Instructions to use ibivibiv/multimaster-7b-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ibivibiv/multimaster-7b-v2 with Transformers:

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

pipe = pipeline("text-generation", model="ibivibiv/multimaster-7b-v2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ibivibiv/multimaster-7b-v2")
model = AutoModelForCausalLM.from_pretrained("ibivibiv/multimaster-7b-v2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ibivibiv/multimaster-7b-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ibivibiv/multimaster-7b-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ibivibiv/multimaster-7b-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ibivibiv/multimaster-7b-v2

SGLang

How to use ibivibiv/multimaster-7b-v2 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 "ibivibiv/multimaster-7b-v2" \
    --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": "ibivibiv/multimaster-7b-v2",
		"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 "ibivibiv/multimaster-7b-v2" \
        --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": "ibivibiv/multimaster-7b-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ibivibiv/multimaster-7b-v2 with Docker Model Runner:
```
docker model run hf.co/ibivibiv/multimaster-7b-v2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Card for MultiMaster 5x7B

Version 2 of a general purpose model for knowledge.

Model Details

Model Description

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

Developed by: ibivibiv
Funded by: ibivibiv
Shared by: ibivibiv
Model type: Mixtral
Language(s) (NLP): English
License: Apache 2

Uses

General Knowledge

Direct Use

Evaluation

Coming Soon

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	73.33
AI2 Reasoning Challenge (25-Shot)	70.48
HellaSwag (10-Shot)	87.59
MMLU (5-Shot)	65.09
TruthfulQA (0-shot)	60.63
Winogrande (5-shot)	84.29
GSM8k (5-shot)	71.87

Downloads last month: 70

Safetensors

Model size

35B params

Tensor type

F32

Model tree for ibivibiv/multimaster-7b-v2

Quantizations

2 models

Collection including ibivibiv/multimaster-7b-v2

Multi Master

Collection

MOE models for general query information models that have good prior knowledge training • 6 items • Updated Feb 29, 2024

Evaluation results

normalized accuracy on AI2 Reasoning Challenge (25-Shot)
test set Open LLM Leaderboard

70.480
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

87.590
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

65.090
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

60.630
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

84.290
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

71.870