Hugging Face's logo

mradermacher
/
llama-65b-hf-GGUF

Transformers
GGUF
English
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
b4601eb
•
1 Parent(s): 0fd52fb

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -2
README.md CHANGED
@@ -14,9 +14,8 @@ quantized_by: mradermacher
14
  <!-- ### vocab_type: -->
15
  static quants of https://huggingface.co/Enoch/llama-65b-hf
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
@@ -30,13 +29,17 @@ more details, including on how to concatenate multi-part files.
30
  | Link | Type | Size/GB | Notes |
31
  |:-----|:-----|--------:|:------|
32
  | [GGUF](https://huggingface.co/mradermacher/llama-65b-hf-GGUF/resolve/main/llama-65b-hf.Q2_K.gguf) | Q2_K | 24.2 | |
 
33
  | [GGUF](https://huggingface.co/mradermacher/llama-65b-hf-GGUF/resolve/main/llama-65b-hf.IQ3_S.gguf) | IQ3_S | 28.3 | beats Q3_K* |
34
  | [GGUF](https://huggingface.co/mradermacher/llama-65b-hf-GGUF/resolve/main/llama-65b-hf.Q3_K_S.gguf) | Q3_K_S | 28.3 | |
35
  | [GGUF](https://huggingface.co/mradermacher/llama-65b-hf-GGUF/resolve/main/llama-65b-hf.IQ3_M.gguf) | IQ3_M | 29.9 | |
36
  | [GGUF](https://huggingface.co/mradermacher/llama-65b-hf-GGUF/resolve/main/llama-65b-hf.Q3_K_M.gguf) | Q3_K_M | 31.7 | lower quality |
37
  | [GGUF](https://huggingface.co/mradermacher/llama-65b-hf-GGUF/resolve/main/llama-65b-hf.Q3_K_L.gguf) | Q3_K_L | 34.7 | |
 
38
  | [GGUF](https://huggingface.co/mradermacher/llama-65b-hf-GGUF/resolve/main/llama-65b-hf.Q4_K_S.gguf) | Q4_K_S | 37.2 | fast, recommended |
39
  | [GGUF](https://huggingface.co/mradermacher/llama-65b-hf-GGUF/resolve/main/llama-65b-hf.Q4_K_M.gguf) | Q4_K_M | 39.4 | fast, recommended |
 
 
40
  | [PART 1](https://huggingface.co/mradermacher/llama-65b-hf-GGUF/resolve/main/llama-65b-hf.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/llama-65b-hf-GGUF/resolve/main/llama-65b-hf.Q6_K.gguf.part2of2) | Q6_K | 53.7 | very good quality |
41
  | [PART 1](https://huggingface.co/mradermacher/llama-65b-hf-GGUF/resolve/main/llama-65b-hf.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/llama-65b-hf-GGUF/resolve/main/llama-65b-hf.Q8_0.gguf.part2of2) | Q8_0 | 69.5 | fast, best quality |
42
 
 
14
  <!-- ### vocab_type: -->
15
  static quants of https://huggingface.co/Enoch/llama-65b-hf
16
 
 
17
  <!-- provided-files -->
18
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/llama-65b-hf-i1-GGUF
19
  ## Usage
20
 
21
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
 
29
  | Link | Type | Size/GB | Notes |
30
  |:-----|:-----|--------:|:------|
31
  | [GGUF](https://huggingface.co/mradermacher/llama-65b-hf-GGUF/resolve/main/llama-65b-hf.Q2_K.gguf) | Q2_K | 24.2 | |
32
+ | [GGUF](https://huggingface.co/mradermacher/llama-65b-hf-GGUF/resolve/main/llama-65b-hf.IQ3_XS.gguf) | IQ3_XS | 26.7 | |
33
  | [GGUF](https://huggingface.co/mradermacher/llama-65b-hf-GGUF/resolve/main/llama-65b-hf.IQ3_S.gguf) | IQ3_S | 28.3 | beats Q3_K* |
34
  | [GGUF](https://huggingface.co/mradermacher/llama-65b-hf-GGUF/resolve/main/llama-65b-hf.Q3_K_S.gguf) | Q3_K_S | 28.3 | |
35
  | [GGUF](https://huggingface.co/mradermacher/llama-65b-hf-GGUF/resolve/main/llama-65b-hf.IQ3_M.gguf) | IQ3_M | 29.9 | |
36
  | [GGUF](https://huggingface.co/mradermacher/llama-65b-hf-GGUF/resolve/main/llama-65b-hf.Q3_K_M.gguf) | Q3_K_M | 31.7 | lower quality |
37
  | [GGUF](https://huggingface.co/mradermacher/llama-65b-hf-GGUF/resolve/main/llama-65b-hf.Q3_K_L.gguf) | Q3_K_L | 34.7 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/llama-65b-hf-GGUF/resolve/main/llama-65b-hf.IQ4_XS.gguf) | IQ4_XS | 35.1 | |
39
  | [GGUF](https://huggingface.co/mradermacher/llama-65b-hf-GGUF/resolve/main/llama-65b-hf.Q4_K_S.gguf) | Q4_K_S | 37.2 | fast, recommended |
40
  | [GGUF](https://huggingface.co/mradermacher/llama-65b-hf-GGUF/resolve/main/llama-65b-hf.Q4_K_M.gguf) | Q4_K_M | 39.4 | fast, recommended |
41
+ | [GGUF](https://huggingface.co/mradermacher/llama-65b-hf-GGUF/resolve/main/llama-65b-hf.Q5_K_S.gguf) | Q5_K_S | 45.0 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/llama-65b-hf-GGUF/resolve/main/llama-65b-hf.Q5_K_M.gguf) | Q5_K_M | 46.3 | |
43
  | [PART 1](https://huggingface.co/mradermacher/llama-65b-hf-GGUF/resolve/main/llama-65b-hf.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/llama-65b-hf-GGUF/resolve/main/llama-65b-hf.Q6_K.gguf.part2of2) | Q6_K | 53.7 | very good quality |
44
  | [PART 1](https://huggingface.co/mradermacher/llama-65b-hf-GGUF/resolve/main/llama-65b-hf.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/llama-65b-hf-GGUF/resolve/main/llama-65b-hf.Q8_0.gguf.part2of2) | Q8_0 | 69.5 | fast, best quality |
45