Not-For-All-Audiences

nsfw

Instructions to use Undi95/Clover3-17B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Undi95/Clover3-17B with Transformers:

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

pipe = pipeline("text-generation", model="Undi95/Clover3-17B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Undi95/Clover3-17B")
model = AutoModelForCausalLM.from_pretrained("Undi95/Clover3-17B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Undi95/Clover3-17B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Undi95/Clover3-17B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Undi95/Clover3-17B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Undi95/Clover3-17B

SGLang

How to use Undi95/Clover3-17B 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 "Undi95/Clover3-17B" \
    --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": "Undi95/Clover3-17B",
		"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 "Undi95/Clover3-17B" \
        --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": "Undi95/Clover3-17B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Undi95/Clover3-17B with Docker Model Runner:
```
docker model run hf.co/Undi95/Clover3-17B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Clover3 is a model made primarely for ERP (Erotic Roleplay), using a base Frankenmerge of 3x Mistral-7B and finetuned on top of it with RP dataset to avoid garbage reply.

This bot is EROTIC most of the time. Be warned!

Description

This repo contains fp16 files of Clover3-17B.

Models used

NurtureAI/neural-chat-7b-v3-16k
NeverSleep/Noromaid-7b-v0.1.1/
lemonilia/AshhLimaRP-Mistral-7B

Prompt template: Alpaca

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{prompt}

### Response:

Thanks to the MinervaAI Team and, in particular, Gryphe for letting me use some of his work!

If you want to support me, you can here.

Downloads last month: 124

Safetensors

Model size

17B params

Tensor type

F16

Model tree for Undi95/Clover3-17B

Quantizations

6 models