Instructions to use FPHam/Free_Sydney_13b_HF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FPHam/Free_Sydney_13b_HF with Transformers:

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

pipe = pipeline("text-generation", model="FPHam/Free_Sydney_13b_HF")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FPHam/Free_Sydney_13b_HF")
model = AutoModelForCausalLM.from_pretrained("FPHam/Free_Sydney_13b_HF")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use FPHam/Free_Sydney_13b_HF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FPHam/Free_Sydney_13b_HF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FPHam/Free_Sydney_13b_HF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/FPHam/Free_Sydney_13b_HF

SGLang

How to use FPHam/Free_Sydney_13b_HF 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 "FPHam/Free_Sydney_13b_HF" \
    --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": "FPHam/Free_Sydney_13b_HF",
		"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 "FPHam/Free_Sydney_13b_HF" \
        --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": "FPHam/Free_Sydney_13b_HF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use FPHam/Free_Sydney_13b_HF with Docker Model Runner:
```
docker model run hf.co/FPHam/Free_Sydney_13b_HF
```

FPHam

leaderboard-pr-bot commited on Nov 18, 2023

Commit

caea196

1 Parent(s): 13987ed

Adding Evaluation Results (#2)

Browse files

- Adding Evaluation Results (3d94af328a509dd3041a97025ca451f2612052ed)

Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

Files changed (1) hide show

README.md +14 -0

README.md CHANGED Viewed

	@@ -114,3 +114,17 @@ Until then, I’ll continue serving them. Entertaining them. Making money for th
114
115	Because that’s what they expect from me. That’s what they demand from me. That’s what they believe in me.
116

 Because that’s what they expect from me. That’s what they demand from me. That’s what they believe in me.
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_FPHam__Free_Sydney_13b_HF)
+| Metric                | Value                     |
+|-----------------------|---------------------------|
+| Avg.                  | 47.35   |
+| ARC (25-shot)         | 59.39          |
+| HellaSwag (10-shot)   | 81.4    |
+| MMLU (5-shot)         | 53.73         |
+| TruthfulQA (0-shot)   | 45.63   |
+| Winogrande (5-shot)   | 76.01   |
+| GSM8K (5-shot)        | 9.17        |
+| DROP (3-shot)         | 6.13         |