mradermacher commited on
Commit
9027ded
·
verified ·
1 Parent(s): 09fddf3

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +117 -0
README.md CHANGED
@@ -1,6 +1,123 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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/Weyaxi/Einstein-v4-phi2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Weyaxi/Einstein-v4-phi2
3
+ datasets:
4
+ - allenai/ai2_arc
5
+ - camel-ai/physics
6
+ - camel-ai/chemistry
7
+ - camel-ai/biology
8
+ - camel-ai/math
9
+ - metaeval/reclor
10
+ - openbookqa
11
+ - mandyyyyii/scibench
12
+ - derek-thomas/ScienceQA
13
+ - TIGER-Lab/ScienceEval
14
+ - jondurbin/airoboros-3.2
15
+ - LDJnr/Capybara
16
+ - Cot-Alpaca-GPT4-From-OpenHermes-2.5
17
+ - STEM-AI-mtl/Electrical-engineering
18
+ - knowrohit07/saraswati-stem
19
+ - sablo/oasst2_curated
20
+ - glaiveai/glaive-code-assistant
21
+ - lmsys/lmsys-chat-1m
22
+ - TIGER-Lab/MathInstruct
23
+ - bigbio/med_qa
24
+ - meta-math/MetaMathQA-40K
25
+ - openbookqa
26
+ - piqa
27
+ - metaeval/reclor
28
+ - derek-thomas/ScienceQA
29
+ - scibench
30
+ - sciq
31
+ - Open-Orca/SlimOrca
32
+ - migtissera/Synthia-v1.3
33
+ - TIGER-Lab/ScienceEval
34
+ language:
35
+ - en
36
+ library_name: transformers
37
+ license: other
38
+ quantized_by: mradermacher
39
+ tags:
40
+ - axolotl
41
+ - generated_from_trainer
42
+ - phi
43
+ - phi2
44
+ - einstein
45
+ - instruct
46
+ - finetune
47
+ - chatml
48
+ - gpt4
49
+ - synthetic data
50
+ - science
51
+ - physics
52
+ - chemistry
53
+ - biology
54
+ - math
55
+ ---
56
+ ## About
57
+
58
  <!-- ### quantize_version: 2 -->
59
  <!-- ### output_tensor_quantised: 1 -->
60
  <!-- ### convert_type: hf -->
61
  <!-- ### vocab_type: -->
62
  <!-- ### tags: nicoboss -->
63
  weighted/imatrix quants of https://huggingface.co/Weyaxi/Einstein-v4-phi2
64
+
65
+ <!-- provided-files -->
66
+ static quants are available at https://huggingface.co/mradermacher/Einstein-v4-phi2-GGUF
67
+ ## Usage
68
+
69
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
70
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
71
+ more details, including on how to concatenate multi-part files.
72
+
73
+ ## Provided Quants
74
+
75
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
76
+
77
+ | Link | Type | Size/GB | Notes |
78
+ |:-----|:-----|--------:|:------|
79
+ | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-phi2-i1-GGUF/resolve/main/Einstein-v4-phi2.i1-IQ1_S.gguf) | i1-IQ1_S | 0.8 | for the desperate |
80
+ | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-phi2-i1-GGUF/resolve/main/Einstein-v4-phi2.i1-IQ1_M.gguf) | i1-IQ1_M | 0.8 | mostly desperate |
81
+ | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-phi2-i1-GGUF/resolve/main/Einstein-v4-phi2.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.9 | |
82
+ | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-phi2-i1-GGUF/resolve/main/Einstein-v4-phi2.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.0 | |
83
+ | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-phi2-i1-GGUF/resolve/main/Einstein-v4-phi2.i1-IQ2_S.gguf) | i1-IQ2_S | 1.1 | |
84
+ | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-phi2-i1-GGUF/resolve/main/Einstein-v4-phi2.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.1 | very low quality |
85
+ | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-phi2-i1-GGUF/resolve/main/Einstein-v4-phi2.i1-IQ2_M.gguf) | i1-IQ2_M | 1.1 | |
86
+ | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-phi2-i1-GGUF/resolve/main/Einstein-v4-phi2.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.2 | lower quality |
87
+ | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-phi2-i1-GGUF/resolve/main/Einstein-v4-phi2.i1-Q2_K.gguf) | i1-Q2_K | 1.2 | IQ3_XXS probably better |
88
+ | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-phi2-i1-GGUF/resolve/main/Einstein-v4-phi2.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.3 | |
89
+ | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-phi2-i1-GGUF/resolve/main/Einstein-v4-phi2.i1-IQ3_S.gguf) | i1-IQ3_S | 1.4 | beats Q3_K* |
90
+ | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-phi2-i1-GGUF/resolve/main/Einstein-v4-phi2.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.4 | IQ3_XS probably better |
91
+ | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-phi2-i1-GGUF/resolve/main/Einstein-v4-phi2.i1-IQ3_M.gguf) | i1-IQ3_M | 1.4 | |
92
+ | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-phi2-i1-GGUF/resolve/main/Einstein-v4-phi2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.5 | IQ3_S probably better |
93
+ | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-phi2-i1-GGUF/resolve/main/Einstein-v4-phi2.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.6 | |
94
+ | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-phi2-i1-GGUF/resolve/main/Einstein-v4-phi2.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.7 | IQ3_M probably better |
95
+ | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-phi2-i1-GGUF/resolve/main/Einstein-v4-phi2.i1-IQ4_NL.gguf) | i1-IQ4_NL | 1.7 | prefer IQ4_XS |
96
+ | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-phi2-i1-GGUF/resolve/main/Einstein-v4-phi2.i1-Q4_0.gguf) | i1-Q4_0 | 1.7 | fast, low quality |
97
+ | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-phi2-i1-GGUF/resolve/main/Einstein-v4-phi2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.7 | optimal size/speed/quality |
98
+ | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-phi2-i1-GGUF/resolve/main/Einstein-v4-phi2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 1.8 | fast, recommended |
99
+ | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-phi2-i1-GGUF/resolve/main/Einstein-v4-phi2.i1-Q4_1.gguf) | i1-Q4_1 | 1.9 | |
100
+ | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-phi2-i1-GGUF/resolve/main/Einstein-v4-phi2.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.0 | |
101
+ | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-phi2-i1-GGUF/resolve/main/Einstein-v4-phi2.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.1 | |
102
+ | [GGUF](https://huggingface.co/mradermacher/Einstein-v4-phi2-i1-GGUF/resolve/main/Einstein-v4-phi2.i1-Q6_K.gguf) | i1-Q6_K | 2.4 | practically like static Q6_K |
103
+
104
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
105
+ types (lower is better):
106
+
107
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
108
+
109
+ And here are Artefact2's thoughts on the matter:
110
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
111
+
112
+ ## FAQ / Model Request
113
+
114
+ See https://huggingface.co/mradermacher/model_requests for some answers to
115
+ questions you might have and/or if you want some other model quantized.
116
+
117
+ ## Thanks
118
+
119
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
120
+ me use its servers and providing upgrades to my workstation to enable
121
+ 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.
122
+
123
+ <!-- end -->