Instructions to use jeiku/Mewthree_7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jeiku/Mewthree_7B with Transformers:

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

pipe = pipeline("text-generation", model="jeiku/Mewthree_7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jeiku/Mewthree_7B")
model = AutoModelForCausalLM.from_pretrained("jeiku/Mewthree_7B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jeiku/Mewthree_7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jeiku/Mewthree_7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jeiku/Mewthree_7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/jeiku/Mewthree_7B

SGLang

How to use jeiku/Mewthree_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 "jeiku/Mewthree_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": "jeiku/Mewthree_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 "jeiku/Mewthree_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": "jeiku/Mewthree_7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use jeiku/Mewthree_7B with Docker Model Runner:
```
docker model run hf.co/jeiku/Mewthree_7B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Mewthree

Draws upon the Prodigy lineage with some no robots tossed in for good measure. Dipped its toes in some memerboard essence and added a kiss of BioMistral for anatomy. Applied a DPO LoRA over top.

Seems to do markdown well. It's an overall balanced model with a focus on RP.

Downloads last month: 50

Safetensors

Model size

7B params

Tensor type

F16

Model tree for jeiku/Mewthree_7B

Base model

Krisbiantoro/mistral7b_dpo_en

Finetuned

(1)

this model

Quantizations

3 models