Update README.md
Browse filesUpdated with links to working GGUFs.
README.md
CHANGED
|
@@ -14,15 +14,16 @@ pipeline_tag: text-generation
|
|
| 14 |
---
|
| 15 |
# Llama-3-Luminurse-v0.1-OAS-8B
|
| 16 |
|
|
|
|
|
|
|
| 17 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
| 18 |
|
| 19 |
Given that a biomedical model was merged with Lumimaid, the obvious resulting name was Luminurse.
|
| 20 |
|
| 21 |
-
WARNING: There appears to be something broken with the current GGUFs despite quantization having completed without errors. This repo will be updated once working GGUFs are generated.
|
| 22 |
-
|
| 23 |
- [Full weights](https://huggingface.co/grimjim/Llama-3-Luminurse-v0.1-OAS-8B)
|
| 24 |
-
- [GGUF quants](https://huggingface.co/
|
| 25 |
-
|
|
|
|
| 26 |
Built with Meta Llama 3.
|
| 27 |
|
| 28 |
## Merge Details
|
|
|
|
| 14 |
---
|
| 15 |
# Llama-3-Luminurse-v0.1-OAS-8B
|
| 16 |
|
| 17 |
+
*WARNING:* There appears to be something broken with the current GGUFs despite quantization having completed without errors. This repo will eventually be updated once working GGUFs are generated. In the meantime, check out the GGUFs helpfully provided via links below.
|
| 18 |
+
|
| 19 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
| 20 |
|
| 21 |
Given that a biomedical model was merged with Lumimaid, the obvious resulting name was Luminurse.
|
| 22 |
|
|
|
|
|
|
|
| 23 |
- [Full weights](https://huggingface.co/grimjim/Llama-3-Luminurse-v0.1-OAS-8B)
|
| 24 |
+
- [GGUF quants c/o mradermacher](https://huggingface.co/mradermacher/Llama-3-Luminurse-v0.1-OAS-8B-GGUF)
|
| 25 |
+
- [iMatrix GGUF quants c/o mradermacher](https://huggingface.co/mradermacher/Llama-3-Luminurse-v0.1-OAS-8B-i1-GGUF)
|
| 26 |
+
-
|
| 27 |
Built with Meta Llama 3.
|
| 28 |
|
| 29 |
## Merge Details
|