Instructions to use TomGrc/FusionNet_7Bx2_MoE_14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TomGrc/FusionNet_7Bx2_MoE_14B with Transformers:

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

pipe = pipeline("text-generation", model="TomGrc/FusionNet_7Bx2_MoE_14B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TomGrc/FusionNet_7Bx2_MoE_14B")
model = AutoModelForCausalLM.from_pretrained("TomGrc/FusionNet_7Bx2_MoE_14B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TomGrc/FusionNet_7Bx2_MoE_14B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TomGrc/FusionNet_7Bx2_MoE_14B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TomGrc/FusionNet_7Bx2_MoE_14B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TomGrc/FusionNet_7Bx2_MoE_14B

SGLang

How to use TomGrc/FusionNet_7Bx2_MoE_14B 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 "TomGrc/FusionNet_7Bx2_MoE_14B" \
    --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": "TomGrc/FusionNet_7Bx2_MoE_14B",
		"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 "TomGrc/FusionNet_7Bx2_MoE_14B" \
        --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": "TomGrc/FusionNet_7Bx2_MoE_14B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TomGrc/FusionNet_7Bx2_MoE_14B with Docker Model Runner:
```
docker model run hf.co/TomGrc/FusionNet_7Bx2_MoE_14B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

FusionNet

Fine-tuned model on English language using MoE method.

Model description

The FusionNet is a model to experiment with the MoE method, which could significantly increase the performance of the original model. The FusionNet has 12.9B parameters, and this model is fine-tuned. Enjoy!

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	75.91
AI2 Reasoning Challenge (25-Shot)	73.55
HellaSwag (10-Shot)	88.84
MMLU (5-Shot)	64.68
TruthfulQA (0-shot)	69.60
Winogrande (5-shot)	88.16
GSM8k (5-shot)	70.66

Downloads last month: 194

Safetensors

Model size

13B params

Tensor type

BF16

Model tree for TomGrc/FusionNet_7Bx2_MoE_14B

Merges

4 models

Quantizations

6 models

Space using TomGrc/FusionNet_7Bx2_MoE_14B 1

Evaluation results

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

73.550
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

88.840
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

64.680
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

69.600
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

88.160
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

70.660