grimjim
/

kukulemon-7B-8.0bpw_h8_exl2

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

grimjim commited on Apr 25

Commit

2bc260c

•

1 Parent(s): 83056ed

Update README.md

Updated links to quants

Files changed (1) hide show

README.md +4 -3

README.md CHANGED Viewed

@@ -7,6 +7,7 @@ tags:
 - mergekit
 - merge
 license: cc-by-nc-4.0
 ---
 # kukulemon-7B-8.0bpw-h8_exl2
@@ -15,9 +16,9 @@ This is an 8.0bpw h8 exl2 quant of a merger of two similar models with strong re
 I've tested with ChatML prompts with temperature=1.1 and minP=0.03. The model itself supports Alpaca format prompts. The model claims a context length of 32K, but I found it lost coherence after 8K in informal testing. I prefer to stick with 8.0bpw h8 exl2 or Q8_0 GGUF for maximum coherence.
 Alternative downloads:
-[GGUF quants courtesy of Lewdiculous](https://huggingface.co/Lewdiculous/kukulemon-7B-GGUF-IQ-Imatrix)
-[fp16 safetensors](https://huggingface.co/grimjim/kukulemon-7B)
-[Q8_0 GGUF](https://huggingface.co/grimjim/kukulemon-7B-GGUF)
 This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

 - mergekit
 - merge
 license: cc-by-nc-4.0
+pipeline_tag: text-generation
 ---
 # kukulemon-7B-8.0bpw-h8_exl2
 I've tested with ChatML prompts with temperature=1.1 and minP=0.03. The model itself supports Alpaca format prompts. The model claims a context length of 32K, but I found it lost coherence after 8K in informal testing. I prefer to stick with 8.0bpw h8 exl2 or Q8_0 GGUF for maximum coherence.
 Alternative downloads:
+- [iMatrix GGUF quants courtesy of Lewdiculous](https://huggingface.co/Lewdiculous/kukulemon-7B-GGUF-IQ-Imatrix)
+- [fp16 safetensors](https://huggingface.co/grimjim/kukulemon-7B)
+- [GGUF quants](https://huggingface.co/grimjim/kukulemon-7B-GGUF)
 This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).