Instructions to use bhenrym14/airophin-13b-pntk-16k-fp16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bhenrym14/airophin-13b-pntk-16k-fp16 with Transformers:

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

pipe = pipeline("text-generation", model="bhenrym14/airophin-13b-pntk-16k-fp16")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bhenrym14/airophin-13b-pntk-16k-fp16")
model = AutoModelForCausalLM.from_pretrained("bhenrym14/airophin-13b-pntk-16k-fp16", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bhenrym14/airophin-13b-pntk-16k-fp16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bhenrym14/airophin-13b-pntk-16k-fp16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bhenrym14/airophin-13b-pntk-16k-fp16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/bhenrym14/airophin-13b-pntk-16k-fp16

SGLang

How to use bhenrym14/airophin-13b-pntk-16k-fp16 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 "bhenrym14/airophin-13b-pntk-16k-fp16" \
    --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": "bhenrym14/airophin-13b-pntk-16k-fp16",
		"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 "bhenrym14/airophin-13b-pntk-16k-fp16" \
        --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": "bhenrym14/airophin-13b-pntk-16k-fp16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use bhenrym14/airophin-13b-pntk-16k-fp16 with Docker Model Runner:
```
docker model run hf.co/bhenrym14/airophin-13b-pntk-16k-fp16
```

Any chance for a ggml version to have a better perplexity?

by Nexesenex - opened Aug 14, 2023

Discussion

Nexesenex

Aug 14, 2023

I'm using this model (its GPTQ version) in competition with Airoboros lxctx 16384 PI (GGML version).
I enjoy your work, Brandon, and it deserves more.. attention!
Any chance of some GGML versions (QK_4_M or Q5_S/M) to surpass the GPTQ quality (which is more in the QK_3 range usually) and do the most with your model?
Thanks you in any case.

bhenrym14

Owner Aug 14, 2023

I'd be happy to! My only concern is with how the PNTK embeddings would work with GGML. I'm just not very familiar with it. Any idea how this might work?

Nexesenex

Aug 15, 2023

•

edited Aug 15, 2023

I'm not an expert, and the NTK evolving terminology and lack of reference documentation "for end users" confuse me a bit.
But here's a llama.cpp PR thread (and its appendixes at its bottom) which might be of interest for you to get an idea if PNTK is already implemented (whatever the name used for it, and this, even in unmerged PRs).

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment