Hugging Face's logo

mradermacher
/
Indic-gemma-7b-finetuned-sft-Navarasa-2.0-i1-GGUF

Transformers
GGUF
Inference Endpoints
imatrix
Model card Files Community
mradermacher commited on
Commit
a192c28
•
1 Parent(s): 36b08da

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +106 -0
README.md CHANGED
@@ -1,6 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 2 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: hf -->
4
  <!-- ### vocab_type: -->
5
  <!-- ### tags: nicoboss -->
6
  weighted/imatrix quants of https://huggingface.co/Telugu-LLM-Labs/Indic-gemma-7b-finetuned-sft-Navarasa-2.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Telugu-LLM-Labs/Indic-gemma-7b-finetuned-sft-Navarasa-2.0
3
+ datasets:
4
+ - ravithejads/samvaad-hi-filtered
5
+ - Telugu-LLM-Labs/telugu_teknium_GPTeacher_general_instruct_filtered_romanized
6
+ - Telugu-LLM-Labs/telugu_alpaca_yahma_cleaned_filtered_romanized
7
+ - Telugu-LLM-Labs/sindhi_alpaca_yahma_cleaned_filtered
8
+ - Telugu-LLM-Labs/urdu_alpaca_yahma_cleaned_filtered
9
+ - Telugu-LLM-Labs/marathi_alpaca_yahma_cleaned_filtered
10
+ - Telugu-LLM-Labs/assamese_alpaca_yahma_cleaned_filtered
11
+ - Telugu-LLM-Labs/konkani_alpaca_yahma_cleaned_filtered
12
+ - Telugu-LLM-Labs/nepali_alpaca_yahma_cleaned_filtered
13
+ - abhinand/tamil-alpaca
14
+ - Tensoic/airoboros-3.2_kn
15
+ - Tensoic/gpt-teacher_kn
16
+ - VishnuPJ/Alpaca_Instruct_Malayalam
17
+ - Tensoic/Alpaca-Gujarati
18
+ - HydraIndicLM/punjabi_alpaca_52K
19
+ - HydraIndicLM/bengali_alpaca_dolly_67k
20
+ - OdiaGenAI/Odia_Alpaca_instructions_52k
21
+ - yahma/alpaca-cleaned
22
+ language:
23
+ - te
24
+ - en
25
+ - ta
26
+ - ml
27
+ - mr
28
+ - hi
29
+ - kn
30
+ - sd
31
+ - ne
32
+ - ur
33
+ - as
34
+ - gu
35
+ - bn
36
+ - pa
37
+ - or
38
+ library_name: transformers
39
+ license: other
40
+ license_link: https://ai.google.dev/gemma/terms
41
+ license_name: gemma-terms-of-use
42
+ quantized_by: mradermacher
43
+ ---
44
+ ## About
45
+
46
  <!-- ### quantize_version: 2 -->
47
  <!-- ### output_tensor_quantised: 1 -->
48
  <!-- ### convert_type: hf -->
49
  <!-- ### vocab_type: -->
50
  <!-- ### tags: nicoboss -->
51
  weighted/imatrix quants of https://huggingface.co/Telugu-LLM-Labs/Indic-gemma-7b-finetuned-sft-Navarasa-2.0
52
+
53
+ <!-- provided-files -->
54
+ static quants are available at https://huggingface.co/mradermacher/Indic-gemma-7b-finetuned-sft-Navarasa-2.0-GGUF
55
+ ## Usage
56
+
57
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
58
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
59
+ more details, including on how to concatenate multi-part files.
60
+
61
+ ## Provided Quants
62
+
63
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
64
+
65
+ | Link | Type | Size/GB | Notes |
66
+ |:-----|:-----|--------:|:------|
67
+ | [GGUF](https://huggingface.co/mradermacher/Indic-gemma-7b-finetuned-sft-Navarasa-2.0-i1-GGUF/resolve/main/Indic-gemma-7b-finetuned-sft-Navarasa-2.0.i1-IQ1_S.gguf) | i1-IQ1_S | 2.3 | for the desperate |
68
+ | [GGUF](https://huggingface.co/mradermacher/Indic-gemma-7b-finetuned-sft-Navarasa-2.0-i1-GGUF/resolve/main/Indic-gemma-7b-finetuned-sft-Navarasa-2.0.i1-IQ1_M.gguf) | i1-IQ1_M | 2.4 | mostly desperate |
69
+ | [GGUF](https://huggingface.co/mradermacher/Indic-gemma-7b-finetuned-sft-Navarasa-2.0-i1-GGUF/resolve/main/Indic-gemma-7b-finetuned-sft-Navarasa-2.0.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.7 | |
70
+ | [GGUF](https://huggingface.co/mradermacher/Indic-gemma-7b-finetuned-sft-Navarasa-2.0-i1-GGUF/resolve/main/Indic-gemma-7b-finetuned-sft-Navarasa-2.0.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.9 | |
71
+ | [GGUF](https://huggingface.co/mradermacher/Indic-gemma-7b-finetuned-sft-Navarasa-2.0-i1-GGUF/resolve/main/Indic-gemma-7b-finetuned-sft-Navarasa-2.0.i1-IQ2_S.gguf) | i1-IQ2_S | 3.0 | |
72
+ | [GGUF](https://huggingface.co/mradermacher/Indic-gemma-7b-finetuned-sft-Navarasa-2.0-i1-GGUF/resolve/main/Indic-gemma-7b-finetuned-sft-Navarasa-2.0.i1-IQ2_M.gguf) | i1-IQ2_M | 3.2 | |
73
+ | [GGUF](https://huggingface.co/mradermacher/Indic-gemma-7b-finetuned-sft-Navarasa-2.0-i1-GGUF/resolve/main/Indic-gemma-7b-finetuned-sft-Navarasa-2.0.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.3 | very low quality |
74
+ | [GGUF](https://huggingface.co/mradermacher/Indic-gemma-7b-finetuned-sft-Navarasa-2.0-i1-GGUF/resolve/main/Indic-gemma-7b-finetuned-sft-Navarasa-2.0.i1-Q2_K.gguf) | i1-Q2_K | 3.6 | IQ3_XXS probably better |
75
+ | [GGUF](https://huggingface.co/mradermacher/Indic-gemma-7b-finetuned-sft-Navarasa-2.0-i1-GGUF/resolve/main/Indic-gemma-7b-finetuned-sft-Navarasa-2.0.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.6 | lower quality |
76
+ | [GGUF](https://huggingface.co/mradermacher/Indic-gemma-7b-finetuned-sft-Navarasa-2.0-i1-GGUF/resolve/main/Indic-gemma-7b-finetuned-sft-Navarasa-2.0.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.9 | |
77
+ | [GGUF](https://huggingface.co/mradermacher/Indic-gemma-7b-finetuned-sft-Navarasa-2.0-i1-GGUF/resolve/main/Indic-gemma-7b-finetuned-sft-Navarasa-2.0.i1-IQ3_S.gguf) | i1-IQ3_S | 4.1 | beats Q3_K* |
78
+ | [GGUF](https://huggingface.co/mradermacher/Indic-gemma-7b-finetuned-sft-Navarasa-2.0-i1-GGUF/resolve/main/Indic-gemma-7b-finetuned-sft-Navarasa-2.0.i1-Q3_K_S.gguf) | i1-Q3_K_S | 4.1 | IQ3_XS probably better |
79
+ | [GGUF](https://huggingface.co/mradermacher/Indic-gemma-7b-finetuned-sft-Navarasa-2.0-i1-GGUF/resolve/main/Indic-gemma-7b-finetuned-sft-Navarasa-2.0.i1-IQ3_M.gguf) | i1-IQ3_M | 4.2 | |
80
+ | [GGUF](https://huggingface.co/mradermacher/Indic-gemma-7b-finetuned-sft-Navarasa-2.0-i1-GGUF/resolve/main/Indic-gemma-7b-finetuned-sft-Navarasa-2.0.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.5 | IQ3_S probably better |
81
+ | [GGUF](https://huggingface.co/mradermacher/Indic-gemma-7b-finetuned-sft-Navarasa-2.0-i1-GGUF/resolve/main/Indic-gemma-7b-finetuned-sft-Navarasa-2.0.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.8 | IQ3_M probably better |
82
+ | [GGUF](https://huggingface.co/mradermacher/Indic-gemma-7b-finetuned-sft-Navarasa-2.0-i1-GGUF/resolve/main/Indic-gemma-7b-finetuned-sft-Navarasa-2.0.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.9 | |
83
+ | [GGUF](https://huggingface.co/mradermacher/Indic-gemma-7b-finetuned-sft-Navarasa-2.0-i1-GGUF/resolve/main/Indic-gemma-7b-finetuned-sft-Navarasa-2.0.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 5.1 | fast on arm, low quality |
84
+ | [GGUF](https://huggingface.co/mradermacher/Indic-gemma-7b-finetuned-sft-Navarasa-2.0-i1-GGUF/resolve/main/Indic-gemma-7b-finetuned-sft-Navarasa-2.0.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 5.1 | fast on arm+i8mm, low quality |
85
+ | [GGUF](https://huggingface.co/mradermacher/Indic-gemma-7b-finetuned-sft-Navarasa-2.0-i1-GGUF/resolve/main/Indic-gemma-7b-finetuned-sft-Navarasa-2.0.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 5.1 | fast on arm+sve, low quality |
86
+ | [GGUF](https://huggingface.co/mradermacher/Indic-gemma-7b-finetuned-sft-Navarasa-2.0-i1-GGUF/resolve/main/Indic-gemma-7b-finetuned-sft-Navarasa-2.0.i1-Q4_0.gguf) | i1-Q4_0 | 5.1 | fast, low quality |
87
+ | [GGUF](https://huggingface.co/mradermacher/Indic-gemma-7b-finetuned-sft-Navarasa-2.0-i1-GGUF/resolve/main/Indic-gemma-7b-finetuned-sft-Navarasa-2.0.i1-Q4_K_S.gguf) | i1-Q4_K_S | 5.1 | optimal size/speed/quality |
88
+ | [GGUF](https://huggingface.co/mradermacher/Indic-gemma-7b-finetuned-sft-Navarasa-2.0-i1-GGUF/resolve/main/Indic-gemma-7b-finetuned-sft-Navarasa-2.0.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.4 | fast, recommended |
89
+ | [GGUF](https://huggingface.co/mradermacher/Indic-gemma-7b-finetuned-sft-Navarasa-2.0-i1-GGUF/resolve/main/Indic-gemma-7b-finetuned-sft-Navarasa-2.0.i1-Q5_K_S.gguf) | i1-Q5_K_S | 6.1 | |
90
+ | [GGUF](https://huggingface.co/mradermacher/Indic-gemma-7b-finetuned-sft-Navarasa-2.0-i1-GGUF/resolve/main/Indic-gemma-7b-finetuned-sft-Navarasa-2.0.i1-Q5_K_M.gguf) | i1-Q5_K_M | 6.2 | |
91
+ | [GGUF](https://huggingface.co/mradermacher/Indic-gemma-7b-finetuned-sft-Navarasa-2.0-i1-GGUF/resolve/main/Indic-gemma-7b-finetuned-sft-Navarasa-2.0.i1-Q6_K.gguf) | i1-Q6_K | 7.1 | practically like static Q6_K |
92
+
93
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
94
+ types (lower is better):
95
+
96
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
97
+
98
+ And here are Artefact2's thoughts on the matter:
99
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
100
+
101
+ ## FAQ / Model Request
102
+
103
+ See https://huggingface.co/mradermacher/model_requests for some answers to
104
+ questions you might have and/or if you want some other model quantized.
105
+
106
+ ## Thanks
107
+
108
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
109
+ me use its servers and providing upgrades to my workstation to enable
110
+ this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
111
+
112
+ <!-- end -->