Update README.md
Browse files
README.md
CHANGED
|
@@ -14,12 +14,18 @@ tags:
|
|
| 14 |
|
| 15 |
BRAG-Llama-3.1-8b-v0.1 is part of the BRAG series of SLMs (Small Language Models) specifically trained for RAG (Retrieval-Augmented Generation) tasks. This model is an instruct finetuning of the Llama-3.1-8b-instruct base model. For more details about BRAG series, please refer to our blogpost.
|
| 16 |
|
|
|
|
|
|
|
| 17 |
## Key Features
|
| 18 |
|
| 19 |
- **Model Size**: 8 billion parameters
|
| 20 |
- **Context Length**: Supports up to 128k tokens
|
| 21 |
- **Language**: Trained and evaluated for English, but the base model has multi-lingual capabilities
|
| 22 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
## Performance
|
| 24 |
|
| 25 |
- **ChatRAG-Bench (all)**: 51.70
|
|
|
|
| 14 |
|
| 15 |
BRAG-Llama-3.1-8b-v0.1 is part of the BRAG series of SLMs (Small Language Models) specifically trained for RAG (Retrieval-Augmented Generation) tasks. This model is an instruct finetuning of the Llama-3.1-8b-instruct base model. For more details about BRAG series, please refer to our blogpost.
|
| 16 |
|
| 17 |
+
**Authors**: [Pratik Bhavasar](https://www.linkedin.com/in/bhavsarpratik/), [Ravi Theja](https://www.linkedin.com/in/ravidesetty/)
|
| 18 |
+
|
| 19 |
## Key Features
|
| 20 |
|
| 21 |
- **Model Size**: 8 billion parameters
|
| 22 |
- **Context Length**: Supports up to 128k tokens
|
| 23 |
- **Language**: Trained and evaluated for English, but the base model has multi-lingual capabilities
|
| 24 |
|
| 25 |
+
## Other Resources
|
| 26 |
+
|
| 27 |
+
[BRAG-v0.1 Model Collection](https://huggingface.co/collections/maximalists/brag-v01-66aefc10e3a6c29c496c7476) Blogpost
|
| 28 |
+
|
| 29 |
## Performance
|
| 30 |
|
| 31 |
- **ChatRAG-Bench (all)**: 51.70
|