Instructions to use grimjim/Daichi-Instructed-12B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use grimjim/Daichi-Instructed-12B with Transformers:

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

pipe = pipeline("image-text-to-text", model="grimjim/Daichi-Instructed-12B")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("grimjim/Daichi-Instructed-12B")
model = AutoModelForImageTextToText.from_pretrained("grimjim/Daichi-Instructed-12B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use grimjim/Daichi-Instructed-12B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "grimjim/Daichi-Instructed-12B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "grimjim/Daichi-Instructed-12B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/grimjim/Daichi-Instructed-12B

SGLang

How to use grimjim/Daichi-Instructed-12B 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 "grimjim/Daichi-Instructed-12B" \
    --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": "grimjim/Daichi-Instructed-12B",
		"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 "grimjim/Daichi-Instructed-12B" \
        --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": "grimjim/Daichi-Instructed-12B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use grimjim/Daichi-Instructed-12B with Docker Model Runner:
```
docker model run hf.co/grimjim/Daichi-Instructed-12B
```

Questioning utility.

by Erquint - opened Mar 21

Discussion

Erquint

Mar 21

So, you took a painstakingly uncensored finetune of one of the most infamously censored model ever created and reinforced the nanny base back into it as hard as you could, huh, including both the corpo-poisoned PT and IT..? I fail to see the point of this regression.

grimjim

Owner Mar 23

From a geometric standpoint, to prove that the intervention direction can be reversed successfully, rather than making the model incoherent.

And ultimately to demonstrate that too much safety isn't really what most people want. People aren't supposed to enjoy this model.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment