Instructions to use ethzanalytics/gpt-j-8bit-daily_dialogues with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ethzanalytics/gpt-j-8bit-daily_dialogues with Transformers:

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

pipe = pipeline("text-generation", model="ethzanalytics/gpt-j-8bit-daily_dialogues")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ethzanalytics/gpt-j-8bit-daily_dialogues")
model = AutoModelForCausalLM.from_pretrained("ethzanalytics/gpt-j-8bit-daily_dialogues", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ethzanalytics/gpt-j-8bit-daily_dialogues with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ethzanalytics/gpt-j-8bit-daily_dialogues

SGLang

How to use ethzanalytics/gpt-j-8bit-daily_dialogues 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 "ethzanalytics/gpt-j-8bit-daily_dialogues" \
    --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": "ethzanalytics/gpt-j-8bit-daily_dialogues",
		"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 "ethzanalytics/gpt-j-8bit-daily_dialogues" \
        --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": "ethzanalytics/gpt-j-8bit-daily_dialogues",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ethzanalytics/gpt-j-8bit-daily_dialogues with Docker Model Runner:
```
docker model run hf.co/ethzanalytics/gpt-j-8bit-daily_dialogues
```

pszemraj commited on Nov 27, 2022

Commit

e323036

1 Parent(s): 1721ded

Update README.md

Browse files

Files changed (1) hide show

README.md +16 -6

README.md CHANGED Viewed

@@ -14,18 +14,28 @@ inference: False
 license: apache-2.0
 ---
-# ethzanalytics/gpt-j-8bit-daily_dialogues_1E
-This is a version of `hivemind/gpt-j-6B-8bit` fine-tuned on the daily-dialogues dataset for an epoch. it can be used as a chatbot.
-_NOTE: this needs to be loaded via the special patching technique outlined in the hivemind model card (as with all 8bit models)_
-TODO: rest of README
----
-[original demo link](https://colab.research.google.com/gist/pszemraj/76c0a80c9eacfb2c31e21c4cceb344a0/ai-msgbot-gpt-j-6b-8bit-chatbot-demo.ipynb)

 license: apache-2.0
 ---
+# ethzanalytics/gpt-j-8bit-daily_dialogues
+<a href="https://colab.research.google.com/gist/pszemraj/e49c60aafe04acc52fcfdd1baefe12e4/-ai-msgbot-gpt-j-6b-8bit-with-hub.ipynb">
+  <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
+</a>
+This version of `hivemind/gpt-j-6B-8bit` is fine-tuned on a parsed version of the [daily dialogues](https://huggingface.co/datasets/daily_dialog) dataset for an epoch. It can be used as a chatbot.
+It is designed to be used with [ai-msgbot](https://github.com/pszemraj/ai-msgbot) to take advantage of prompt engineering in fine-tuning.
+## Usage
+_**NOTE: this needs to be loaded via the special patching technique** outlined in the hivemind model card (as with all 8bit models)_
+Examples of how to load the model correctly are already in place in the notebook linked above. A `.py` of said notebook was uploaded to the repo for reference - [link here](https://huggingface.co/ethzanalytics/gpt-j-8bit-daily_dialogues/blob/main/_ai_msgbot_gpt_j_6b_8bit_with_hub.py)
+## Training
+For details, please see [this wandb report](https://wandb.ai/pszemraj/conversational-6B-train-vanilla/reports/Training-6B-GPT-J-8bit-for-Dialogue--VmlldzoyNTg3MzE0) for both the daily-dialogues version and the WoW version.
+---