Instructions to use Undi95/UndiMix-v2-13b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Undi95/UndiMix-v2-13b with Transformers:

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

pipe = pipeline("text-generation", model="Undi95/UndiMix-v2-13b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Undi95/UndiMix-v2-13b")
model = AutoModelForCausalLM.from_pretrained("Undi95/UndiMix-v2-13b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Undi95/UndiMix-v2-13b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Undi95/UndiMix-v2-13b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Undi95/UndiMix-v2-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Undi95/UndiMix-v2-13b

SGLang

How to use Undi95/UndiMix-v2-13b 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/UndiMix-v2-13b" \
    --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/UndiMix-v2-13b",
		"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/UndiMix-v2-13b" \
        --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/UndiMix-v2-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Undi95/UndiMix-v2-13b with Docker Model Runner:
```
docker model run hf.co/Undi95/UndiMix-v2-13b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

This model speak way more than the v1, be warned.

Command used :

python ties_merge.py TheBloke/Llama-2-13B-fp16 ./UndiMix-v2-13b  --merge jondurbin/airoboros-l2-13b-2.1 --density 0.10 --merge IkariDev/Athena-v1 --density 0.10 --merge Undi95/UndiMix-v1-13b --density 0.80 --cuda

Testing around²...

Description

This repo contains fp16 files of personal mix : "UndiMix-v2".

It can be hot, serious, playful, and can use emoji thanks to llama-2-13b-chat-limarp-v2-merged.

Models used

TheBloke/Llama-2-13B-fp16 (base)
Undi95/MythoMax-L2-Kimiko-v2-13b (0.33)
The-Face-Of-Goonery/Huginn-13b-v1.2 (0.33)
Doctor-Shotgun/llama-2-13b-chat-limarp-v2-merged (0.33)
====REMIX====
jondurbin/airoboros-l2-13b-2.1 (0.10)
IkariDev/Athena-v1 (0.10)
UndiMix-v1-13b (0.80)

Prompt template: Alpaca

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

### Instruction:
{prompt}

### Response:

Special thanks to Sushi kek

Downloads last month: 40

Safetensors

Model size

13B params

Tensor type

F32

BF16

Model tree for Undi95/UndiMix-v2-13b

Finetunes

1 model

Quantizations

3 models

Collection including Undi95/UndiMix-v2-13b

Undimix Series

Collection

Series of old models I made for me in the past, some people always use it today, but I found them less good than my recents merges • 4 items • Updated Oct 14, 2023 • 1