1.43 TB
149 files
Updated 8 days ago
Name
Size
.eval_results
InternScience_MLExpert-bf16
data
layouts
.gitattributes2.19 kB
xet
All_charts.jpg140 kB
xet
IS-LM-3B.IQ4_XS.gguf1.54 GB
xet
IS-LM-3B.Q2_K.gguf1.08 GB
xet
IS-LM-3B.Q3_K_L.gguf1.51 GB
xet
IS-LM-3B.Q3_K_M.gguf1.39 GB
xet
IS-LM-3B.Q3_K_S.gguf1.25 GB
xet
IS-LM-3B.Q4_K_M.gguf1.71 GB
xet
IS-LM-3B.Q4_K_S.gguf1.62 GB
xet
IS-LM-3B.Q5_K_M.gguf1.99 GB
xet
IS-LM-3B.Q5_K_S.gguf1.94 GB
xet
IS-LM-3B.Q6_K.gguf2.3 GB
xet
IS-LM-3B.Q8_0.gguf2.97 GB
xet
IS-LM-3B.f16.gguf5.59 GB
xet
InternScience_MLExpert-IQ2_M.gguf13.2 GB
xet
InternScience_MLExpert-IQ2_S.gguf12 GB
xet
InternScience_MLExpert-IQ2_XS.gguf11.3 GB
xet
InternScience_MLExpert-IQ2_XXS.gguf10.8 GB
xet
InternScience_MLExpert-IQ3_M.gguf19 GB
xet
InternScience_MLExpert-IQ3_XS.gguf16.3 GB
xet
InternScience_MLExpert-IQ3_XXS.gguf15.6 GB
xet
InternScience_MLExpert-IQ4_NL.gguf22.3 GB
xet
InternScience_MLExpert-IQ4_XS.gguf19.9 GB
xet
InternScience_MLExpert-Q2_K.gguf13.8 GB
xet
InternScience_MLExpert-Q3_K_L.gguf18.3 GB
xet
InternScience_MLExpert-Q3_K_M.gguf17.3 GB
xet
InternScience_MLExpert-Q3_K_S.gguf16.3 GB
xet
InternScience_MLExpert-Q4_0.gguf19.9 GB
xet
InternScience_MLExpert-Q4_1.gguf22 GB
xet
InternScience_MLExpert-Q4_K_L.gguf24.1 GB
xet
InternScience_MLExpert-Q4_K_M.gguf22.3 GB
xet
InternScience_MLExpert-Q4_K_S.gguf20.9 GB
xet
InternScience_MLExpert-Q5_K_M.gguf27 GB
xet
InternScience_MLExpert-Q5_K_S.gguf25.1 GB
xet
InternScience_MLExpert-Q6_K.gguf30.7 GB
xet
InternScience_MLExpert-Q6_K_L.gguf32.3 GB
xet
InternScience_MLExpert-Q6_K_S.gguf29.4 GB
xet
InternScience_MLExpert-Q8_0.gguf36.9 GB
xet
InternScience_MLExpert-calibration-v6.txt1.18 MB
xet
InternScience_MLExpert-imatrix.gguf384 MB
xet
LICENSE2.62 kB
xet
README.md3.01 kB
xet
__init__.py141 Bytes
xet
added_tokens.json707 Bytes
xet
all_results.json201 Bytes
xet
chat_template.jinja8.35 kB
xet
config.json729 Bytes
xet
configuration_afmoe.py4.75 kB
xet
generation_config.json214 Bytes
xet
merges.txt1.67 MB
xet
model-00001-of-00004.safetensors4.9 GB
xet
model-00001-of-00006.safetensors4.98 GB
xet
model-00001-of-00031.safetensors2.46 GB
xet
model-00002-of-00004.safetensors4.92 GB
xet
model-00002-of-00006.safetensors4.98 GB
xet
model-00002-of-00031.safetensors705 MB
xet
model-00003-of-00004.safetensors4.98 GB
xet
model-00003-of-00006.safetensors4.93 GB
xet
model-00003-of-00031.safetensors705 MB
xet
model-00004-of-00004.safetensors1.58 GB
xet
model-00004-of-00006.safetensors4.98 GB
xet
model-00004-of-00031.safetensors705 MB
xet
model-00005-of-00006.safetensors4.93 GB
xet
model-00005-of-00031.safetensors29.4 GB
xet
model-00006-of-00006.safetensors4.73 GB
xet
model-00006-of-00031.safetensors29.4 GB
xet
model-00007-of-00031.safetensors29.4 GB
xet
model-00008-of-00031.safetensors29.4 GB
xet
model-00009-of-00031.safetensors29.4 GB
xet
model-00010-of-00031.safetensors29.4 GB
xet
model-00011-of-00031.safetensors29.4 GB
xet
model-00012-of-00031.safetensors29.4 GB
xet
model-00013-of-00031.safetensors29.4 GB
xet
model-00014-of-00031.safetensors29.4 GB
xet
model-00015-of-00031.safetensors29.4 GB
xet
model-00016-of-00031.safetensors29.4 GB
xet
model-00017-of-00031.safetensors29.4 GB
xet
model-00018-of-00031.safetensors29.4 GB
xet
model-00019-of-00031.safetensors29.4 GB
xet
model-00020-of-00031.safetensors29.4 GB
xet
model-00021-of-00031.safetensors29.4 GB
xet
model-00022-of-00031.safetensors29.4 GB
xet
model-00023-of-00031.safetensors29.4 GB
xet
model-00024-of-00031.safetensors29.4 GB
xet
model-00025-of-00031.safetensors29.4 GB
xet
model-00026-of-00031.safetensors29.4 GB
xet
model-00027-of-00031.safetensors29.4 GB
xet
model-00028-of-00031.safetensors29.4 GB
xet
model-00029-of-00031.safetensors29.4 GB
xet
model-00030-of-00031.safetensors29.4 GB
xet
model-00031-of-00031.safetensors29.4 GB
xet
model.safetensors.index.json36.5 kB
xet
modeling_afmoe.py26.6 kB
xet
special_tokens_map.json613 Bytes
xet
tokenizer.json11.4 MB
xet
tokenizer_config.json9.71 kB
xet
README.md

About

static quants of https://huggingface.co/acrastt/IS-LM-3B

Usage

If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files.

Provided Quants

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Link Type Size/GB Notes
GGUF Q2_K 1.2
GGUF Q3_K_S 1.4
GGUF Q3_K_M 1.5 lower quality
GGUF Q3_K_L 1.6
GGUF IQ4_XS 1.6
GGUF Q4_K_S 1.7 fast, recommended
GGUF Q4_K_M 1.8 fast, recommended
GGUF Q5_K_S 2.0
GGUF Q5_K_M 2.1
GGUF Q6_K 2.4 very good quality
GGUF Q8_0 3.1 fast, best quality
GGUF f16 5.7 16 bpw, overkill

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):

image.png

And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

FAQ / Model Request

See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized.

Thanks

I thank my company, nethype GmbH, for letting me use its servers and providing upgrades to my workstation to enable this work in my free time.

Total size
1.43 TB
Files
149
Last updated
Oct 27
Pre-warmed CDN
US EU US EU

Contributors