Instructions to use Undi95/UndiMix-v1-13b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Undi95/UndiMix-v1-13b with Transformers:

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

pipe = pipeline("text-generation", model="Undi95/UndiMix-v1-13b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Undi95/UndiMix-v1-13b")
model = AutoModelForCausalLM.from_pretrained("Undi95/UndiMix-v1-13b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Undi95/UndiMix-v1-13b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Undi95/UndiMix-v1-13b"
# 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-v1-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Undi95/UndiMix-v1-13b

SGLang

How to use Undi95/UndiMix-v1-13b 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-v1-13b" \
    --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-v1-13b",
		"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-v1-13b" \
        --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-v1-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Undi95/UndiMix-v1-13b with Docker Model Runner:
```
docker model run hf.co/Undi95/UndiMix-v1-13b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Command used :

python ties_merge.py TheBloke/Llama-2-13B-fp16 .UndiMix-v1-13b  --merge The-Face-Of-Goonery/Huginn-13b-v1.2 --merge Doctor-Shotgun/llama-2-13b-chat-limarp-v2-merged

Testing around...

Description

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

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
The-Face-Of-Goonery/Huginn-13b-v1.2
Doctor-Shotgun/llama-2-13b-chat-limarp-v2-merged

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

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	52.56
ARC (25-shot)	59.47
HellaSwag (10-shot)	82.45
MMLU (5-shot)	55.83
TruthfulQA (0-shot)	49.78
Winogrande (5-shot)	75.45
GSM8K (5-shot)	10.01
DROP (3-shot)	34.95