Update README.md
Browse files
README.md
CHANGED
|
@@ -32,6 +32,8 @@ These are only LoRA adapters of [FastLlama-3.2-1B-Instruct](https://huggingface.
|
|
| 32 |
|
| 33 |
You can use ChatML & Alpaca format.
|
| 34 |
|
|
|
|
|
|
|
| 35 |
**Overview:**
|
| 36 |
|
| 37 |
FastLlama is a highly optimized version of the Llama-3.2-1B-Instruct model. Designed for superior performance in constrained environments, it combines speed, compactness, and high accuracy. This version has been fine-tuned using the MetaMathQA-50k section of the HuggingFaceTB/smoltalk dataset to enhance its mathematical reasoning and problem-solving abilities.
|
|
|
|
| 32 |
|
| 33 |
You can use ChatML & Alpaca format.
|
| 34 |
|
| 35 |
+
You can chat with the model via this [space](https://huggingface.co/spaces/suayptalha/Chat-with-FastLlama).
|
| 36 |
+
|
| 37 |
**Overview:**
|
| 38 |
|
| 39 |
FastLlama is a highly optimized version of the Llama-3.2-1B-Instruct model. Designed for superior performance in constrained environments, it combines speed, compactness, and high accuracy. This version has been fine-tuned using the MetaMathQA-50k section of the HuggingFaceTB/smoltalk dataset to enhance its mathematical reasoning and problem-solving abilities.
|