Hugging Face's logo

mradermacher
/
Miqu-70B-Alpaca-DPO-i1-GGUF

Transformers
GGUF
English
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
eda9bf6
•
1 Parent(s): c037e32

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -3
README.md CHANGED
@@ -24,7 +24,7 @@ more details, including on how to concatenate multi-part files.
24
  | Link | Type | Size/GB | Notes |
25
  |:-----|:-----|--------:|:------|
26
  | [GGUF](https://huggingface.co/mradermacher/Miqu-70B-Alpaca-DPO-i1-GGUF/resolve/main/Miqu-70B-Alpaca-DPO.i1-IQ1_S.gguf) | i1-IQ1_S | 15.0 | for the desperate |
27
- | [GGUF](https://huggingface.co/mradermacher/Miqu-70B-Alpaca-DPO-i1-GGUF/resolve/main/Miqu-70B-Alpaca-DPO.i1-IQ1_M.gguf) | i1-IQ1_M | 16.0 | for the desperate |
28
  | [GGUF](https://huggingface.co/mradermacher/Miqu-70B-Alpaca-DPO-i1-GGUF/resolve/main/Miqu-70B-Alpaca-DPO.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 18.7 | |
29
  | [GGUF](https://huggingface.co/mradermacher/Miqu-70B-Alpaca-DPO-i1-GGUF/resolve/main/Miqu-70B-Alpaca-DPO.i1-IQ2_XS.gguf) | i1-IQ2_XS | 20.8 | |
30
  | [GGUF](https://huggingface.co/mradermacher/Miqu-70B-Alpaca-DPO-i1-GGUF/resolve/main/Miqu-70B-Alpaca-DPO.i1-IQ2_S.gguf) | i1-IQ2_S | 21.8 | |
@@ -38,7 +38,7 @@ more details, including on how to concatenate multi-part files.
38
  | [GGUF](https://huggingface.co/mradermacher/Miqu-70B-Alpaca-DPO-i1-GGUF/resolve/main/Miqu-70B-Alpaca-DPO.i1-Q3_K_M.gguf) | i1-Q3_K_M | 33.7 | IQ3_S probably better |
39
  | [GGUF](https://huggingface.co/mradermacher/Miqu-70B-Alpaca-DPO-i1-GGUF/resolve/main/Miqu-70B-Alpaca-DPO.i1-Q3_K_L.gguf) | i1-Q3_K_L | 36.6 | IQ3_M probably better |
40
  | [GGUF](https://huggingface.co/mradermacher/Miqu-70B-Alpaca-DPO-i1-GGUF/resolve/main/Miqu-70B-Alpaca-DPO.i1-IQ4_XS.gguf) | i1-IQ4_XS | 37.2 | |
41
- | [GGUF](https://huggingface.co/mradermacher/Miqu-70B-Alpaca-DPO-i1-GGUF/resolve/main/Miqu-70B-Alpaca-DPO.i1-IQ4_NL.gguf) | i1-IQ4_NL | 39.4 | slightly worse than Q4_K_S |
42
  | [GGUF](https://huggingface.co/mradermacher/Miqu-70B-Alpaca-DPO-i1-GGUF/resolve/main/Miqu-70B-Alpaca-DPO.i1-Q4_0.gguf) | i1-Q4_0 | 39.4 | fast, low quality |
43
  | [GGUF](https://huggingface.co/mradermacher/Miqu-70B-Alpaca-DPO-i1-GGUF/resolve/main/Miqu-70B-Alpaca-DPO.i1-Q4_K_S.gguf) | i1-Q4_K_S | 39.7 | optimal size/speed/quality |
44
  | [GGUF](https://huggingface.co/mradermacher/Miqu-70B-Alpaca-DPO-i1-GGUF/resolve/main/Miqu-70B-Alpaca-DPO.i1-Q4_K_M.gguf) | i1-Q4_K_M | 41.8 | fast, recommended |
@@ -46,7 +46,6 @@ more details, including on how to concatenate multi-part files.
46
  | [GGUF](https://huggingface.co/mradermacher/Miqu-70B-Alpaca-DPO-i1-GGUF/resolve/main/Miqu-70B-Alpaca-DPO.i1-Q5_K_M.gguf) | i1-Q5_K_M | 49.2 | |
47
  | [PART 1](https://huggingface.co/mradermacher/Miqu-70B-Alpaca-DPO-i1-GGUF/resolve/main/Miqu-70B-Alpaca-DPO.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Miqu-70B-Alpaca-DPO-i1-GGUF/resolve/main/Miqu-70B-Alpaca-DPO.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 57.0 | practically like static Q6_K |
48
 
49
-
50
  Here is a handy graph by ikawrakow comparing some lower-quality quant
51
  types (lower is better):
52
 
 
24
  | Link | Type | Size/GB | Notes |
25
  |:-----|:-----|--------:|:------|
26
  | [GGUF](https://huggingface.co/mradermacher/Miqu-70B-Alpaca-DPO-i1-GGUF/resolve/main/Miqu-70B-Alpaca-DPO.i1-IQ1_S.gguf) | i1-IQ1_S | 15.0 | for the desperate |
27
+ | [GGUF](https://huggingface.co/mradermacher/Miqu-70B-Alpaca-DPO-i1-GGUF/resolve/main/Miqu-70B-Alpaca-DPO.i1-IQ1_M.gguf) | i1-IQ1_M | 16.0 | mostly desperate |
28
  | [GGUF](https://huggingface.co/mradermacher/Miqu-70B-Alpaca-DPO-i1-GGUF/resolve/main/Miqu-70B-Alpaca-DPO.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 18.7 | |
29
  | [GGUF](https://huggingface.co/mradermacher/Miqu-70B-Alpaca-DPO-i1-GGUF/resolve/main/Miqu-70B-Alpaca-DPO.i1-IQ2_XS.gguf) | i1-IQ2_XS | 20.8 | |
30
  | [GGUF](https://huggingface.co/mradermacher/Miqu-70B-Alpaca-DPO-i1-GGUF/resolve/main/Miqu-70B-Alpaca-DPO.i1-IQ2_S.gguf) | i1-IQ2_S | 21.8 | |
 
38
  | [GGUF](https://huggingface.co/mradermacher/Miqu-70B-Alpaca-DPO-i1-GGUF/resolve/main/Miqu-70B-Alpaca-DPO.i1-Q3_K_M.gguf) | i1-Q3_K_M | 33.7 | IQ3_S probably better |
39
  | [GGUF](https://huggingface.co/mradermacher/Miqu-70B-Alpaca-DPO-i1-GGUF/resolve/main/Miqu-70B-Alpaca-DPO.i1-Q3_K_L.gguf) | i1-Q3_K_L | 36.6 | IQ3_M probably better |
40
  | [GGUF](https://huggingface.co/mradermacher/Miqu-70B-Alpaca-DPO-i1-GGUF/resolve/main/Miqu-70B-Alpaca-DPO.i1-IQ4_XS.gguf) | i1-IQ4_XS | 37.2 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/Miqu-70B-Alpaca-DPO-i1-GGUF/resolve/main/Miqu-70B-Alpaca-DPO.i1-IQ4_NL.gguf) | i1-IQ4_NL | 39.4 | prefer IQ4_XS |
42
  | [GGUF](https://huggingface.co/mradermacher/Miqu-70B-Alpaca-DPO-i1-GGUF/resolve/main/Miqu-70B-Alpaca-DPO.i1-Q4_0.gguf) | i1-Q4_0 | 39.4 | fast, low quality |
43
  | [GGUF](https://huggingface.co/mradermacher/Miqu-70B-Alpaca-DPO-i1-GGUF/resolve/main/Miqu-70B-Alpaca-DPO.i1-Q4_K_S.gguf) | i1-Q4_K_S | 39.7 | optimal size/speed/quality |
44
  | [GGUF](https://huggingface.co/mradermacher/Miqu-70B-Alpaca-DPO-i1-GGUF/resolve/main/Miqu-70B-Alpaca-DPO.i1-Q4_K_M.gguf) | i1-Q4_K_M | 41.8 | fast, recommended |
 
46
  | [GGUF](https://huggingface.co/mradermacher/Miqu-70B-Alpaca-DPO-i1-GGUF/resolve/main/Miqu-70B-Alpaca-DPO.i1-Q5_K_M.gguf) | i1-Q5_K_M | 49.2 | |
47
  | [PART 1](https://huggingface.co/mradermacher/Miqu-70B-Alpaca-DPO-i1-GGUF/resolve/main/Miqu-70B-Alpaca-DPO.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Miqu-70B-Alpaca-DPO-i1-GGUF/resolve/main/Miqu-70B-Alpaca-DPO.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 57.0 | practically like static Q6_K |
48
 
 
49
  Here is a handy graph by ikawrakow comparing some lower-quality quant
50
  types (lower is better):
51