Instructions to use IDEA-CCNL/Ziya-Reader-13B-v1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use IDEA-CCNL/Ziya-Reader-13B-v1.0 with Transformers:

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

pipe = pipeline("text-generation", model="IDEA-CCNL/Ziya-Reader-13B-v1.0")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("IDEA-CCNL/Ziya-Reader-13B-v1.0")
model = AutoModelForCausalLM.from_pretrained("IDEA-CCNL/Ziya-Reader-13B-v1.0")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use IDEA-CCNL/Ziya-Reader-13B-v1.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "IDEA-CCNL/Ziya-Reader-13B-v1.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "IDEA-CCNL/Ziya-Reader-13B-v1.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/IDEA-CCNL/Ziya-Reader-13B-v1.0

SGLang

How to use IDEA-CCNL/Ziya-Reader-13B-v1.0 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 "IDEA-CCNL/Ziya-Reader-13B-v1.0" \
    --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": "IDEA-CCNL/Ziya-Reader-13B-v1.0",
		"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 "IDEA-CCNL/Ziya-Reader-13B-v1.0" \
        --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": "IDEA-CCNL/Ziya-Reader-13B-v1.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use IDEA-CCNL/Ziya-Reader-13B-v1.0 with Docker Model Runner:
```
docker model run hf.co/IDEA-CCNL/Ziya-Reader-13B-v1.0
```

GPTQ

#10

by momo4826 - opened Nov 27, 2023

Discussion

momo4826

Nov 27, 2023

Hi, I want to quantize this model with AutoGPTQ, could you provide several hundred samples as calibration data?

pskun

Fengshenbang-LM org Nov 28, 2023

Hi, I want to quantize this model with AutoGPTQ, could you provide several hundred samples as calibration data?

Hello, could you provide an email address so that we can share the data with you?

momo4826

Nov 28, 2023

echoguo4826@gmail.com

Thx!!

momo4826

Dec 5, 2023

I appreciate your willingness to share the data, however, I haven't received it.

Whenever it's convenient for you, could you please check and send it? echoguo4826@gmail.com

Thx!

Justcode

Fengshenbang-LM org Dec 7, 2023

I appreciate your willingness to share the data, however, I haven't received it.

Whenever it's convenient for you, could you please check and send it? echoguo4826@gmail.com

Thx!

Sorry for the late reply. We have two different understandings about calibration data, whether they are used for training or testing the inference results to ensure the performance. So, are you requesting the training data or the inference results from our model? Thanks for clarifying the term.

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