Skip to page content
SAVRN
Search Plan a project

Open-weight model

llmplasticity-zh_nl_linear_8-rand-d0.01-c0.999-r0.2-s42

by Hongao Cisco1963/llmplasticity-zh_nl_linear_8-rand-d0.01-c0.999-r0.2-s42

llmplasticity-zh_nl_linear_8-rand-d0.01-c0.999-r0.2-s42 is an open-weight model from Hongao. It has 123M parameters. At 16-bit it needs about 0.3 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.

Parameters123M
Context—
Weights11.3 GB
License—
AccessOpen weights
Monthly Downloads—

Runs On

What it takes to serve llmplasticity-zh_nl_linear_8-rand-d0.01-c0.999-r0.2-s42 (123M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.

PrecisionWeightsMemory neededCheapest setupPer hourAlso fits
16-bit 0.2 GB 0.3 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00
8-bit 0.1 GB 0.1 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00
4-bit 0.1 GB 0.1 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00

Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Oct 19, 2026.

llmplasticity-zh_nl_linear_8-rand-d0.01-c0.999-r0.2-s42 on every accelerator the SAVRN Index prices, at every precision

Model Card

The publisher has not written a card for this model.

Configuration

Architecture
GPT2LMHeadModel
Vocabulary size
48,000
Model type
gpt2

Identity and Version

Repository
Cisco1963/llmplasticity-zh_nl_linear_8-rand-d0.01-c0.999-r0.2-s42
Publisher
Hongao
Task
Not stated by the source
Modality
Other
Library
Not stated by the source
Parameters
123M parameters
Languages
Not stated by the source
Revision
cc5967060e8396c07fc7ceda76be44e7d0252061
First published
2026-10-13
Last updated
2026-10-13

Files and Weights

208 files, 11.4 GB in total. The weights are 66 files totalling 11.3 GB in bin, pt, safetensors.

Weights66 files · 11.3 GB
Configuration95 files · 178.0 KB
Tokenizer46 files · 89.0 MB
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
checkpoint-1/model.safetensorsWeights490.8 MB 81d46e82e03d
checkpoint-1/training_args.binWeights6.0 KB 0eba3b7c5ea9
checkpoint-1024/model.safetensorsWeights490.8 MB 05c9424fb18d
checkpoint-1024/training_args.binWeights6.0 KB 0eba3b7c5ea9
checkpoint-11200/freeze_state.ptWeights5.1 KB 0dac70d4daa7
checkpoint-11200/frozen_index_map.ptWeights1.4 MB 3e7631031b70
checkpoint-11200/model.safetensorsWeights490.8 MB d07f0e421dd8
checkpoint-11200/training_args.binWeights6.0 KB 926ad2b587fa
checkpoint-128/model.safetensorsWeights490.8 MB ed04c0eec119
checkpoint-128/training_args.binWeights6.0 KB 0eba3b7c5ea9
checkpoint-12800/freeze_state.ptWeights5.1 KB 0dac70d4daa7
checkpoint-12800/frozen_index_map.ptWeights1.4 MB 3e7631031b70
checkpoint-12800/model.safetensorsWeights490.8 MB e5b160776721
checkpoint-12800/training_args.binWeights6.0 KB d24b1dffb2ed
checkpoint-14400/freeze_state.ptWeights5.1 KB 0dac70d4daa7
checkpoint-14400/frozen_index_map.ptWeights1.4 MB 3e7631031b70
checkpoint-14400/model.safetensorsWeights490.8 MB 480155d03730
checkpoint-14400/training_args.binWeights6.0 KB d24b1dffb2ed
checkpoint-16/model.safetensorsWeights490.8 MB 3d62c2a3831b
checkpoint-16/training_args.binWeights6.0 KB 0eba3b7c5ea9
checkpoint-16000/freeze_state.ptWeights5.1 KB 0dac70d4daa7
checkpoint-16000/frozen_index_map.ptWeights1.4 MB 3e7631031b70
checkpoint-16000/model.safetensorsWeights490.8 MB 7bbf55291352
checkpoint-16000/training_args.binWeights6.0 KB d24b1dffb2ed
checkpoint-17600/freeze_state.ptWeights5.1 KB 0dac70d4daa7
checkpoint-17600/frozen_index_map.ptWeights1.4 MB 3e7631031b70
checkpoint-17600/model.safetensorsWeights490.8 MB 7f803e8f1c3e
checkpoint-17600/training_args.binWeights6.0 KB d24b1dffb2ed
checkpoint-19076/freeze_state.ptWeights5.1 KB 0dac70d4daa7
checkpoint-19076/frozen_index_map.ptWeights1.4 MB 3e7631031b70
checkpoint-19076/model.safetensorsWeights490.8 MB a3077cf5644b
checkpoint-19076/training_args.binWeights6.0 KB d24b1dffb2ed
checkpoint-2/model.safetensorsWeights490.8 MB 3a314d5c1f84
checkpoint-2/training_args.binWeights6.0 KB 0eba3b7c5ea9
checkpoint-2048/model.safetensorsWeights490.8 MB 0118ce5d5202
checkpoint-2048/training_args.binWeights6.0 KB 0eba3b7c5ea9
checkpoint-256/model.safetensorsWeights490.8 MB e324d83dacbc
checkpoint-256/training_args.binWeights6.0 KB 0eba3b7c5ea9
checkpoint-32/model.safetensorsWeights490.8 MB d8b306a02b53
checkpoint-32/training_args.binWeights6.0 KB 0eba3b7c5ea9
checkpoint-4/model.safetensorsWeights490.8 MB 756a6efb01aa
checkpoint-4/training_args.binWeights6.0 KB 0eba3b7c5ea9
checkpoint-4800/freeze_state.ptWeights5.1 KB 5b4b8d1eb44f
checkpoint-4800/frozen_index_map.ptWeights1.3 MB fd11c4a7d49e
checkpoint-4800/model.safetensorsWeights490.8 MB e630a309f247
checkpoint-4800/training_args.binWeights6.0 KB 0eba3b7c5ea9
checkpoint-512/model.safetensorsWeights490.8 MB 311f58ede4ed
checkpoint-512/training_args.binWeights6.0 KB 0eba3b7c5ea9
checkpoint-64/model.safetensorsWeights490.8 MB 732389f9d3d6
checkpoint-64/training_args.binWeights6.0 KB 0eba3b7c5ea9
checkpoint-6400/freeze_state.ptWeights5.1 KB 0dac70d4daa7
checkpoint-6400/frozen_index_map.ptWeights1.4 MB 3e7631031b70
checkpoint-6400/model.safetensorsWeights490.8 MB f9be93a9a1fe
checkpoint-6400/training_args.binWeights6.0 KB 0eba3b7c5ea9
checkpoint-8/model.safetensorsWeights490.8 MB 85942e471d5a
checkpoint-8/training_args.binWeights6.0 KB 0eba3b7c5ea9
checkpoint-8000/freeze_state.ptWeights5.1 KB 0dac70d4daa7
checkpoint-8000/frozen_index_map.ptWeights1.4 MB 3e7631031b70
checkpoint-8000/model.safetensorsWeights490.8 MB 10cd006db657
checkpoint-8000/training_args.binWeights6.0 KB 0eba3b7c5ea9
checkpoint-9600/freeze_state.ptWeights5.1 KB 0dac70d4daa7
checkpoint-9600/frozen_index_map.ptWeights1.4 MB 3e7631031b70
checkpoint-9600/model.safetensorsWeights490.8 MB a9444edea83d
checkpoint-9600/training_args.binWeights6.0 KB 0eba3b7c5ea9
model.safetensorsWeights490.8 MB a3077cf5644b
training_args.binWeights6.0 KB d24b1dffb2ed
all_results.jsonConfiguration697 B —
checkpoint-1/config.jsonConfiguration874 B —
checkpoint-1/generation_config.jsonConfiguration119 B —
checkpoint-1/special_tokens_map.jsonConfiguration692 B —
checkpoint-1/trainer_state.jsonConfiguration1.2 KB —
checkpoint-1024/config.jsonConfiguration874 B —
checkpoint-1024/generation_config.jsonConfiguration119 B —
checkpoint-1024/special_tokens_map.jsonConfiguration692 B —
checkpoint-1024/trainer_state.jsonConfiguration5.6 KB —
checkpoint-11200/config.jsonConfiguration874 B —
checkpoint-11200/generation_config.jsonConfiguration119 B —
checkpoint-11200/special_tokens_map.jsonConfiguration692 B —
checkpoint-11200/trainer_state.jsonConfiguration8.2 KB —
checkpoint-128/config.jsonConfiguration874 B —
checkpoint-128/generation_config.jsonConfiguration119 B —
checkpoint-128/special_tokens_map.jsonConfiguration692 B —
checkpoint-128/trainer_state.jsonConfiguration4.3 KB —
checkpoint-12800/config.jsonConfiguration874 B —
checkpoint-12800/generation_config.jsonConfiguration119 B —
checkpoint-12800/special_tokens_map.jsonConfiguration692 B —
checkpoint-12800/trainer_state.jsonConfiguration8.7 KB —
checkpoint-14400/config.jsonConfiguration874 B —
checkpoint-14400/generation_config.jsonConfiguration119 B —
checkpoint-14400/special_tokens_map.jsonConfiguration692 B —
checkpoint-14400/trainer_state.jsonConfiguration9.1 KB —
checkpoint-16/config.jsonConfiguration874 B —
checkpoint-16/generation_config.jsonConfiguration119 B —
checkpoint-16/special_tokens_map.jsonConfiguration692 B —
checkpoint-16/trainer_state.jsonConfiguration3.0 KB —
checkpoint-16000/config.jsonConfiguration874 B —
checkpoint-16000/generation_config.jsonConfiguration119 B —
checkpoint-16000/special_tokens_map.jsonConfiguration692 B —
checkpoint-16000/trainer_state.jsonConfiguration9.5 KB —
checkpoint-17600/config.jsonConfiguration874 B —
checkpoint-17600/generation_config.jsonConfiguration119 B —
checkpoint-17600/special_tokens_map.jsonConfiguration692 B —
checkpoint-17600/trainer_state.jsonConfiguration10.0 KB —
checkpoint-19076/config.jsonConfiguration874 B —
checkpoint-19076/generation_config.jsonConfiguration119 B —
checkpoint-19076/special_tokens_map.jsonConfiguration692 B —
checkpoint-19076/trainer_state.jsonConfiguration10.0 KB —
checkpoint-2/config.jsonConfiguration874 B —
checkpoint-2/generation_config.jsonConfiguration119 B —
checkpoint-2/special_tokens_map.jsonConfiguration692 B —
checkpoint-2/trainer_state.jsonConfiguration1.7 KB —
checkpoint-2048/config.jsonConfiguration874 B —
checkpoint-2048/generation_config.jsonConfiguration119 B —
checkpoint-2048/special_tokens_map.jsonConfiguration692 B —
checkpoint-2048/trainer_state.jsonConfiguration6.0 KB —
checkpoint-256/config.jsonConfiguration874 B —
checkpoint-256/generation_config.jsonConfiguration119 B —
checkpoint-256/special_tokens_map.jsonConfiguration692 B —
checkpoint-256/trainer_state.jsonConfiguration4.7 KB —
checkpoint-32/config.jsonConfiguration874 B —
checkpoint-32/generation_config.jsonConfiguration119 B —
checkpoint-32/special_tokens_map.jsonConfiguration692 B —
checkpoint-32/trainer_state.jsonConfiguration3.4 KB —
checkpoint-4/config.jsonConfiguration874 B —
checkpoint-4/generation_config.jsonConfiguration119 B —
checkpoint-4/special_tokens_map.jsonConfiguration692 B —
checkpoint-4/trainer_state.jsonConfiguration2.1 KB —
checkpoint-4800/config.jsonConfiguration874 B —
checkpoint-4800/generation_config.jsonConfiguration119 B —
checkpoint-4800/special_tokens_map.jsonConfiguration692 B —
checkpoint-4800/trainer_state.jsonConfiguration6.5 KB —
checkpoint-512/config.jsonConfiguration874 B —
checkpoint-512/generation_config.jsonConfiguration119 B —
checkpoint-512/special_tokens_map.jsonConfiguration692 B —
checkpoint-512/trainer_state.jsonConfiguration5.2 KB —
checkpoint-64/config.jsonConfiguration874 B —
checkpoint-64/generation_config.jsonConfiguration119 B —
checkpoint-64/special_tokens_map.jsonConfiguration692 B —
checkpoint-64/trainer_state.jsonConfiguration3.9 KB —
checkpoint-6400/config.jsonConfiguration874 B —
checkpoint-6400/generation_config.jsonConfiguration119 B —
checkpoint-6400/special_tokens_map.jsonConfiguration692 B —
checkpoint-6400/trainer_state.jsonConfiguration6.9 KB —
checkpoint-8/config.jsonConfiguration874 B —
checkpoint-8/generation_config.jsonConfiguration119 B —
checkpoint-8/special_tokens_map.jsonConfiguration692 B —
checkpoint-8/trainer_state.jsonConfiguration2.5 KB —
checkpoint-8000/config.jsonConfiguration874 B —
checkpoint-8000/generation_config.jsonConfiguration119 B —
checkpoint-8000/special_tokens_map.jsonConfiguration692 B —
checkpoint-8000/trainer_state.jsonConfiguration7.4 KB —
checkpoint-9600/config.jsonConfiguration874 B —
checkpoint-9600/generation_config.jsonConfiguration119 B —
checkpoint-9600/special_tokens_map.jsonConfiguration692 B —
checkpoint-9600/trainer_state.jsonConfiguration7.8 KB —
config.jsonConfiguration874 B —
eval_results.jsonConfiguration478 B —
generation_config.jsonConfiguration119 B —
special_tokens_map.jsonConfiguration692 B —
train_results.jsonConfiguration239 B —
trainer_state.jsonConfiguration10.2 KB —
.gitattributesRepository1.5 KB —
checkpoint-1/tokenizer.jsonTokenizer3.9 MB —
checkpoint-1/tokenizer_config.jsonTokenizer1.1 KB —
checkpoint-1024/tokenizer.jsonTokenizer3.9 MB —
checkpoint-1024/tokenizer_config.jsonTokenizer1.1 KB —
checkpoint-11200/tokenizer.jsonTokenizer3.9 MB —
checkpoint-11200/tokenizer_config.jsonTokenizer1.1 KB —
checkpoint-128/tokenizer.jsonTokenizer3.9 MB —
checkpoint-128/tokenizer_config.jsonTokenizer1.1 KB —
checkpoint-12800/tokenizer.jsonTokenizer3.9 MB —
checkpoint-12800/tokenizer_config.jsonTokenizer1.1 KB —
checkpoint-14400/tokenizer.jsonTokenizer3.9 MB —
checkpoint-14400/tokenizer_config.jsonTokenizer1.1 KB —
checkpoint-16/tokenizer.jsonTokenizer3.9 MB —
checkpoint-16/tokenizer_config.jsonTokenizer1.1 KB —
checkpoint-16000/tokenizer.jsonTokenizer3.9 MB —
checkpoint-16000/tokenizer_config.jsonTokenizer1.1 KB —
checkpoint-17600/tokenizer.jsonTokenizer3.9 MB —
checkpoint-17600/tokenizer_config.jsonTokenizer1.1 KB —
checkpoint-19076/tokenizer.jsonTokenizer3.9 MB —
checkpoint-19076/tokenizer_config.jsonTokenizer1.1 KB —
checkpoint-2/tokenizer.jsonTokenizer3.9 MB —
checkpoint-2/tokenizer_config.jsonTokenizer1.1 KB —
checkpoint-2048/tokenizer.jsonTokenizer3.9 MB —
checkpoint-2048/tokenizer_config.jsonTokenizer1.1 KB —
checkpoint-256/tokenizer.jsonTokenizer3.9 MB —
checkpoint-256/tokenizer_config.jsonTokenizer1.1 KB —
checkpoint-32/tokenizer.jsonTokenizer3.9 MB —
checkpoint-32/tokenizer_config.jsonTokenizer1.1 KB —
checkpoint-4/tokenizer.jsonTokenizer3.9 MB —
checkpoint-4/tokenizer_config.jsonTokenizer1.1 KB —
checkpoint-4800/tokenizer.jsonTokenizer3.9 MB —
checkpoint-4800/tokenizer_config.jsonTokenizer1.1 KB —
checkpoint-512/tokenizer.jsonTokenizer3.9 MB —
checkpoint-512/tokenizer_config.jsonTokenizer1.1 KB —
checkpoint-64/tokenizer.jsonTokenizer3.9 MB —
checkpoint-64/tokenizer_config.jsonTokenizer1.1 KB —
checkpoint-6400/tokenizer.jsonTokenizer3.9 MB —
checkpoint-6400/tokenizer_config.jsonTokenizer1.1 KB —
checkpoint-8/tokenizer.jsonTokenizer3.9 MB —
checkpoint-8/tokenizer_config.jsonTokenizer1.1 KB —
checkpoint-8000/tokenizer.jsonTokenizer3.9 MB —
checkpoint-8000/tokenizer_config.jsonTokenizer1.1 KB —
checkpoint-9600/tokenizer.jsonTokenizer3.9 MB —
checkpoint-9600/tokenizer_config.jsonTokenizer1.1 KB —
tokenizer.jsonTokenizer3.9 MB —
tokenizer_config.jsonTokenizer1.1 KB —

License and Download

License
Not stated by the source
Access
Open weights, no gate
Download size
11.3 GB
Download from Hongao

Released by Hongao through its official repository on Hugging Face.

Memory Requirements

PrecisionWeights in memory
As published11.3 GB
16-bit0.2 GB
8-bit0.1 GB
4-bit0.1 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About llmplasticity-zh_nl_linear_8-rand-d0.01-c0.999-r0.2-s42

How much GPU memory does llmplasticity-zh_nl_linear_8-rand-d0.01-c0.999-r0.2-s42 need?

About 0.3 GB at 16-bit and 0.1 GB at 4-bit: the weights (123M parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run llmplasticity-zh_nl_linear_8-rand-d0.01-c0.999-r0.2-s42 on?

At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.