Text Generation
Transformers
Safetensors
Arabic
English
gemma
text-generation-inference
4-bit precision
bitsandbytes
Instructions to use m7alek/MathQA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use m7alek/MathQA with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="m7alek/MathQA")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("m7alek/MathQA") model = AutoModelForCausalLM.from_pretrained("m7alek/MathQA") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use m7alek/MathQA with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "m7alek/MathQA" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "m7alek/MathQA", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/m7alek/MathQA
- SGLang
How to use m7alek/MathQA 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 "m7alek/MathQA" \ --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": "m7alek/MathQA", "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 "m7alek/MathQA" \ --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": "m7alek/MathQA", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use m7alek/MathQA with Docker Model Runner:
docker model run hf.co/m7alek/MathQA
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
This directory includes a few sample datasets to get you started.
|
| 2 |
|
| 3 |
* `california_housing_data*.csv` is California housing data from the 1990 US
|
|
@@ -16,4 +35,4 @@ This directory includes a few sample datasets to get you started.
|
|
| 16 |
Statistician. 27 (1): 17-21. JSTOR 2682899.
|
| 17 |
|
| 18 |
and our copy was prepared by the
|
| 19 |
-
[vega_datasets library](https://github.com/altair-viz/vega_datasets/blob/4f67bdaad10f45e3549984e17e1b3088c731503d/vega_datasets/_data/anscombe.json).
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
datasets:
|
| 4 |
+
- m7alek/ninth_file
|
| 5 |
+
- m7alek/external_df
|
| 6 |
+
- m7alek/eighth_file
|
| 7 |
+
language:
|
| 8 |
+
- ar
|
| 9 |
+
- en
|
| 10 |
+
metrics:
|
| 11 |
+
- accuracy
|
| 12 |
+
- bertscore
|
| 13 |
+
base_model:
|
| 14 |
+
- nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
|
| 15 |
+
new_version: google/gemma-7b-aps-it
|
| 16 |
+
library_name: transformers
|
| 17 |
+
tags:
|
| 18 |
+
- text-generation-inference
|
| 19 |
+
---
|
| 20 |
This directory includes a few sample datasets to get you started.
|
| 21 |
|
| 22 |
* `california_housing_data*.csv` is California housing data from the 1990 US
|
|
|
|
| 35 |
Statistician. 27 (1): 17-21. JSTOR 2682899.
|
| 36 |
|
| 37 |
and our copy was prepared by the
|
| 38 |
+
[vega_datasets library](https://github.com/altair-viz/vega_datasets/blob/4f67bdaad10f45e3549984e17e1b3088c731503d/vega_datasets/_data/anscombe.json).
|