Instructions to use diffnamehard/Psyfighter2-Noromaid-ties-13B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use diffnamehard/Psyfighter2-Noromaid-ties-13B with Transformers:

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

pipe = pipeline("text-generation", model="diffnamehard/Psyfighter2-Noromaid-ties-13B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("diffnamehard/Psyfighter2-Noromaid-ties-13B")
model = AutoModelForCausalLM.from_pretrained("diffnamehard/Psyfighter2-Noromaid-ties-13B")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use diffnamehard/Psyfighter2-Noromaid-ties-13B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "diffnamehard/Psyfighter2-Noromaid-ties-13B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "diffnamehard/Psyfighter2-Noromaid-ties-13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/diffnamehard/Psyfighter2-Noromaid-ties-13B

SGLang

How to use diffnamehard/Psyfighter2-Noromaid-ties-13B 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 "diffnamehard/Psyfighter2-Noromaid-ties-13B" \
    --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": "diffnamehard/Psyfighter2-Noromaid-ties-13B",
		"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 "diffnamehard/Psyfighter2-Noromaid-ties-13B" \
        --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": "diffnamehard/Psyfighter2-Noromaid-ties-13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use diffnamehard/Psyfighter2-Noromaid-ties-13B with Docker Model Runner:
```
docker model run hf.co/diffnamehard/Psyfighter2-Noromaid-ties-13B
```

diffnamehard commited on Jan 14, 2024

Commit

6907ab2

verified ·

1 Parent(s): 1a6f95e

Update README.md

Browse files

Files changed (1) hide show

README.md +11 -1

README.md CHANGED Viewed

@@ -20,4 +20,14 @@ parameters:
   normalize: true
   int8_mask: true
 dtype: float16
-```

   normalize: true
   int8_mask: true
 dtype: float16
+```
+| Metric | Value |
+| --- | --- |
+| Avg. | 59.47 |
+| ARC (25-shot) | 61.86 |
+| HellaSwag (10-shot) | 84.58 |
+| MMLU (5-shot) | 57.04 |
+| TruthfulQA (0-shot) | 50.66 |
+| Winogrande (5-shot) | 75.37 |
+| GSM8K (5-shot) | 27.29 |