Upload folder using huggingface_hub
Browse files
README.md
CHANGED
|
@@ -13,8 +13,6 @@ We extend the context length of Llama-3-8B-Instruct to 80K using QLoRA and 3.5K
|
|
| 13 |
|
| 14 |
**NOTE**: This repo contains the quantized model of [namespace-Pt/Llama-3-8B-Instruct-80K-QLoRA-Merged](https://huggingface.co/namespace-Pt/Llama-3-8B-Instruct-80K-QLoRA-Merged). The quantization is conducted with [llama.cpp](https://github.com/ggerganov/llama.cpp) (Q4_K_M and Q8_0).
|
| 15 |
|
| 16 |
-
# Evaluation
|
| 17 |
-
|
| 18 |
All the following evaluation results are based on the [UNQUANTIZED MODEL](https://huggingface.co/namespace-Pt/Llama-3-8B-Instruct-80K-QLoRA-Merged). They can be reproduced following instructions [here](https://github.com/FlagOpen/FlagEmbedding/tree/master/Long_LLM/longllm_qlora).
|
| 19 |
|
| 20 |
**NOTE**: After quantization, you may observe quality degradation.
|
|
|
|
| 13 |
|
| 14 |
**NOTE**: This repo contains the quantized model of [namespace-Pt/Llama-3-8B-Instruct-80K-QLoRA-Merged](https://huggingface.co/namespace-Pt/Llama-3-8B-Instruct-80K-QLoRA-Merged). The quantization is conducted with [llama.cpp](https://github.com/ggerganov/llama.cpp) (Q4_K_M and Q8_0).
|
| 15 |
|
|
|
|
|
|
|
| 16 |
All the following evaluation results are based on the [UNQUANTIZED MODEL](https://huggingface.co/namespace-Pt/Llama-3-8B-Instruct-80K-QLoRA-Merged). They can be reproduced following instructions [here](https://github.com/FlagOpen/FlagEmbedding/tree/master/Long_LLM/longllm_qlora).
|
| 17 |
|
| 18 |
**NOTE**: After quantization, you may observe quality degradation.
|