Instructions to use bhenrym14/platypus-yi-34b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bhenrym14/platypus-yi-34b with Transformers:

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

pipe = pipeline("text-generation", model="bhenrym14/platypus-yi-34b")

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

tokenizer = AutoTokenizer.from_pretrained("bhenrym14/platypus-yi-34b")
model = AutoModelForCausalLM.from_pretrained("bhenrym14/platypus-yi-34b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bhenrym14/platypus-yi-34b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bhenrym14/platypus-yi-34b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bhenrym14/platypus-yi-34b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/bhenrym14/platypus-yi-34b

SGLang

How to use bhenrym14/platypus-yi-34b 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/platypus-yi-34b" \
    --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/platypus-yi-34b",
		"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/platypus-yi-34b" \
        --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/platypus-yi-34b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use bhenrym14/platypus-yi-34b with Docker Model Runner:
```
docker model run hf.co/bhenrym14/platypus-yi-34b
```

Fine-tuning framework?

by Yhyu13 - opened Nov 23, 2023

Discussion

Yhyu13

Nov 23, 2023

Hi,

Which framework that you for fine-tuning? I was trying to adapt ToolBench (https://github.com/OpenBMB/ToolBench), a function calling dataset to the Yi series,

But the source code works for LLaMA2 but not for Yi seris, the train loss was 0.0 and eval loss being NaN.

I am looking for a working/stable QLoRA framework for open source LLMs where users simply need to bring their models and curated datasets.

Thanks!

bhenrym14

Owner Nov 23, 2023

I use an a version of the original qlora training script that I've adapted over time; it's rather hacked together at this point, but it works. This model, however, uses Yi-34b as adapted to the LLama2 architecture (https://huggingface.co/chargoddard/Yi-34B-Llama), so in principle you should be able to get ToolBench to work if it does for other llama2 models (though I have no experience with ToolBench). Note that I use the model from the llama-tokenizer branch of that model repo to also remove any dependency on the Yi tokenizer definition. I haven't tried training native Yi with the custom model and/or tokenizer definitions.

bhenrym14 changed discussion status to closed Dec 1, 2023

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