-exl2), [5bpw](https://huggingface.co/Kooten/Pasta-Lake-7b-5bpw-exl2), [4bpw](https://huggingface.co/Kooten/Pasta-Lake-7b-4bpw-exl2)
+## Prompt format: Alpaca
 ```
+Below is an instruction that describes a task. Write a response that appropriately completes the request.
+### Instruction:
+{prompt}
+### Input:
+{input}
+### Response:
 ```
 ## Contact