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
```

bhenrym14 commited on Jul 25, 2023

Commit

4a04f5a

1 Parent(s): 89e2fd2

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -3

README.md CHANGED Viewed

@@ -50,11 +50,10 @@ Here I explore whether training on long sequences that have clear conceptual dep
 | 8192 | **4.90** | 5.32 | Not Tested | 57.1 |
 | 12000 | **4.82** | 56.1 | Not Tested | Not Tested |
-- This model is very competitive with the Llama-1 33b extended context variants.
 - Not presented here, but this model outperforms the base llama-2-13b on MMLU-fs with a score of 54.9. While perhaps an insignificant difference, the fact there isn't a clear performance regression despite the context extension is notable.
 - Perplexity continues to decline to 12000 tokens, the longest context length I tested due to VRAM constraints.
-- Feedback regarding real-world performance is appreciated. I don't know if the first dolphin training phase really contributed much; many relevant modeling components changed here, so it's difficult to make any specific attributions. The base model improvement may very well be the most dominant change.
 ## Prompting:

 | 8192 | **4.90** | 5.32 | Not Tested | 57.1 |
 | 12000 | **4.82** | 56.1 | Not Tested | Not Tested |
+- This model is very competitive with the Llama-1 33b extended context variants. In particular, at 512 tokens it has lower perplexity. This is probably an improvement imparted (in part) by the NTK by parts scaling method.
 - Not presented here, but this model outperforms the base llama-2-13b on MMLU-fs with a score of 54.9. While perhaps an insignificant difference, the fact there isn't a clear performance regression despite the context extension is notable.
 - Perplexity continues to decline to 12000 tokens, the longest context length I tested due to VRAM constraints.
+- Feedback regarding real-world performance is appreciated. I don't know if the first dolphin training phase really contributed much beyond what pile did for the 33b-lxctx model; many relevant modeling components changed here, so it's difficult to make any specific attributions. The base model improvement may very well be the most dominant change.
 ## Prompting: