Instructions to use Peeepy/Airoboros-13b-SuperHOT-8k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Peeepy/Airoboros-13b-SuperHOT-8k with Transformers:

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

pipe = pipeline("text-generation", model="Peeepy/Airoboros-13b-SuperHOT-8k")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Peeepy/Airoboros-13b-SuperHOT-8k")
model = AutoModelForCausalLM.from_pretrained("Peeepy/Airoboros-13b-SuperHOT-8k")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Peeepy/Airoboros-13b-SuperHOT-8k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Peeepy/Airoboros-13b-SuperHOT-8k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Peeepy/Airoboros-13b-SuperHOT-8k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Peeepy/Airoboros-13b-SuperHOT-8k

SGLang

How to use Peeepy/Airoboros-13b-SuperHOT-8k 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 "Peeepy/Airoboros-13b-SuperHOT-8k" \
    --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": "Peeepy/Airoboros-13b-SuperHOT-8k",
		"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 "Peeepy/Airoboros-13b-SuperHOT-8k" \
        --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": "Peeepy/Airoboros-13b-SuperHOT-8k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Peeepy/Airoboros-13b-SuperHOT-8k with Docker Model Runner:
```
docker model run hf.co/Peeepy/Airoboros-13b-SuperHOT-8k
```

Peeepy commited on Jun 23, 2023

Commit

b68311b

1 Parent(s): 284ecd1

Update README.md

Browse files

Files changed (1) hide show

README.md +9 -1

README.md CHANGED Viewed

@@ -2,4 +2,12 @@
 The code to merge these can be found [here](https://files.catbox.moe/mg5v4g.py). Change information as needed.
-NOTE: This requires a monkey patch to work. FlashVenom has, along with kindly quantising this model to 4bit, added the monkeypatch file to their repo. You can access this [here](https://huggingface.co/flashvenom/Airoboros-13B-SuperHOT-8K-4bit-GPTQ).

 The code to merge these can be found [here](https://files.catbox.moe/mg5v4g.py). Change information as needed.
+NOTE: This requires a monkey patch to work. FlashVenom has, along with kindly quantising this model to 4bit, added the monkeypatch file to their repo. You can access this [here](https://huggingface.co/flashvenom/Airoboros-13B-SuperHOT-8K-4bit-GPTQ).
+FROM THE ORIGINAL LORA MODEL CARD:
+This is a second prototype of SuperHOT, this time with 4K context and no RLHF. In my testing, it can go all the way to 6K without breaking down and I made the change with intention to reach 8K, so I'll assume it will go to 8K although I only trained on 4K sequences.
+In order to use the 8K context, you will need to apply the monkeypatch I have added in this repo -- without it, it will not work. The patch is very simple, and you can make the changes yourself:
+    Increase the max_position_embeddings to 8192 to stretch the sinusoidal
+    Stretch the frequency steps by a scale of 0.25