Hugging Face's logo

mradermacher
/
Llama3-70B-ShiningValiant2-GGUF

Transformers
GGUF
English
shining-valiant
shining-valiant-2
valiant
valiant-labs
llama
llama-3
llama-3-instruct
llama-3-instruct-70b
70b
conversational
chat
instruct
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
f381e6c
·
verified ·
1 Parent(s): e3e1281

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -2
README.md CHANGED
@@ -30,9 +30,8 @@ tags:
30
  <!-- ### vocab_type: -->
31
  static quants of https://huggingface.co/ValiantLabs/Llama3-70B-ShiningValiant2
32
 
33
-
34
  <!-- provided-files -->
35
- 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.
36
  ## Usage
37
 
38
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
@@ -45,6 +44,19 @@ more details, including on how to concatenate multi-part files.
45
 
46
  | Link | Type | Size/GB | Notes |
47
  |:-----|:-----|--------:|:------|
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  | [PART 1](https://huggingface.co/mradermacher/Llama3-70B-ShiningValiant2-GGUF/resolve/main/Llama3-70B-ShiningValiant2.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama3-70B-ShiningValiant2-GGUF/resolve/main/Llama3-70B-ShiningValiant2.Q8_0.gguf.part2of2) | Q8_0 | 75.1 | fast, best quality |
49
 
50
 
 
30
  <!-- ### vocab_type: -->
31
  static quants of https://huggingface.co/ValiantLabs/Llama3-70B-ShiningValiant2
32
 
 
33
  <!-- provided-files -->
34
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama3-70B-ShiningValiant2-i1-GGUF
35
  ## Usage
36
 
37
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
 
44
 
45
  | Link | Type | Size/GB | Notes |
46
  |:-----|:-----|--------:|:------|
47
+ | [GGUF](https://huggingface.co/mradermacher/Llama3-70B-ShiningValiant2-GGUF/resolve/main/Llama3-70B-ShiningValiant2.Q2_K.gguf) | Q2_K | 26.5 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/Llama3-70B-ShiningValiant2-GGUF/resolve/main/Llama3-70B-ShiningValiant2.IQ3_XS.gguf) | IQ3_XS | 29.4 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/Llama3-70B-ShiningValiant2-GGUF/resolve/main/Llama3-70B-ShiningValiant2.IQ3_S.gguf) | IQ3_S | 31.0 | beats Q3_K* |
50
+ | [GGUF](https://huggingface.co/mradermacher/Llama3-70B-ShiningValiant2-GGUF/resolve/main/Llama3-70B-ShiningValiant2.Q3_K_S.gguf) | Q3_K_S | 31.0 | |
51
+ | [GGUF](https://huggingface.co/mradermacher/Llama3-70B-ShiningValiant2-GGUF/resolve/main/Llama3-70B-ShiningValiant2.IQ3_M.gguf) | IQ3_M | 32.0 | |
52
+ | [GGUF](https://huggingface.co/mradermacher/Llama3-70B-ShiningValiant2-GGUF/resolve/main/Llama3-70B-ShiningValiant2.Q3_K_M.gguf) | Q3_K_M | 34.4 | lower quality |
53
+ | [GGUF](https://huggingface.co/mradermacher/Llama3-70B-ShiningValiant2-GGUF/resolve/main/Llama3-70B-ShiningValiant2.Q3_K_L.gguf) | Q3_K_L | 37.2 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/Llama3-70B-ShiningValiant2-GGUF/resolve/main/Llama3-70B-ShiningValiant2.IQ4_XS.gguf) | IQ4_XS | 38.4 | |
55
+ | [GGUF](https://huggingface.co/mradermacher/Llama3-70B-ShiningValiant2-GGUF/resolve/main/Llama3-70B-ShiningValiant2.Q4_K_S.gguf) | Q4_K_S | 40.4 | fast, recommended |
56
+ | [GGUF](https://huggingface.co/mradermacher/Llama3-70B-ShiningValiant2-GGUF/resolve/main/Llama3-70B-ShiningValiant2.Q4_K_M.gguf) | Q4_K_M | 42.6 | fast, recommended |
57
+ | [GGUF](https://huggingface.co/mradermacher/Llama3-70B-ShiningValiant2-GGUF/resolve/main/Llama3-70B-ShiningValiant2.Q5_K_S.gguf) | Q5_K_S | 48.8 | |
58
+ | [GGUF](https://huggingface.co/mradermacher/Llama3-70B-ShiningValiant2-GGUF/resolve/main/Llama3-70B-ShiningValiant2.Q5_K_M.gguf) | Q5_K_M | 50.1 | |
59
+ | [PART 1](https://huggingface.co/mradermacher/Llama3-70B-ShiningValiant2-GGUF/resolve/main/Llama3-70B-ShiningValiant2.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama3-70B-ShiningValiant2-GGUF/resolve/main/Llama3-70B-ShiningValiant2.Q6_K.gguf.part2of2) | Q6_K | 58.0 | very good quality |
60
  | [PART 1](https://huggingface.co/mradermacher/Llama3-70B-ShiningValiant2-GGUF/resolve/main/Llama3-70B-ShiningValiant2.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama3-70B-ShiningValiant2-GGUF/resolve/main/Llama3-70B-ShiningValiant2.Q8_0.gguf.part2of2) | Q8_0 | 75.1 | fast, best quality |
61
 
62