Hugging Face's logo

mradermacher
/
Rudra-7b-GGUF

Transformers
GGUF
Sanskrit
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
7f5a44f
•
1 Parent(s): 95a3aa1

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -3
README.md CHANGED
@@ -3,7 +3,7 @@ base_model: saucam/Rudra-7b
3
  datasets:
4
  - saucam/sans_data
5
  language:
6
- - en
7
  library_name: transformers
8
  license: apache-2.0
9
  quantized_by: mradermacher
@@ -35,7 +35,7 @@ more details, including on how to concatenate multi-part files.
35
  | [GGUF](https://huggingface.co/mradermacher/Rudra-7b-GGUF/resolve/main/Rudra-7b.Q3_K_L.gguf) | Q3_K_L | 4.8 | |
36
  | [GGUF](https://huggingface.co/mradermacher/Rudra-7b-GGUF/resolve/main/Rudra-7b.IQ4_XS.gguf) | IQ4_XS | 4.9 | |
37
  | [GGUF](https://huggingface.co/mradermacher/Rudra-7b-GGUF/resolve/main/Rudra-7b.Q4_0.gguf) | Q4_0 | 5.1 | fast, low quality |
38
- | [GGUF](https://huggingface.co/mradermacher/Rudra-7b-GGUF/resolve/main/Rudra-7b.IQ4_NL.gguf) | IQ4_NL | 5.1 | slightly worse than Q4_K_S |
39
  | [GGUF](https://huggingface.co/mradermacher/Rudra-7b-GGUF/resolve/main/Rudra-7b.Q4_K_S.gguf) | Q4_K_S | 5.1 | fast, recommended |
40
  | [GGUF](https://huggingface.co/mradermacher/Rudra-7b-GGUF/resolve/main/Rudra-7b.Q4_K_M.gguf) | Q4_K_M | 5.4 | fast, recommended |
41
  | [GGUF](https://huggingface.co/mradermacher/Rudra-7b-GGUF/resolve/main/Rudra-7b.Q5_K_S.gguf) | Q5_K_S | 6.1 | |
@@ -43,7 +43,6 @@ more details, including on how to concatenate multi-part files.
43
  | [GGUF](https://huggingface.co/mradermacher/Rudra-7b-GGUF/resolve/main/Rudra-7b.Q6_K.gguf) | Q6_K | 7.1 | very good quality |
44
  | [GGUF](https://huggingface.co/mradermacher/Rudra-7b-GGUF/resolve/main/Rudra-7b.Q8_0.gguf) | Q8_0 | 9.2 | fast, best quality |
45
 
46
-
47
  Here is a handy graph by ikawrakow comparing some lower-quality quant
48
  types (lower is better):
49
 
 
3
  datasets:
4
  - saucam/sans_data
5
  language:
6
+ - sa
7
  library_name: transformers
8
  license: apache-2.0
9
  quantized_by: mradermacher
 
35
  | [GGUF](https://huggingface.co/mradermacher/Rudra-7b-GGUF/resolve/main/Rudra-7b.Q3_K_L.gguf) | Q3_K_L | 4.8 | |
36
  | [GGUF](https://huggingface.co/mradermacher/Rudra-7b-GGUF/resolve/main/Rudra-7b.IQ4_XS.gguf) | IQ4_XS | 4.9 | |
37
  | [GGUF](https://huggingface.co/mradermacher/Rudra-7b-GGUF/resolve/main/Rudra-7b.Q4_0.gguf) | Q4_0 | 5.1 | fast, low quality |
38
+ | [GGUF](https://huggingface.co/mradermacher/Rudra-7b-GGUF/resolve/main/Rudra-7b.IQ4_NL.gguf) | IQ4_NL | 5.1 | prefer IQ4_XS |
39
  | [GGUF](https://huggingface.co/mradermacher/Rudra-7b-GGUF/resolve/main/Rudra-7b.Q4_K_S.gguf) | Q4_K_S | 5.1 | fast, recommended |
40
  | [GGUF](https://huggingface.co/mradermacher/Rudra-7b-GGUF/resolve/main/Rudra-7b.Q4_K_M.gguf) | Q4_K_M | 5.4 | fast, recommended |
41
  | [GGUF](https://huggingface.co/mradermacher/Rudra-7b-GGUF/resolve/main/Rudra-7b.Q5_K_S.gguf) | Q5_K_S | 6.1 | |
 
43
  | [GGUF](https://huggingface.co/mradermacher/Rudra-7b-GGUF/resolve/main/Rudra-7b.Q6_K.gguf) | Q6_K | 7.1 | very good quality |
44
  | [GGUF](https://huggingface.co/mradermacher/Rudra-7b-GGUF/resolve/main/Rudra-7b.Q8_0.gguf) | Q8_0 | 9.2 | fast, best quality |
45
 
 
46
  Here is a handy graph by ikawrakow comparing some lower-quality quant
47
  types (lower is better):
48