mradermacher commited on
Commit
2f8c74f
1 Parent(s): 6fcc2dc

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +55 -0
README.md CHANGED
@@ -1,5 +1,60 @@
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 2 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: -->
4
  <!-- ### vocab_type: -->
5
  static quants of https://huggingface.co/grimulkan/Goliath-longLORA-120b-rope8-32k-fp16
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: grimulkan/Goliath-longLORA-120b-rope8-32k-fp16
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ license: llama2
7
+ quantized_by: mradermacher
8
+ ---
9
+ ## About
10
+
11
  <!-- ### quantize_version: 2 -->
12
  <!-- ### output_tensor_quantised: 1 -->
13
  <!-- ### convert_type: -->
14
  <!-- ### vocab_type: -->
15
  static quants of https://huggingface.co/grimulkan/Goliath-longLORA-120b-rope8-32k-fp16
16
+
17
+
18
+ <!-- provided-files -->
19
+ 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.
20
+ ## Usage
21
+
22
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
23
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
24
+ more details, including on how to concatenate multi-part files.
25
+
26
+ ## Provided Quants
27
+
28
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
29
+
30
+ | Link | Type | Size/GB | Notes |
31
+ |:-----|:-----|--------:|:------|
32
+ | [GGUF](https://huggingface.co/mradermacher/Goliath-longLORA-120b-rope8-32k-fp16-GGUF/resolve/main/Goliath-longLORA-120b-rope8-32k-fp16.Q2_K.gguf) | Q2_K | 43.3 | |
33
+ | [PART 1](https://huggingface.co/mradermacher/Goliath-longLORA-120b-rope8-32k-fp16-GGUF/resolve/main/Goliath-longLORA-120b-rope8-32k-fp16.IQ3_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Goliath-longLORA-120b-rope8-32k-fp16-GGUF/resolve/main/Goliath-longLORA-120b-rope8-32k-fp16.IQ3_S.gguf.part2of2) | IQ3_S | 51.0 | beats Q3_K* |
34
+ | [PART 1](https://huggingface.co/mradermacher/Goliath-longLORA-120b-rope8-32k-fp16-GGUF/resolve/main/Goliath-longLORA-120b-rope8-32k-fp16.IQ3_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Goliath-longLORA-120b-rope8-32k-fp16-GGUF/resolve/main/Goliath-longLORA-120b-rope8-32k-fp16.IQ3_M.gguf.part2of2) | IQ3_M | 52.7 | |
35
+ | [PART 1](https://huggingface.co/mradermacher/Goliath-longLORA-120b-rope8-32k-fp16-GGUF/resolve/main/Goliath-longLORA-120b-rope8-32k-fp16.Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Goliath-longLORA-120b-rope8-32k-fp16-GGUF/resolve/main/Goliath-longLORA-120b-rope8-32k-fp16.Q3_K_M.gguf.part2of2) | Q3_K_M | 56.7 | lower quality |
36
+ | [PART 1](https://huggingface.co/mradermacher/Goliath-longLORA-120b-rope8-32k-fp16-GGUF/resolve/main/Goliath-longLORA-120b-rope8-32k-fp16.Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Goliath-longLORA-120b-rope8-32k-fp16-GGUF/resolve/main/Goliath-longLORA-120b-rope8-32k-fp16.Q4_K_S.gguf.part2of2) | Q4_K_S | 66.9 | fast, recommended |
37
+ | [PART 1](https://huggingface.co/mradermacher/Goliath-longLORA-120b-rope8-32k-fp16-GGUF/resolve/main/Goliath-longLORA-120b-rope8-32k-fp16.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Goliath-longLORA-120b-rope8-32k-fp16-GGUF/resolve/main/Goliath-longLORA-120b-rope8-32k-fp16.Q6_K.gguf.part2of2) | Q6_K | 96.7 | very good quality |
38
+ | [PART 1](https://huggingface.co/mradermacher/Goliath-longLORA-120b-rope8-32k-fp16-GGUF/resolve/main/Goliath-longLORA-120b-rope8-32k-fp16.Q8_0.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Goliath-longLORA-120b-rope8-32k-fp16-GGUF/resolve/main/Goliath-longLORA-120b-rope8-32k-fp16.Q8_0.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Goliath-longLORA-120b-rope8-32k-fp16-GGUF/resolve/main/Goliath-longLORA-120b-rope8-32k-fp16.Q8_0.gguf.part3of3) | Q8_0 | 125.2 | fast, best quality |
39
+
40
+
41
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
42
+ types (lower is better):
43
+
44
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
45
+
46
+ And here are Artefact2's thoughts on the matter:
47
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
48
+
49
+ ## FAQ / Model Request
50
+
51
+ See https://huggingface.co/mradermacher/model_requests for some answers to
52
+ questions you might have and/or if you want some other model quantized.
53
+
54
+ ## Thanks
55
+
56
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
57
+ me use its servers and providing upgrades to my workstation to enable
58
+ this work in my free time.
59
+
60
+ <!-- end -->