Hugging Face's logo

mradermacher
/
Pearl-34B-ties-GGUF

Transformers
GGUF
English
Merge
mergekit
jondurbin/bagel-dpo-34b-v0.2
abacusai/MetaMath-Bagel-DPO-34B
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
3be356d
•
1 Parent(s): 858433f

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -2
README.md CHANGED
@@ -20,9 +20,8 @@ tags:
20
  <!-- ### vocab_type: -->
21
  static quants of https://huggingface.co/louisbrulenaudet/Pearl-34B-ties
22
 
23
-
24
  <!-- provided-files -->
25
- weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
26
  ## Usage
27
 
28
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
@@ -35,8 +34,20 @@ more details, including on how to concatenate multi-part files.
35
 
36
  | Link | Type | Size/GB | Notes |
37
  |:-----|:-----|--------:|:------|
 
 
 
 
 
38
  | [GGUF](https://huggingface.co/mradermacher/Pearl-34B-ties-GGUF/resolve/main/Pearl-34B-ties.Q3_K_M.gguf) | Q3_K_M | 17.3 | lower quality |
 
 
39
  | [GGUF](https://huggingface.co/mradermacher/Pearl-34B-ties-GGUF/resolve/main/Pearl-34B-ties.Q4_K_S.gguf) | Q4_K_S | 20.2 | fast, recommended |
 
 
 
 
 
40
 
41
 
42
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
20
  <!-- ### vocab_type: -->
21
  static quants of https://huggingface.co/louisbrulenaudet/Pearl-34B-ties
22
 
 
23
  <!-- provided-files -->
24
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/Pearl-34B-ties-i1-GGUF
25
  ## Usage
26
 
27
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
 
34
 
35
  | Link | Type | Size/GB | Notes |
36
  |:-----|:-----|--------:|:------|
37
+ | [GGUF](https://huggingface.co/mradermacher/Pearl-34B-ties-GGUF/resolve/main/Pearl-34B-ties.Q2_K.gguf) | Q2_K | 13.5 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/Pearl-34B-ties-GGUF/resolve/main/Pearl-34B-ties.IQ3_XS.gguf) | IQ3_XS | 14.9 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/Pearl-34B-ties-GGUF/resolve/main/Pearl-34B-ties.Q3_K_S.gguf) | Q3_K_S | 15.6 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/Pearl-34B-ties-GGUF/resolve/main/Pearl-34B-ties.IQ3_S.gguf) | IQ3_S | 15.7 | beats Q3_K* |
41
+ | [GGUF](https://huggingface.co/mradermacher/Pearl-34B-ties-GGUF/resolve/main/Pearl-34B-ties.IQ3_M.gguf) | IQ3_M | 16.2 | |
42
  | [GGUF](https://huggingface.co/mradermacher/Pearl-34B-ties-GGUF/resolve/main/Pearl-34B-ties.Q3_K_M.gguf) | Q3_K_M | 17.3 | lower quality |
43
+ | [GGUF](https://huggingface.co/mradermacher/Pearl-34B-ties-GGUF/resolve/main/Pearl-34B-ties.Q3_K_L.gguf) | Q3_K_L | 18.8 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/Pearl-34B-ties-GGUF/resolve/main/Pearl-34B-ties.IQ4_XS.gguf) | IQ4_XS | 19.3 | |
45
  | [GGUF](https://huggingface.co/mradermacher/Pearl-34B-ties-GGUF/resolve/main/Pearl-34B-ties.Q4_K_S.gguf) | Q4_K_S | 20.2 | fast, recommended |
46
+ | [GGUF](https://huggingface.co/mradermacher/Pearl-34B-ties-GGUF/resolve/main/Pearl-34B-ties.Q4_K_M.gguf) | Q4_K_M | 21.3 | fast, recommended |
47
+ | [GGUF](https://huggingface.co/mradermacher/Pearl-34B-ties-GGUF/resolve/main/Pearl-34B-ties.Q5_K_S.gguf) | Q5_K_S | 24.3 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/Pearl-34B-ties-GGUF/resolve/main/Pearl-34B-ties.Q5_K_M.gguf) | Q5_K_M | 25.0 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/Pearl-34B-ties-GGUF/resolve/main/Pearl-34B-ties.Q6_K.gguf) | Q6_K | 28.9 | very good quality |
50
+ | [GGUF](https://huggingface.co/mradermacher/Pearl-34B-ties-GGUF/resolve/main/Pearl-34B-ties.Q8_0.gguf) | Q8_0 | 37.1 | fast, best quality |
51
 
52
 
53
  Here is a handy graph by ikawrakow comparing some lower-quality quant