Instructions to use Undi95/ReMM-v2.1-L2-13B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Undi95/ReMM-v2.1-L2-13B with Transformers:

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

pipe = pipeline("text-generation", model="Undi95/ReMM-v2.1-L2-13B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Undi95/ReMM-v2.1-L2-13B")
model = AutoModelForCausalLM.from_pretrained("Undi95/ReMM-v2.1-L2-13B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Undi95/ReMM-v2.1-L2-13B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Undi95/ReMM-v2.1-L2-13B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Undi95/ReMM-v2.1-L2-13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Undi95/ReMM-v2.1-L2-13B

SGLang

How to use Undi95/ReMM-v2.1-L2-13B 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/ReMM-v2.1-L2-13B" \
    --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/ReMM-v2.1-L2-13B",
		"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/ReMM-v2.1-L2-13B" \
        --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/ReMM-v2.1-L2-13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Undi95/ReMM-v2.1-L2-13B with Docker Model Runner:
```
docker model run hf.co/Undi95/ReMM-v2.1-L2-13B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Re:MythoMax v2.1 (ReMM v2.1) is a recreation trial of the original MythoMax-L2-B13 with updated models.

This merge use SLERP merging method to merge ReML v2.1 and Huginn v1.2.

Explaination :

- ReML-v2.1: (Chronos-Beluga v2/Hermes/Airboros 2.2)
=> Keeping The-Face-Of-Goonery/Chronos-Beluga-v2-13bfp16
=> Replacing jondurbin/spicyboros-13b-2.2 by jondurbin/airoboros-l2-13b-2.2 (last version)
=> Keeping NousResearch/Nous-Hermes-Llama2-13b

With that :
- ReMM-v2.1: (ReML v2.1/Huginn v1.2)
=> Replacing ReML by the one above (ReML v2.1)
=> Keeping The-Face-Of-Goonery/Huginn-13b-v1.2

Description

This repo contains fp16 files of ReMM v2.1, a recreation of the original MythoMax, but updated and merged with SLERP.

Models used

The-Face-Of-Goonery/Chronos-Beluga-v2-13bfp16
jondurbin/airoboros-l2-13b-2.2
NousResearch/Nous-Hermes-Llama2-13b
The-Face-Of-Goonery/Huginn-13b-v1.2
ReML-v2.1-L2-13B (Private recreation trial of an updated Mythologic-L2-13B)

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.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	50.41
ARC (25-shot)	61.43
HellaSwag (10-shot)	83.92
MMLU (5-shot)	55.95
TruthfulQA (0-shot)	50.3
Winogrande (5-shot)	75.93
GSM8K (5-shot)	12.74
DROP (3-shot)	12.62

Downloads last month: 212

Safetensors

Model size

13B params

Tensor type

F32

BF16

Model tree for Undi95/ReMM-v2.1-L2-13B

Quantizations

6 models

Collection including Undi95/ReMM-v2.1-L2-13B

ReMM series

Collection

Models based on MythoMax with updated base models. • 4 items • Updated Oct 12, 2023 • 10