Instructions to use nectec/Pathumma-llm-audio-1.0.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nectec/Pathumma-llm-audio-1.0.0 with Transformers:

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

pipe = pipeline("text-generation", model="nectec/Pathumma-llm-audio-1.0.0", trust_remote_code=True)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("nectec/Pathumma-llm-audio-1.0.0", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nectec/Pathumma-llm-audio-1.0.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nectec/Pathumma-llm-audio-1.0.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nectec/Pathumma-llm-audio-1.0.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/nectec/Pathumma-llm-audio-1.0.0

SGLang

How to use nectec/Pathumma-llm-audio-1.0.0 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 "nectec/Pathumma-llm-audio-1.0.0" \
    --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": "nectec/Pathumma-llm-audio-1.0.0",
		"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 "nectec/Pathumma-llm-audio-1.0.0" \
        --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": "nectec/Pathumma-llm-audio-1.0.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use nectec/Pathumma-llm-audio-1.0.0 with Docker Model Runner:
```
docker model run hf.co/nectec/Pathumma-llm-audio-1.0.0
```

Update README.md

by kwanchiva - opened Oct 24, 2024

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-1

Files changed (1) hide show

README.md +6 -1

README.md CHANGED Viewed

@@ -68,7 +68,12 @@ Additional details are required.
 At present, our model remains in the experimental research phase and is not yet fully suitable for practical applications as an assistant. Future work will focus on upgrading the language model to a newer version ([OpenThaiLLM-DoodNiLT-V1.0.0-Beta-7B](https://huggingface.co/nectec/OpenThaiLLM-DoodNiLT-V1.0.0-Beta-7B)), and curating more refined and robust datasets to improve performance. Additionally, we aim to address and prioritize the safety and reliability of the model's outputs.
 ## Citation
-Additional details are required.
 ## Acknowledgements
 We are grateful to ThaiSC, also known as NSTDA Supercomputer Centre, for providing the LANTA that was utilised for model training and finetuning.  Additionally, we would like to express our gratitude to the SALMONN team for making their code publicly available, and to Typhoon Audio at SCB 10X for making available the huggingface project, source code, and technical paper, which served as a valuable guide for us. Many other open-source projects have contributed valuable information, code, data, and model weights; we are grateful to them all.

 At present, our model remains in the experimental research phase and is not yet fully suitable for practical applications as an assistant. Future work will focus on upgrading the language model to a newer version ([OpenThaiLLM-DoodNiLT-V1.0.0-Beta-7B](https://huggingface.co/nectec/OpenThaiLLM-DoodNiLT-V1.0.0-Beta-7B)), and curating more refined and robust datasets to improve performance. Additionally, we aim to address and prioritize the safety and reliability of the model's outputs.
 ## Citation
+@misc{tipkasorn2024pathumma,
+  Note = {\href{https://huggingface.co/nectec/Pathumma-llm-audio-1.0.0}{Pathumma-Audio}},
+  author = {Pattara Tipkasorn and Wayupuk Sommuang and Oatsada Chatthong and Kwanchiva Thangthai},
+  publisher = { Hugging Face },
+  year = {2024},
+}
 ## Acknowledgements
 We are grateful to ThaiSC, also known as NSTDA Supercomputer Centre, for providing the LANTA that was utilised for model training and finetuning.  Additionally, we would like to express our gratitude to the SALMONN team for making their code publicly available, and to Typhoon Audio at SCB 10X for making available the huggingface project, source code, and technical paper, which served as a valuable guide for us. Many other open-source projects have contributed valuable information, code, data, and model weights; we are grateful to them all.