mradermacher commited on
Commit
fec0617
1 Parent(s): 9766da2

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -1
README.md CHANGED
@@ -19,7 +19,7 @@ tags:
19
  static quants of https://huggingface.co/upstage/llama-65b-instruct
20
 
21
  <!-- provided-files -->
22
- 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.
23
  ## Usage
24
 
25
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
@@ -32,7 +32,19 @@ more details, including on how to concatenate multi-part files.
32
 
33
  | Link | Type | Size/GB | Notes |
34
  |:-----|:-----|--------:|:------|
 
 
35
  | [GGUF](https://huggingface.co/mradermacher/llama-65b-instruct-GGUF/resolve/main/llama-65b-instruct.IQ3_S.gguf) | IQ3_S | 28.3 | beats Q3_K* |
 
 
 
 
 
 
 
 
 
 
36
  | [PART 1](https://huggingface.co/mradermacher/llama-65b-instruct-GGUF/resolve/main/llama-65b-instruct.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/llama-65b-instruct-GGUF/resolve/main/llama-65b-instruct.Q8_0.gguf.part2of2) | Q8_0 | 69.5 | fast, best quality |
37
 
38
 
 
19
  static quants of https://huggingface.co/upstage/llama-65b-instruct
20
 
21
  <!-- provided-files -->
22
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/llama-65b-instruct-i1-GGUF
23
  ## Usage
24
 
25
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
 
32
 
33
  | Link | Type | Size/GB | Notes |
34
  |:-----|:-----|--------:|:------|
35
+ | [GGUF](https://huggingface.co/mradermacher/llama-65b-instruct-GGUF/resolve/main/llama-65b-instruct.Q2_K.gguf) | Q2_K | 24.2 | |
36
+ | [GGUF](https://huggingface.co/mradermacher/llama-65b-instruct-GGUF/resolve/main/llama-65b-instruct.IQ3_XS.gguf) | IQ3_XS | 26.7 | |
37
  | [GGUF](https://huggingface.co/mradermacher/llama-65b-instruct-GGUF/resolve/main/llama-65b-instruct.IQ3_S.gguf) | IQ3_S | 28.3 | beats Q3_K* |
38
+ | [GGUF](https://huggingface.co/mradermacher/llama-65b-instruct-GGUF/resolve/main/llama-65b-instruct.Q3_K_S.gguf) | Q3_K_S | 28.3 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/llama-65b-instruct-GGUF/resolve/main/llama-65b-instruct.IQ3_M.gguf) | IQ3_M | 29.9 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/llama-65b-instruct-GGUF/resolve/main/llama-65b-instruct.Q3_K_M.gguf) | Q3_K_M | 31.7 | lower quality |
41
+ | [GGUF](https://huggingface.co/mradermacher/llama-65b-instruct-GGUF/resolve/main/llama-65b-instruct.Q3_K_L.gguf) | Q3_K_L | 34.7 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/llama-65b-instruct-GGUF/resolve/main/llama-65b-instruct.IQ4_XS.gguf) | IQ4_XS | 35.1 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/llama-65b-instruct-GGUF/resolve/main/llama-65b-instruct.Q4_K_S.gguf) | Q4_K_S | 37.2 | fast, recommended |
44
+ | [GGUF](https://huggingface.co/mradermacher/llama-65b-instruct-GGUF/resolve/main/llama-65b-instruct.Q4_K_M.gguf) | Q4_K_M | 39.4 | fast, recommended |
45
+ | [GGUF](https://huggingface.co/mradermacher/llama-65b-instruct-GGUF/resolve/main/llama-65b-instruct.Q5_K_S.gguf) | Q5_K_S | 45.0 | |
46
+ | [GGUF](https://huggingface.co/mradermacher/llama-65b-instruct-GGUF/resolve/main/llama-65b-instruct.Q5_K_M.gguf) | Q5_K_M | 46.3 | |
47
+ | [PART 1](https://huggingface.co/mradermacher/llama-65b-instruct-GGUF/resolve/main/llama-65b-instruct.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/llama-65b-instruct-GGUF/resolve/main/llama-65b-instruct.Q6_K.gguf.part2of2) | Q6_K | 53.7 | very good quality |
48
  | [PART 1](https://huggingface.co/mradermacher/llama-65b-instruct-GGUF/resolve/main/llama-65b-instruct.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/llama-65b-instruct-GGUF/resolve/main/llama-65b-instruct.Q8_0.gguf.part2of2) | Q8_0 | 69.5 | fast, best quality |
49
 
50