Text Generation
Transformers
PyTorch
Safetensors
English
llama
open-llama
mpt
model-fusion
fusellm
Eval Results (legacy)
text-generation-inference
Instructions to use Wanfq/FuseLLM-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Wanfq/FuseLLM-7B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Wanfq/FuseLLM-7B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Wanfq/FuseLLM-7B") model = AutoModelForCausalLM.from_pretrained("Wanfq/FuseLLM-7B", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Wanfq/FuseLLM-7B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Wanfq/FuseLLM-7B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Wanfq/FuseLLM-7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Wanfq/FuseLLM-7B
- SGLang
How to use Wanfq/FuseLLM-7B 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 "Wanfq/FuseLLM-7B" \ --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": "Wanfq/FuseLLM-7B", "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 "Wanfq/FuseLLM-7B" \ --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": "Wanfq/FuseLLM-7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Wanfq/FuseLLM-7B with Docker Model Runner:
docker model run hf.co/Wanfq/FuseLLM-7B
Update README.md
Browse files
README.md
CHANGED
|
@@ -35,6 +35,24 @@ _**Fanqi Wan<sup>†</sup>, Xinting Huang<sup>‡</sup>, Deng Cai<sup>‡</sup>,
|
|
| 35 |
_<sup>†</sup> Sun Yat-sen University,
|
| 36 |
<sup>‡</sup> Tencent AI Lab_
|
| 37 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 38 |
</div>
|
| 39 |
|
| 40 |
|
|
|
|
| 35 |
_<sup>†</sup> Sun Yat-sen University,
|
| 36 |
<sup>‡</sup> Tencent AI Lab_
|
| 37 |
|
| 38 |
+
| Model | BBH | ARC-easy | ARC-challenge | BoolQ | HellaSwag | OpenBookQA |
|
| 39 |
+
|----------------------------------------------------------|-------|----------|---------------|-------|-----------|------------|
|
| 40 |
+
| OpenLLaMA-7B | 33.87 | 69.70 | 41.38 | 72.29 | 74.53 | 41.00 |
|
| 41 |
+
| MPT-7B | 33.38 | 70.12 | 42.15 | 74.74 | 76.25 | 42.40 |
|
| 42 |
+
| Llama-2-7B | 39.70 | 74.58 | 46.33 | 77.71 | 76.00 | 44.20 |
|
| 43 |
+
| Llama-2-CLM-7B | 40.44 | 74.54 | 46.50 | 76.88 | 76.57 | 44.80 |
|
| 44 |
+
| 🤗 [FuseLLM-7B](https://huggingface.co/Wanfq/FuseLLM-7B) | 41.75 | 75.04 | 47.44 | 78.13 | 76.78 | 45.40 |
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
| Model | MultiPL-E | TrivialQA | DROP | LAMBADA | IWSLT2017 | SciBench |
|
| 48 |
+
|----------------------------------------------------------|-----------|-----------|-------|---------|-----------|----------|
|
| 49 |
+
| OpenLLaMA-7B | 18.11 | 39.96 | 22.31 | 70.31 | 5.51 | 0.68 |
|
| 50 |
+
| MPT-7B | 17.26 | 28.89 | 23.54 | 70.08 | 5.49 | 0.88 |
|
| 51 |
+
| Llama-2-7B | 14.63 | 52.46 | 27.25 | 73.28 | 6.48 | 0.14 |
|
| 52 |
+
| Llama-2-CLM-7B | 14.83 | 53.14 | 28.51 | 73.45 | 6.91 | 0.94 |
|
| 53 |
+
| 🤗 [FuseLLM-7B](https://huggingface.co/Wanfq/FuseLLM-7B) | 15.56 | 54.49 | 28.97 | 73.72 | 6.75 | 1.65 |
|
| 54 |
+
|
| 55 |
+
|
| 56 |
</div>
|
| 57 |
|
| 58 |
|