Improve model card: Add pipeline_tag, library_name, and resource links
#3
by
nielsr HF Staff - opened
README.md
CHANGED
|
@@ -1,27 +1,29 @@
|
|
| 1 |
---
|
| 2 |
base_model: unsloth/Meta-Llama-3.1-8B
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
tags:
|
| 4 |
- text-generation-inference
|
| 5 |
-
- transformers
|
| 6 |
- unsloth
|
| 7 |
- llama
|
| 8 |
- trl
|
| 9 |
-
license: apache-2.0
|
| 10 |
-
language:
|
| 11 |
-
- en
|
| 12 |
-
- ur
|
| 13 |
---
|
| 14 |
|
| 15 |
-
|
| 16 |
# Model Card for Alif 1.0 8B Instruct
|
| 17 |
|
| 18 |
-
|
| 19 |
|
| 20 |
-
|
| 21 |
-
|
| 22 |
-
-
|
| 23 |
-
-
|
| 24 |
-
-
|
|
|
|
|
|
|
| 25 |
|
| 26 |
This model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
| 27 |
|
|
@@ -103,5 +105,4 @@ We evaluated Alif 1.0 8B Instruct against Gemma 2 9B, Llama 3.1 8B, Mistral Nemo
|
|
| 103 |
|
| 104 |
### Model Card Contact
|
| 105 |
|
| 106 |
-
For errors or additional questions about details in this model card, contact: contact@traversaal.ai
|
| 107 |
-
|
|
|
|
| 1 |
---
|
| 2 |
base_model: unsloth/Meta-Llama-3.1-8B
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
- ur
|
| 6 |
+
license: apache-2.0
|
| 7 |
+
pipeline_tag: text-generation
|
| 8 |
+
library_name: transformers
|
| 9 |
tags:
|
| 10 |
- text-generation-inference
|
|
|
|
| 11 |
- unsloth
|
| 12 |
- llama
|
| 13 |
- trl
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
---
|
| 15 |
|
|
|
|
| 16 |
# Model Card for Alif 1.0 8B Instruct
|
| 17 |
|
| 18 |
+
[[Paper](https://huggingface.co/papers/2510.09051)] [[Code](https://github.com/traversaal-ai/alif-urdu-llm)] [[Datasets](https://huggingface.co/datasets/large-traversaal/urdu-instruct)] [[Blog](https://blog.traversaal.ai/announcing-alif-1-0-our-first-urdu-llm-outperforming-other-open-source-llms/)] [[Live Demo](https://huggingface.co/spaces/large-traversaal/Alif-1.0-8B-Instruct)]
|
| 19 |
|
| 20 |
+
**Alif 1.0 8B Instruct** is an open-source model with highly advanced multilingual reasoning capabilities. It utilizes human refined multilingual synthetic data paired with reasoning to enhance cultural nuance and reasoning capabilities in english and urdu languages. This model was presented in the paper [Alif: Advancing Urdu Large Language Models via Multilingual Synthetic Data Distillation](https://huggingface.co/papers/2510.09051).
|
| 21 |
+
|
| 22 |
+
- **Developed by:** large-traversaal
|
| 23 |
+
- **License:** apache-2.0
|
| 24 |
+
- **Base model:** unsloth/Meta-Llama-3.1-8B
|
| 25 |
+
- **Model:** Alif-1.0-8B-Instruct
|
| 26 |
+
- **Model Size:** 8 billion parameters
|
| 27 |
|
| 28 |
This model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
| 29 |
|
|
|
|
| 105 |
|
| 106 |
### Model Card Contact
|
| 107 |
|
| 108 |
+
For errors or additional questions about details in this model card, contact: contact@traversaal.ai
|
|
|