Hugging Face's logo

mradermacher
/
Nous-Hermes-Llama2-70b-i1-GGUF

Transformers
GGUF
English
llama-2
self-instruct
distillation
synthetic instruction
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
4788b08
•
1 Parent(s): 1cc6ba3

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -1
README.md CHANGED
@@ -20,7 +20,6 @@ tags:
20
  <!-- ### vocab_type: -->
21
  weighted/imatrix quants of https://huggingface.co/NousResearch/Nous-Hermes-Llama2-70b
22
 
23
-
24
  <!-- provided-files -->
25
  static quants are available at https://huggingface.co/mradermacher/Nous-Hermes-Llama2-70b-GGUF
26
  ## Usage
@@ -35,11 +34,15 @@ more details, including on how to concatenate multi-part files.
35
 
36
  | Link | Type | Size/GB | Notes |
37
  |:-----|:-----|--------:|:------|
 
 
38
  | [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-Llama2-70b-i1-GGUF/resolve/main/Nous-Hermes-Llama2-70b.i1-IQ2_M.gguf) | i1-IQ2_M | 23.3 | |
39
  | [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-Llama2-70b-i1-GGUF/resolve/main/Nous-Hermes-Llama2-70b.i1-Q2_K.gguf) | i1-Q2_K | 25.6 | IQ3_XXS probably better |
40
  | [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-Llama2-70b-i1-GGUF/resolve/main/Nous-Hermes-Llama2-70b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 26.7 | lower quality |
41
  | [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-Llama2-70b-i1-GGUF/resolve/main/Nous-Hermes-Llama2-70b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 28.4 | |
 
42
  | [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-Llama2-70b-i1-GGUF/resolve/main/Nous-Hermes-Llama2-70b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 30.0 | IQ3_XS probably better |
 
43
  | [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-Llama2-70b-i1-GGUF/resolve/main/Nous-Hermes-Llama2-70b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 33.4 | IQ3_S probably better |
44
  | [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-Llama2-70b-i1-GGUF/resolve/main/Nous-Hermes-Llama2-70b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 36.2 | IQ3_M probably better |
45
  | [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-Llama2-70b-i1-GGUF/resolve/main/Nous-Hermes-Llama2-70b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 36.9 | |
 
20
  <!-- ### vocab_type: -->
21
  weighted/imatrix quants of https://huggingface.co/NousResearch/Nous-Hermes-Llama2-70b
22
 
 
23
  <!-- provided-files -->
24
  static quants are available at https://huggingface.co/mradermacher/Nous-Hermes-Llama2-70b-GGUF
25
  ## Usage
 
34
 
35
  | Link | Type | Size/GB | Notes |
36
  |:-----|:-----|--------:|:------|
37
+ | [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-Llama2-70b-i1-GGUF/resolve/main/Nous-Hermes-Llama2-70b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 18.4 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-Llama2-70b-i1-GGUF/resolve/main/Nous-Hermes-Llama2-70b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 20.4 | |
39
  | [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-Llama2-70b-i1-GGUF/resolve/main/Nous-Hermes-Llama2-70b.i1-IQ2_M.gguf) | i1-IQ2_M | 23.3 | |
40
  | [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-Llama2-70b-i1-GGUF/resolve/main/Nous-Hermes-Llama2-70b.i1-Q2_K.gguf) | i1-Q2_K | 25.6 | IQ3_XXS probably better |
41
  | [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-Llama2-70b-i1-GGUF/resolve/main/Nous-Hermes-Llama2-70b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 26.7 | lower quality |
42
  | [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-Llama2-70b-i1-GGUF/resolve/main/Nous-Hermes-Llama2-70b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 28.4 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-Llama2-70b-i1-GGUF/resolve/main/Nous-Hermes-Llama2-70b.i1-IQ3_S.gguf) | i1-IQ3_S | 30.0 | beats Q3_K* |
44
  | [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-Llama2-70b-i1-GGUF/resolve/main/Nous-Hermes-Llama2-70b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 30.0 | IQ3_XS probably better |
45
+ | [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-Llama2-70b-i1-GGUF/resolve/main/Nous-Hermes-Llama2-70b.i1-IQ3_M.gguf) | i1-IQ3_M | 31.0 | |
46
  | [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-Llama2-70b-i1-GGUF/resolve/main/Nous-Hermes-Llama2-70b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 33.4 | IQ3_S probably better |
47
  | [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-Llama2-70b-i1-GGUF/resolve/main/Nous-Hermes-Llama2-70b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 36.2 | IQ3_M probably better |
48
  | [GGUF](https://huggingface.co/mradermacher/Nous-Hermes-Llama2-70b-i1-GGUF/resolve/main/Nous-Hermes-Llama2-70b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 36.9 | |