Instructions to use TheBloke/Project-Baize-v2-13B-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/Project-Baize-v2-13B-GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/Project-Baize-v2-13B-GPTQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/Project-Baize-v2-13B-GPTQ")
model = AutoModelForMultimodalLM.from_pretrained("TheBloke/Project-Baize-v2-13B-GPTQ")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TheBloke/Project-Baize-v2-13B-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBloke/Project-Baize-v2-13B-GPTQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/Project-Baize-v2-13B-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TheBloke/Project-Baize-v2-13B-GPTQ

SGLang

How to use TheBloke/Project-Baize-v2-13B-GPTQ 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 "TheBloke/Project-Baize-v2-13B-GPTQ" \
    --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": "TheBloke/Project-Baize-v2-13B-GPTQ",
		"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 "TheBloke/Project-Baize-v2-13B-GPTQ" \
        --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": "TheBloke/Project-Baize-v2-13B-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TheBloke/Project-Baize-v2-13B-GPTQ with Docker Model Runner:
```
docker model run hf.co/TheBloke/Project-Baize-v2-13B-GPTQ
```

I need to read the markdown table to analysis.

by Ares09 - opened May 25, 2023

Discussion

Ares09

May 25, 2023

I wonder if you have a recommended model for me to use

i want to analysis below this table :

Item	Goal	3month_avg	Mar	Apr	W16	W17	0427	0428	0429	0430	0501	0502	0503
A	0	1.2	2.5	1.6	3.4	20.4	2	1	3	7	2	8	0
B	450	593.1	2	1647	0.1	2.1	457	991	1248	1724	131	898	1019
C	0	214	0	2.1	0	0	0	90	1	87	0	5	645
D	0	0	0	0	0	0	0	0	0	0	0	0	0

I want to find the values in the table through GPT, and I need him to tell me the overall trend. I don't know which model is good for such problems, I would like to ask your opinion

now i use TheBloke/OpenAssistant-SFT-7-Llama-30B-GPTQ to inference The accuracy is a little low

Perhaps I should use what prompt way, the accuracy will be better?

tks

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