Hugging Face's logo

mradermacher
/
Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a-i1-GGUF

Transformers
GGUF
English
imatrix
conversational
Model card Files
xet
Community
mradermacher commited on
Commit
a373607
·
verified ·
1 Parent(s): fb64643

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +75 -0
README.md CHANGED
@@ -1,3 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 2 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: hf -->
@@ -7,3 +18,67 @@
7
  <!-- ### quants_skip: -->
8
  <!-- ### skip_mmproj: -->
9
  weighted/imatrix quants of https://huggingface.co/Nitral-Archive/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Nitral-Archive/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ mradermacher:
7
+ readme_rev: 1
8
+ quantized_by: mradermacher
9
+ ---
10
+ ## About
11
+
12
  <!-- ### quantize_version: 2 -->
13
  <!-- ### output_tensor_quantised: 1 -->
14
  <!-- ### convert_type: hf -->
 
18
  <!-- ### quants_skip: -->
19
  <!-- ### skip_mmproj: -->
20
  weighted/imatrix quants of https://huggingface.co/Nitral-Archive/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a
21
+
22
+ <!-- provided-files -->
23
+
24
+ ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a-i1-GGUF).***
25
+
26
+ static quants are available at https://huggingface.co/mradermacher/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a-GGUF
27
+ ## Usage
28
+
29
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
30
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
31
+ more details, including on how to concatenate multi-part files.
32
+
33
+ ## Provided Quants
34
+
35
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
36
+
37
+ | Link | Type | Size/GB | Notes |
38
+ |:-----|:-----|--------:|:------|
39
+ | [GGUF](https://huggingface.co/mradermacher/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a-i1-GGUF/resolve/main/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
40
+ | [GGUF](https://huggingface.co/mradermacher/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a-i1-GGUF/resolve/main/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a.i1-IQ1_S.gguf) | i1-IQ1_S | 3.1 | for the desperate |
41
+ | [GGUF](https://huggingface.co/mradermacher/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a-i1-GGUF/resolve/main/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a.i1-IQ1_M.gguf) | i1-IQ1_M | 3.3 | mostly desperate |
42
+ | [GGUF](https://huggingface.co/mradermacher/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a-i1-GGUF/resolve/main/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.7 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a-i1-GGUF/resolve/main/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.0 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a-i1-GGUF/resolve/main/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a.i1-IQ2_S.gguf) | i1-IQ2_S | 4.2 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a-i1-GGUF/resolve/main/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a.i1-IQ2_M.gguf) | i1-IQ2_M | 4.5 | |
46
+ | [GGUF](https://huggingface.co/mradermacher/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a-i1-GGUF/resolve/main/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a.i1-Q2_K_S.gguf) | i1-Q2_K_S | 4.6 | very low quality |
47
+ | [GGUF](https://huggingface.co/mradermacher/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a-i1-GGUF/resolve/main/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a.i1-Q2_K.gguf) | i1-Q2_K | 4.9 | IQ3_XXS probably better |
48
+ | [GGUF](https://huggingface.co/mradermacher/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a-i1-GGUF/resolve/main/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.0 | lower quality |
49
+ | [GGUF](https://huggingface.co/mradermacher/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a-i1-GGUF/resolve/main/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.4 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a-i1-GGUF/resolve/main/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.6 | IQ3_XS probably better |
51
+ | [GGUF](https://huggingface.co/mradermacher/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a-i1-GGUF/resolve/main/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a.i1-IQ3_S.gguf) | i1-IQ3_S | 5.7 | beats Q3_K* |
52
+ | [GGUF](https://huggingface.co/mradermacher/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a-i1-GGUF/resolve/main/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a.i1-IQ3_M.gguf) | i1-IQ3_M | 5.8 | |
53
+ | [GGUF](https://huggingface.co/mradermacher/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a-i1-GGUF/resolve/main/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.2 | IQ3_S probably better |
54
+ | [GGUF](https://huggingface.co/mradermacher/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a-i1-GGUF/resolve/main/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a.i1-Q3_K_L.gguf) | i1-Q3_K_L | 6.7 | IQ3_M probably better |
55
+ | [GGUF](https://huggingface.co/mradermacher/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a-i1-GGUF/resolve/main/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a.i1-IQ4_XS.gguf) | i1-IQ4_XS | 6.8 | |
56
+ | [GGUF](https://huggingface.co/mradermacher/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a-i1-GGUF/resolve/main/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a.i1-Q4_0.gguf) | i1-Q4_0 | 7.2 | fast, low quality |
57
+ | [GGUF](https://huggingface.co/mradermacher/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a-i1-GGUF/resolve/main/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a.i1-IQ4_NL.gguf) | i1-IQ4_NL | 7.2 | prefer IQ4_XS |
58
+ | [GGUF](https://huggingface.co/mradermacher/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a-i1-GGUF/resolve/main/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.2 | optimal size/speed/quality |
59
+ | [GGUF](https://huggingface.co/mradermacher/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a-i1-GGUF/resolve/main/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a.i1-Q4_K_M.gguf) | i1-Q4_K_M | 7.6 | fast, recommended |
60
+ | [GGUF](https://huggingface.co/mradermacher/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a-i1-GGUF/resolve/main/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a.i1-Q4_1.gguf) | i1-Q4_1 | 7.9 | |
61
+ | [GGUF](https://huggingface.co/mradermacher/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a-i1-GGUF/resolve/main/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a.i1-Q5_K_S.gguf) | i1-Q5_K_S | 8.6 | |
62
+ | [GGUF](https://huggingface.co/mradermacher/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a-i1-GGUF/resolve/main/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a.i1-Q5_K_M.gguf) | i1-Q5_K_M | 8.8 | |
63
+ | [GGUF](https://huggingface.co/mradermacher/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a-i1-GGUF/resolve/main/Pinecone-Rune-12b-Token-Surgery-Chatml-v0.1a.i1-Q6_K.gguf) | i1-Q6_K | 10.2 | practically like static Q6_K |
64
+
65
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
66
+ types (lower is better):
67
+
68
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
69
+
70
+ And here are Artefact2's thoughts on the matter:
71
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
72
+
73
+ ## FAQ / Model Request
74
+
75
+ See https://huggingface.co/mradermacher/model_requests for some answers to
76
+ questions you might have and/or if you want some other model quantized.
77
+
78
+ ## Thanks
79
+
80
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
81
+ me use its servers and providing upgrades to my workstation to enable
82
+ this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
83
+
84
+ <!-- end -->