Instructions to use ibivibiv/orthorus-125b-moe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ibivibiv/orthorus-125b-moe with Transformers:

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

pipe = pipeline("text-generation", model="ibivibiv/orthorus-125b-moe")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ibivibiv/orthorus-125b-moe")
model = AutoModelForCausalLM.from_pretrained("ibivibiv/orthorus-125b-moe")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ibivibiv/orthorus-125b-moe with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ibivibiv/orthorus-125b-moe"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ibivibiv/orthorus-125b-moe",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ibivibiv/orthorus-125b-moe

SGLang

How to use ibivibiv/orthorus-125b-moe 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/orthorus-125b-moe" \
    --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/orthorus-125b-moe",
		"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/orthorus-125b-moe" \
        --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/orthorus-125b-moe",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ibivibiv/orthorus-125b-moe with Docker Model Runner:
```
docker model run hf.co/ibivibiv/orthorus-125b-moe
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

This is a test run for a future 70b parameter models moe model. I took WizardLM/WizardLM-70B-V1.0 and migtissera/Synthia-70B as two base models and created the discriminator prompts to push technical, logic, and math type questions to the Wizard side and then all creative or conversation questions to the Synthia side. Now that this is working for me I am going to move to fine tuning models for more specific tasks. This model takes about 240GB of VRAM for full resolution inference. As far as I know, it is the first 125B parameter moe model publicly available. I plan on making more and sharing of course.

Hopefully I can add more info on this model, it loads perfectly for me and responds nicely. It might take me a bit since I want to make "Cerberus" with the fine tuned models and get it released. But enjoy this one, llama2 model.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	69.58
AI2 Reasoning Challenge (25-Shot)	67.66
HellaSwag (10-Shot)	85.52
MMLU (5-Shot)	68.94
TruthfulQA (0-shot)	56.27
Winogrande (5-shot)	82.32
GSM8k (5-shot)	56.79

Downloads last month: 92

Safetensors

Model size

125B params

Tensor type

F32

Model tree for ibivibiv/orthorus-125b-moe

Quantizations

2 models

Collection including ibivibiv/orthorus-125b-moe

Experimental Models

Collection

These are either first attempts at a specific goal or just a shot in the dark to try something new • 11 items • Updated Feb 29, 2024

Evaluation results

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

67.660
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

85.520
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

68.940
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

56.270
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

82.320
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

56.790