Hugging Face's logo

mradermacher
/
PrathameshLLM-7B-GGUF

Transformers
GGUF
15 languages
text-generation-inference
unsloth
gemma
trl
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
afe0e98
•
1 Parent(s): 6593d8e

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -2
README.md CHANGED
@@ -2,6 +2,20 @@
2
  base_model: pmking27/PrathameshLLM-7B
3
  language:
4
  - en
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  library_name: transformers
6
  license: apache-2.0
7
  quantized_by: mradermacher
@@ -40,14 +54,13 @@ more details, including on how to concatenate multi-part files.
40
  | [GGUF](https://huggingface.co/mradermacher/PrathameshLLM-7B-GGUF/resolve/main/PrathameshLLM-7B.IQ4_XS.gguf) | IQ4_XS | 1.6 | |
41
  | [GGUF](https://huggingface.co/mradermacher/PrathameshLLM-7B-GGUF/resolve/main/PrathameshLLM-7B.Q4_0.gguf) | Q4_0 | 1.7 | fast, low quality |
42
  | [GGUF](https://huggingface.co/mradermacher/PrathameshLLM-7B-GGUF/resolve/main/PrathameshLLM-7B.Q4_K_S.gguf) | Q4_K_S | 1.7 | fast, recommended |
43
- | [GGUF](https://huggingface.co/mradermacher/PrathameshLLM-7B-GGUF/resolve/main/PrathameshLLM-7B.IQ4_NL.gguf) | IQ4_NL | 1.7 | slightly worse than Q4_K_S |
44
  | [GGUF](https://huggingface.co/mradermacher/PrathameshLLM-7B-GGUF/resolve/main/PrathameshLLM-7B.Q4_K_M.gguf) | Q4_K_M | 1.7 | fast, recommended |
45
  | [GGUF](https://huggingface.co/mradermacher/PrathameshLLM-7B-GGUF/resolve/main/PrathameshLLM-7B.Q5_K_S.gguf) | Q5_K_S | 1.9 | |
46
  | [GGUF](https://huggingface.co/mradermacher/PrathameshLLM-7B-GGUF/resolve/main/PrathameshLLM-7B.Q5_K_M.gguf) | Q5_K_M | 1.9 | |
47
  | [GGUF](https://huggingface.co/mradermacher/PrathameshLLM-7B-GGUF/resolve/main/PrathameshLLM-7B.Q6_K.gguf) | Q6_K | 2.2 | very good quality |
48
  | [GGUF](https://huggingface.co/mradermacher/PrathameshLLM-7B-GGUF/resolve/main/PrathameshLLM-7B.Q8_0.gguf) | Q8_0 | 2.8 | fast, best quality |
49
 
50
-
51
  Here is a handy graph by ikawrakow comparing some lower-quality quant
52
  types (lower is better):
53
 
 
2
  base_model: pmking27/PrathameshLLM-7B
3
  language:
4
  - en
5
+ - mr
6
+ - hi
7
+ - gu
8
+ - pa
9
+ - te
10
+ - ta
11
+ - ml
12
+ - kn
13
+ - sd
14
+ - ne
15
+ - ur
16
+ - as
17
+ - bn
18
+ - or
19
  library_name: transformers
20
  license: apache-2.0
21
  quantized_by: mradermacher
 
54
  | [GGUF](https://huggingface.co/mradermacher/PrathameshLLM-7B-GGUF/resolve/main/PrathameshLLM-7B.IQ4_XS.gguf) | IQ4_XS | 1.6 | |
55
  | [GGUF](https://huggingface.co/mradermacher/PrathameshLLM-7B-GGUF/resolve/main/PrathameshLLM-7B.Q4_0.gguf) | Q4_0 | 1.7 | fast, low quality |
56
  | [GGUF](https://huggingface.co/mradermacher/PrathameshLLM-7B-GGUF/resolve/main/PrathameshLLM-7B.Q4_K_S.gguf) | Q4_K_S | 1.7 | fast, recommended |
57
+ | [GGUF](https://huggingface.co/mradermacher/PrathameshLLM-7B-GGUF/resolve/main/PrathameshLLM-7B.IQ4_NL.gguf) | IQ4_NL | 1.7 | prefer IQ4_XS |
58
  | [GGUF](https://huggingface.co/mradermacher/PrathameshLLM-7B-GGUF/resolve/main/PrathameshLLM-7B.Q4_K_M.gguf) | Q4_K_M | 1.7 | fast, recommended |
59
  | [GGUF](https://huggingface.co/mradermacher/PrathameshLLM-7B-GGUF/resolve/main/PrathameshLLM-7B.Q5_K_S.gguf) | Q5_K_S | 1.9 | |
60
  | [GGUF](https://huggingface.co/mradermacher/PrathameshLLM-7B-GGUF/resolve/main/PrathameshLLM-7B.Q5_K_M.gguf) | Q5_K_M | 1.9 | |
61
  | [GGUF](https://huggingface.co/mradermacher/PrathameshLLM-7B-GGUF/resolve/main/PrathameshLLM-7B.Q6_K.gguf) | Q6_K | 2.2 | very good quality |
62
  | [GGUF](https://huggingface.co/mradermacher/PrathameshLLM-7B-GGUF/resolve/main/PrathameshLLM-7B.Q8_0.gguf) | Q8_0 | 2.8 | fast, best quality |
63
 
 
64
  Here is a handy graph by ikawrakow comparing some lower-quality quant
65
  types (lower is better):
66