Instructions to use itspat/RemmMistral13b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use itspat/RemmMistral13b with Transformers:

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

pipe = pipeline("text-generation", model="itspat/RemmMistral13b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("itspat/RemmMistral13b")
model = AutoModelForCausalLM.from_pretrained("itspat/RemmMistral13b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use itspat/RemmMistral13b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "itspat/RemmMistral13b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "itspat/RemmMistral13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/itspat/RemmMistral13b

SGLang

How to use itspat/RemmMistral13b 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 "itspat/RemmMistral13b" \
    --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": "itspat/RemmMistral13b",
		"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 "itspat/RemmMistral13b" \
        --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": "itspat/RemmMistral13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use itspat/RemmMistral13b with Docker Model Runner:
```
docker model run hf.co/itspat/RemmMistral13b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

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

This merge use Gradient merging method to merge ReML-Mistral v2.2 and Huginn.

Explaination :

- ReML-Mistral-v2.2: (Chronos-Beluga v2/Hermes/Airboros 2.2.1 + LoRA)
=> The-Face-Of-Goonery/Chronos-Beluga-v2-13bfp16
=> jondurbin/airoboros-l2-13b-2.2 by jondurbin/airoboros-l2-13b-2.2.1
=> NousResearch/Nous-Hermes-Llama2-13b

=> Applying Undi95/llama2-to-mistral-diff at 1.0 at the end

With that :
- ReMM-Mistral: (ReML-Mistral-v2.2/Huginn)
=> ReMM by the one above
=> The-Face-Of-Goonery/Huginn-13b-FP16

Description

This repo contains fp16 files of ReMM-Mistral, a recreation of the original MythoMax, but updated and merged with Gradient method and Mistral data.

Models used

The-Face-Of-Goonery/Chronos-Beluga-v2-13bfp16
jondurbin/airoboros-l2-13b-2.2.1
NousResearch/Nous-Hermes-Llama2-13b
The-Face-Of-Goonery/Huginn-13b-FP16
Undi95/ReML-Mistral-v2.2-13B (Private recreation trial of an updated Mythologic-L2-13B with Mistral data)
Undi95/llama2-to-mistral-diff

Prompt template: Alpaca

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

### Instruction:
{prompt}

### Response:

A big thanks to KoboldAI dev' Henky for giving me a machine powerfull enough to do some of my work!

If you want to support me, you can here.

Downloads last month: 4

Model tree for itspat/RemmMistral13b

Finetunes

1 model

Quantizations

2 models