Update README.md
Browse files
README.md
CHANGED
|
@@ -40,12 +40,13 @@ I'll find the answer for you.
|
|
| 40 |
|
| 41 |
Soon real PoSE to extend Llama's context length to 64k with using my merge method : "reborn"[reborn](https://medium.com/@puffanddmx82/reborn-elevating-model-adaptation-with-merging-for-superior-nlp-performance-f604e8e307b2)
|
| 42 |
|
| 43 |
-
I have found that most of merge's model outside so far do not actually have 64k in their configs. I will improve it in the next merge.
|
| 44 |
|
| 45 |
256k is not possible. My computer is running out of memory.
|
| 46 |
|
| 47 |
If you support me, i will try it on a computer with maximum specifications, also, i would like to conduct great tests by building a network with high-capacity traffic and high-speed 10G speeds for you.
|
| 48 |
|
|
|
|
| 49 |
### Merge Method
|
| 50 |
|
| 51 |
This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [NousResearch/Meta-Llama-3-8B](https://huggingface.co/NousResearch/Meta-Llama-3-8B) as a base.
|
|
|
|
| 40 |
|
| 41 |
Soon real PoSE to extend Llama's context length to 64k with using my merge method : "reborn"[reborn](https://medium.com/@puffanddmx82/reborn-elevating-model-adaptation-with-merging-for-superior-nlp-performance-f604e8e307b2)
|
| 42 |
|
| 43 |
+
I have found that most of merge's model outside so far do not actually have 64k in their configs. I will improve it in the next merge with my reborn. If that doesn't work, I guess I'll have to find another way, right?
|
| 44 |
|
| 45 |
256k is not possible. My computer is running out of memory.
|
| 46 |
|
| 47 |
If you support me, i will try it on a computer with maximum specifications, also, i would like to conduct great tests by building a network with high-capacity traffic and high-speed 10G speeds for you.
|
| 48 |
|
| 49 |
+
|
| 50 |
### Merge Method
|
| 51 |
|
| 52 |
This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [NousResearch/Meta-Llama-3-8B](https://huggingface.co/NousResearch/Meta-Llama-3-8B) as a base.
|