Text Generation
Transformers
Safetensors
Yiddish
llama
yiddish
continued-pretraining
text-generation-inference
Instructions to use Yiddish-NLP/MameLoshnLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Yiddish-NLP/MameLoshnLM with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Yiddish-NLP/MameLoshnLM")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Yiddish-NLP/MameLoshnLM") model = AutoModelForCausalLM.from_pretrained("Yiddish-NLP/MameLoshnLM", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Yiddish-NLP/MameLoshnLM with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Yiddish-NLP/MameLoshnLM" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Yiddish-NLP/MameLoshnLM", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Yiddish-NLP/MameLoshnLM
- SGLang
How to use Yiddish-NLP/MameLoshnLM 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 "Yiddish-NLP/MameLoshnLM" \ --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": "Yiddish-NLP/MameLoshnLM", "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 "Yiddish-NLP/MameLoshnLM" \ --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": "Yiddish-NLP/MameLoshnLM", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Yiddish-NLP/MameLoshnLM with Docker Model Runner:
docker model run hf.co/Yiddish-NLP/MameLoshnLM
Add paper and code links
#1
by nielsr HF Staff - opened
README.md
CHANGED
|
@@ -1,18 +1,21 @@
|
|
| 1 |
---
|
|
|
|
| 2 |
language:
|
| 3 |
- yi
|
|
|
|
| 4 |
license: cc-by-nc-4.0
|
| 5 |
license_link: https://creativecommons.org/licenses/by-nc/4.0/
|
| 6 |
-
base_model: meta-llama/Llama-3.1-8B
|
| 7 |
pipeline_tag: text-generation
|
| 8 |
tags:
|
| 9 |
- yiddish
|
| 10 |
- continued-pretraining
|
| 11 |
-
library_name: transformers
|
| 12 |
---
|
| 13 |
|
| 14 |
# MameLoshnLM
|
| 15 |
|
|
|
|
|
|
|
|
|
|
| 16 |
MameLoshnLM is an 8B-parameter language model for Yiddish, built by continued pretraining of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on a curated native-Yiddish corpus combining contemporary web-native sources with an extensive collection of literary materials. It is, to our knowledge, the first large generative language model adapted specifically to Yiddish, and it accompanies our paper (reference below).
|
| 17 |
|
| 18 |
## Model details
|
|
@@ -79,4 +82,4 @@ The paper introducing MameLoshnLM has been accepted to COLM 2026. The full citat
|
|
| 79 |
|
| 80 |
## Acknowledgments
|
| 81 |
|
| 82 |
-
We are deeply grateful to the [Yiddish Book Center](https://www.yiddishbookcenter.org/), which granted us permission to train on the Yiddish Book Center's Digital Yiddish Library. This model and the accompanying research would not have been possible without their support and their decades of work digitizing and preserving Yiddish literature.
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: meta-llama/Llama-3.1-8B
|
| 3 |
language:
|
| 4 |
- yi
|
| 5 |
+
library_name: transformers
|
| 6 |
license: cc-by-nc-4.0
|
| 7 |
license_link: https://creativecommons.org/licenses/by-nc/4.0/
|
|
|
|
| 8 |
pipeline_tag: text-generation
|
| 9 |
tags:
|
| 10 |
- yiddish
|
| 11 |
- continued-pretraining
|
|
|
|
| 12 |
---
|
| 13 |
|
| 14 |
# MameLoshnLM
|
| 15 |
|
| 16 |
+
**Paper:** [MameLoshnLM: Yiddish Language Model and Evaluation Benchmark](https://huggingface.co/papers/2608.05850)
|
| 17 |
+
**Code:** [github.com/katzurik/MameLoshnLM](https://github.com/katzurik/MameLoshnLM)
|
| 18 |
+
|
| 19 |
MameLoshnLM is an 8B-parameter language model for Yiddish, built by continued pretraining of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on a curated native-Yiddish corpus combining contemporary web-native sources with an extensive collection of literary materials. It is, to our knowledge, the first large generative language model adapted specifically to Yiddish, and it accompanies our paper (reference below).
|
| 20 |
|
| 21 |
## Model details
|
|
|
|
| 82 |
|
| 83 |
## Acknowledgments
|
| 84 |
|
| 85 |
+
We are deeply grateful to the [Yiddish Book Center](https://www.yiddishbookcenter.org/), which granted us permission to train on the Yiddish Book Center's Digital Yiddish Library. This model and the accompanying research would not have been possible without their support and their decades of work digitizing and preserving Yiddish literature.
|