mradermacher commited on
Commit
6c49c4b
1 Parent(s): 613a2df

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -2
README.md CHANGED
@@ -17,7 +17,6 @@ tags:
17
  <!-- ### vocab_type: -->
18
  weighted/imatrix quants of https://huggingface.co/abacusai/Llama-3-Giraffe-70B-Instruct
19
 
20
-
21
  <!-- provided-files -->
22
  static quants are available at https://huggingface.co/mradermacher/Llama-3-Giraffe-70B-Instruct-GGUF
23
  ## Usage
@@ -54,7 +53,6 @@ more details, including on how to concatenate multi-part files.
54
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-Giraffe-70B-Instruct-i1-GGUF/resolve/main/Llama-3-Giraffe-70B-Instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 50.0 | |
55
  | [PART 1](https://huggingface.co/mradermacher/Llama-3-Giraffe-70B-Instruct-i1-GGUF/resolve/main/Llama-3-Giraffe-70B-Instruct.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-3-Giraffe-70B-Instruct-i1-GGUF/resolve/main/Llama-3-Giraffe-70B-Instruct.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 58.0 | practically like static Q6_K |
56
 
57
-
58
  Here is a handy graph by ikawrakow comparing some lower-quality quant
59
  types (lower is better):
60
 
 
17
  <!-- ### vocab_type: -->
18
  weighted/imatrix quants of https://huggingface.co/abacusai/Llama-3-Giraffe-70B-Instruct
19
 
 
20
  <!-- provided-files -->
21
  static quants are available at https://huggingface.co/mradermacher/Llama-3-Giraffe-70B-Instruct-GGUF
22
  ## Usage
 
53
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-Giraffe-70B-Instruct-i1-GGUF/resolve/main/Llama-3-Giraffe-70B-Instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 50.0 | |
54
  | [PART 1](https://huggingface.co/mradermacher/Llama-3-Giraffe-70B-Instruct-i1-GGUF/resolve/main/Llama-3-Giraffe-70B-Instruct.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-3-Giraffe-70B-Instruct-i1-GGUF/resolve/main/Llama-3-Giraffe-70B-Instruct.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 58.0 | practically like static Q6_K |
55
 
 
56
  Here is a handy graph by ikawrakow comparing some lower-quality quant
57
  types (lower is better):
58