grimjim commited on
Commit
e896e20
1 Parent(s): 4d12c24

Add more quants

Browse files
README.md CHANGED
@@ -7,17 +7,18 @@ tags:
7
  - mergekit
8
  - merge
9
  license: cc-by-nc-4.0
 
10
  ---
11
  # kuno-kunoichi-v1-DPO-v2-SLERP-7B-GGUF
12
 
13
- This is a Q8_0 GGUF quant of [kuno-kunoichi-v1-DPO-v2-SLERP-7B](https://huggingface.co/grimjim/kuno-kunoichi-v1-DPO-v2-SLERP-7B).
14
 
15
  kuno-kunoichi-v1-DPO-v2-SLERP-7B is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
16
- I'm hoping that the result is more robust against errors or when merging due to "denseness", as the two models likely implement comparable reasoning at least somewhat differently.
17
 
18
- I've performed some testing with ChatML format prompting using temperature=1.1 and minP=0.03. The model also supports Alpaca format prompts.
19
 
20
- [GGUF-IQ-Imatrix quants helpfully provided by Lewdiculous.](https://huggingface.co/Lewdiculous/kuno-kunoichi-v1-DPO-v2-SLERP-7B-GGUF-IQ-Imatrix)
21
 
22
  ## Merge Details
23
  ### Merge Method
 
7
  - mergekit
8
  - merge
9
  license: cc-by-nc-4.0
10
+ pipeline_tag: text-generation
11
  ---
12
  # kuno-kunoichi-v1-DPO-v2-SLERP-7B-GGUF
13
 
14
+ This repo contains GGUF quants of [kuno-kunoichi-v1-DPO-v2-SLERP-7B](https://huggingface.co/grimjim/kuno-kunoichi-v1-DPO-v2-SLERP-7B).
15
 
16
  kuno-kunoichi-v1-DPO-v2-SLERP-7B is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
17
+ The expectation is that the result is more robust against errors or when merging due to "denseness", as the two models likely implement comparable reasoning at least somewhat differently.
18
 
19
+ Tested lightly with ChatML instruct format prompting using temperature=1.1 and minP=0.03. The model natively supports Alpaca format prompts.
20
 
21
+ - [GGUF-IQ-Imatrix quants helpfully provided by Lewdiculous.](https://huggingface.co/Lewdiculous/kuno-kunoichi-v1-DPO-v2-SLERP-7B-GGUF-IQ-Imatrix)
22
 
23
  ## Merge Details
24
  ### Merge Method
kuno-kunoichi-v1-DPO-v2-SLERP-7B.Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c078fe9f13144262977eb171e10ea7fe7e76a7e16958b4f4966724848dc9302a
3
+ size 4368439040
kuno-kunoichi-v1-DPO-v2-SLERP-7B.Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e3f5182fc815f7f7ac7a23af7d15e807de4564a2ad861e0cc3bbad9621821f0
3
+ size 5131409152
kuno-kunoichi-v1-DPO-v2-SLERP-7B.Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c111adef3b639c923179f9a8f981a4411b90a8fd42573fc190bae55ebc1e5d0
3
+ size 5942064896
kuno-kunoichi-v1-DPO-v2-SLERP-7B.Q8_0.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a39bb5da986ec3c5566fa43fe00323a408ebbcb3c4e82db4acd92dfea00e048c
3
  size 7695857376
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:865e4c2d55c8c293b6c718218c90ca2748ccb16174b445c585959990afa492d7
3
  size 7695857376