Hugging Face's logo

mradermacher
/
lb-reranker-0.5B-v1.0-GGUF

Transformers
GGUF
reranker
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
172713f
·
verified ·
1 Parent(s): b9381fb

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +157 -0
README.md CHANGED
@@ -1,6 +1,163 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 2 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: hf -->
4
  <!-- ### vocab_type: -->
5
  <!-- ### tags: -->
6
  static quants of https://huggingface.co/lightblue/lb-reranker-0.5B-v1.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: lightblue/lb-reranker-0.5B-v1.0
3
+ datasets:
4
+ - lightblue/reranker_continuous_filt_max7_train
5
+ language:
6
+ - en
7
+ - zh
8
+ - es
9
+ - de
10
+ - ar
11
+ - ru
12
+ - ja
13
+ - ko
14
+ - hi
15
+ - sk
16
+ - vi
17
+ - tr
18
+ - fi
19
+ - id
20
+ - fa
21
+ - no
22
+ - th
23
+ - sv
24
+ - pt
25
+ - da
26
+ - bn
27
+ - te
28
+ - ro
29
+ - it
30
+ - fr
31
+ - nl
32
+ - sw
33
+ - pl
34
+ - hu
35
+ - cs
36
+ - el
37
+ - uk
38
+ - mr
39
+ - ta
40
+ - tl
41
+ - bg
42
+ - lt
43
+ - ur
44
+ - he
45
+ - gu
46
+ - kn
47
+ - am
48
+ - kk
49
+ - hr
50
+ - uz
51
+ - jv
52
+ - ca
53
+ - az
54
+ - ms
55
+ - sr
56
+ - sl
57
+ - yo
58
+ - lv
59
+ - is
60
+ - ha
61
+ - ka
62
+ - et
63
+ - bs
64
+ - hy
65
+ - ml
66
+ - pa
67
+ - mt
68
+ - km
69
+ - sq
70
+ - or
71
+ - as
72
+ - my
73
+ - mn
74
+ - af
75
+ - be
76
+ - ga
77
+ - mk
78
+ - cy
79
+ - gl
80
+ - ceb
81
+ - la
82
+ - yi
83
+ - lb
84
+ - tg
85
+ - gd
86
+ - ne
87
+ - ps
88
+ - eu
89
+ - ky
90
+ - ku
91
+ - si
92
+ - ht
93
+ - eo
94
+ - lo
95
+ - fy
96
+ - sd
97
+ - mg
98
+ - so
99
+ - ckb
100
+ - su
101
+ - nn
102
+ library_name: transformers
103
+ license: apache-2.0
104
+ quantized_by: mradermacher
105
+ tags:
106
+ - reranker
107
+ ---
108
+ ## About
109
+
110
  <!-- ### quantize_version: 2 -->
111
  <!-- ### output_tensor_quantised: 1 -->
112
  <!-- ### convert_type: hf -->
113
  <!-- ### vocab_type: -->
114
  <!-- ### tags: -->
115
  static quants of https://huggingface.co/lightblue/lb-reranker-0.5B-v1.0
116
+
117
+ <!-- provided-files -->
118
+ 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.
119
+ ## Usage
120
+
121
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
122
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
123
+ more details, including on how to concatenate multi-part files.
124
+
125
+ ## Provided Quants
126
+
127
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
128
+
129
+ | Link | Type | Size/GB | Notes |
130
+ |:-----|:-----|--------:|:------|
131
+ | [GGUF](https://huggingface.co/mradermacher/lb-reranker-0.5B-v1.0-GGUF/resolve/main/lb-reranker-0.5B-v1.0.Q3_K_S.gguf) | Q3_K_S | 0.4 | |
132
+ | [GGUF](https://huggingface.co/mradermacher/lb-reranker-0.5B-v1.0-GGUF/resolve/main/lb-reranker-0.5B-v1.0.Q2_K.gguf) | Q2_K | 0.4 | |
133
+ | [GGUF](https://huggingface.co/mradermacher/lb-reranker-0.5B-v1.0-GGUF/resolve/main/lb-reranker-0.5B-v1.0.IQ4_XS.gguf) | IQ4_XS | 0.5 | |
134
+ | [GGUF](https://huggingface.co/mradermacher/lb-reranker-0.5B-v1.0-GGUF/resolve/main/lb-reranker-0.5B-v1.0.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality |
135
+ | [GGUF](https://huggingface.co/mradermacher/lb-reranker-0.5B-v1.0-GGUF/resolve/main/lb-reranker-0.5B-v1.0.Q3_K_L.gguf) | Q3_K_L | 0.5 | |
136
+ | [GGUF](https://huggingface.co/mradermacher/lb-reranker-0.5B-v1.0-GGUF/resolve/main/lb-reranker-0.5B-v1.0.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended |
137
+ | [GGUF](https://huggingface.co/mradermacher/lb-reranker-0.5B-v1.0-GGUF/resolve/main/lb-reranker-0.5B-v1.0.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended |
138
+ | [GGUF](https://huggingface.co/mradermacher/lb-reranker-0.5B-v1.0-GGUF/resolve/main/lb-reranker-0.5B-v1.0.Q5_K_S.gguf) | Q5_K_S | 0.5 | |
139
+ | [GGUF](https://huggingface.co/mradermacher/lb-reranker-0.5B-v1.0-GGUF/resolve/main/lb-reranker-0.5B-v1.0.Q5_K_M.gguf) | Q5_K_M | 0.5 | |
140
+ | [GGUF](https://huggingface.co/mradermacher/lb-reranker-0.5B-v1.0-GGUF/resolve/main/lb-reranker-0.5B-v1.0.Q6_K.gguf) | Q6_K | 0.6 | very good quality |
141
+ | [GGUF](https://huggingface.co/mradermacher/lb-reranker-0.5B-v1.0-GGUF/resolve/main/lb-reranker-0.5B-v1.0.Q8_0.gguf) | Q8_0 | 0.6 | fast, best quality |
142
+ | [GGUF](https://huggingface.co/mradermacher/lb-reranker-0.5B-v1.0-GGUF/resolve/main/lb-reranker-0.5B-v1.0.f16.gguf) | f16 | 1.1 | 16 bpw, overkill |
143
+
144
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
145
+ types (lower is better):
146
+
147
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
148
+
149
+ And here are Artefact2's thoughts on the matter:
150
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
151
+
152
+ ## FAQ / Model Request
153
+
154
+ See https://huggingface.co/mradermacher/model_requests for some answers to
155
+ questions you might have and/or if you want some other model quantized.
156
+
157
+ ## Thanks
158
+
159
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
160
+ me use its servers and providing upgrades to my workstation to enable
161
+ this work in my free time.
162
+
163
+ <!-- end -->