Text Generation
Transformers
Safetensors
English
Italian
quark
causal-lm
small-language-model
gqa
rope
swiglu
bash
code
custom_code
Instructions to use ThingAI/Quark-72M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ThingAI/Quark-72M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ThingAI/Quark-72M", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("ThingAI/Quark-72M", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use ThingAI/Quark-72M with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ThingAI/Quark-72M" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ThingAI/Quark-72M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ThingAI/Quark-72M
- SGLang
How to use ThingAI/Quark-72M 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 "ThingAI/Quark-72M" \ --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": "ThingAI/Quark-72M", "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 "ThingAI/Quark-72M" \ --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": "ThingAI/Quark-72M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ThingAI/Quark-72M with Docker Model Runner:
docker model run hf.co/ThingAI/Quark-72M
Update README.md
Browse files
README.md
CHANGED
|
@@ -2,7 +2,6 @@
|
|
| 2 |
language:
|
| 3 |
- en
|
| 4 |
- it
|
| 5 |
-
license: mit
|
| 6 |
tags:
|
| 7 |
- quark
|
| 8 |
- causal-lm
|
|
@@ -14,6 +13,7 @@ tags:
|
|
| 14 |
- code
|
| 15 |
pipeline_tag: text-generation
|
| 16 |
library_name: transformers
|
|
|
|
| 17 |
---
|
| 18 |
|
| 19 |
# Quark-72M
|
|
@@ -300,8 +300,7 @@ If you use Quark-72M-Instruct in your work, please consider citing the repositor
|
|
| 300 |
|
| 301 |
## License
|
| 302 |
|
| 303 |
-
|
| 304 |
-
|
| 305 |
---
|
| 306 |
|
| 307 |
*Quark-72M is developed and maintained by [ThingAI](https://things-ai.org) as part of an ongoing effort to build self-hostable, fully-inspectable small language models.*
|
|
|
|
| 2 |
language:
|
| 3 |
- en
|
| 4 |
- it
|
|
|
|
| 5 |
tags:
|
| 6 |
- quark
|
| 7 |
- causal-lm
|
|
|
|
| 13 |
- code
|
| 14 |
pipeline_tag: text-generation
|
| 15 |
library_name: transformers
|
| 16 |
+
license: apache-2.0
|
| 17 |
---
|
| 18 |
|
| 19 |
# Quark-72M
|
|
|
|
| 300 |
|
| 301 |
## License
|
| 302 |
|
| 303 |
+
*Apache-2.0*
|
|
|
|
| 304 |
---
|
| 305 |
|
| 306 |
*Quark-72M is developed and maintained by [ThingAI](https://things-ai.org) as part of an ongoing effort to build self-hostable, fully-inspectable small language models.*
|