Update README.md
Browse files
README.md
CHANGED
|
@@ -26,9 +26,6 @@ This instruction model was built via parameter-efficient QLoRA finetuning of [ll
|
|
| 26 |
|
| 27 |
* Model license: Llama 2 Community License Agreement
|
| 28 |
* Basic usage: [notebook](assets/basic_inference_llama_2_dolphin.ipynb)
|
| 29 |
-
* Finetuning code: [script](https://github.com/daniel-furman/sft-demos/blob/main/src/sft/one_gpu/llama-2/dolphin/sft-Llama-2-70B-Instruct-v0.1-peft.py)
|
| 30 |
-
* Loss curves: [plot](https://huggingface.co/dfurman/Llama-2-70B-Instruct-v0.1-peft#finetuning-description)
|
| 31 |
-
* Runtime stats: [table](https://huggingface.co/dfurman/Llama-2-70B-Instruct-v0.1-peft#runtime-tests)
|
| 32 |
|
| 33 |
## Open LLM Leaderboard Evaluation Results
|
| 34 |
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_dfurman__llama-2-70b-dolphin-peft)
|
|
|
|
| 26 |
|
| 27 |
* Model license: Llama 2 Community License Agreement
|
| 28 |
* Basic usage: [notebook](assets/basic_inference_llama_2_dolphin.ipynb)
|
|
|
|
|
|
|
|
|
|
| 29 |
|
| 30 |
## Open LLM Leaderboard Evaluation Results
|
| 31 |
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_dfurman__llama-2-70b-dolphin-peft)
|