Open-weight model
llmplasticity-en_zh_linear_8-d0.01-c0.9-r0.8-s42
by Hongao Cisco1963/llmplasticity-en_zh_linear_8-d0.01-c0.9-r0.8-s42
llmplasticity-en_zh_linear_8-d0.01-c0.9-r0.8-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.
Runs On
What it takes to serve llmplasticity-en_zh_linear_8-d0.01-c0.9-r0.8-s42 (123M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also 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.
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-en_zh_linear_8-d0.01-c0.9-r0.8-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
- ccc24bdba76e2e8b2fa877461212571850e95a28
- First published
- 2026-09-29
- Last updated
- 2026-09-29
Files and Weights
155 files, 9.9 GB in total. The weights are 43 files totalling 9.8 GB in bin, pt, pth, safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| checkpoint-1/model.safetensors | Weights | 490.8 MB | a555ffe5e61e |
| checkpoint-1/training_args.bin | Weights | 6.0 KB | c8b369e9e92d |
| checkpoint-1024/model.safetensors | Weights | 490.8 MB | e6c4d4f0cea2 |
| checkpoint-1024/training_args.bin | Weights | 6.0 KB | c8b369e9e92d |
| checkpoint-128/model.safetensors | Weights | 490.8 MB | 9e1710d6451a |
| checkpoint-128/training_args.bin | Weights | 6.0 KB | c8b369e9e92d |
| checkpoint-16/model.safetensors | Weights | 490.8 MB | 6b0d690208f3 |
| checkpoint-16/training_args.bin | Weights | 6.0 KB | c8b369e9e92d |
| checkpoint-16000/frozen_index_map.pt | Weights | 1.2 MB | 5f0222597bac |
| checkpoint-16000/model.safetensors | Weights | 490.8 MB | af7be9902da1 |
| checkpoint-16000/training_args.bin | Weights | 6.0 KB | c8b369e9e92d |
| checkpoint-17600/frozen_index_map.pt | Weights | 1.2 MB | 0cecec429a23 |
| checkpoint-17600/model.safetensors | Weights | 490.8 MB | 05d8cbe5f97e |
| checkpoint-17600/training_args.bin | Weights | 6.0 KB | c8b369e9e92d |
| checkpoint-18580/frozen_index_map.pt | Weights | 1.2 MB | 0cecec429a23 |
| checkpoint-18580/model.safetensors | Weights | 490.8 MB | b9d59900bdad |
| checkpoint-18580/optimizer.pt | Weights | 981.8 MB | 1db5696d367f |
| checkpoint-18580/rng_state.pth | Weights | 14.6 KB | 36a381e185e2 |
| checkpoint-18580/scaler.pt | Weights | 1.4 KB | a66c38ecd9c1 |
| checkpoint-18580/scheduler.pt | Weights | 1.5 KB | b859a21ab11a |
| checkpoint-18580/training_args.bin | Weights | 6.0 KB | c8b369e9e92d |
| checkpoint-2/model.safetensors | Weights | 490.8 MB | 0bbda9739c15 |
| checkpoint-2/training_args.bin | Weights | 6.0 KB | c8b369e9e92d |
| checkpoint-2048/model.safetensors | Weights | 490.8 MB | 25227f8c19c9 |
| checkpoint-2048/training_args.bin | Weights | 6.0 KB | c8b369e9e92d |
| checkpoint-256/model.safetensors | Weights | 490.8 MB | 35722b391b5b |
| checkpoint-256/training_args.bin | Weights | 6.0 KB | c8b369e9e92d |
| checkpoint-32/model.safetensors | Weights | 490.8 MB | f039e46cd22a |
| checkpoint-32/training_args.bin | Weights | 6.0 KB | c8b369e9e92d |
| checkpoint-4/model.safetensors | Weights | 490.8 MB | e9c82675424f |
| checkpoint-4/training_args.bin | Weights | 6.0 KB | c8b369e9e92d |
| checkpoint-4096/model.safetensors | Weights | 490.8 MB | 24e2c056771b |
| checkpoint-4096/training_args.bin | Weights | 6.0 KB | c8b369e9e92d |
| checkpoint-512/model.safetensors | Weights | 490.8 MB | 2b9f33e2f90f |
| checkpoint-512/training_args.bin | Weights | 6.0 KB | c8b369e9e92d |
| checkpoint-64/model.safetensors | Weights | 490.8 MB | bd202887e836 |
| checkpoint-64/training_args.bin | Weights | 6.0 KB | c8b369e9e92d |
| checkpoint-8/model.safetensors | Weights | 490.8 MB | 714dbd16b7c2 |
| checkpoint-8/training_args.bin | Weights | 6.0 KB | c8b369e9e92d |
| checkpoint-8192/model.safetensors | Weights | 490.8 MB | 2b25c321d192 |
| checkpoint-8192/training_args.bin | Weights | 6.0 KB | c8b369e9e92d |
| model.safetensors | Weights | 490.8 MB | b9d59900bdad |
| training_args.bin | Weights | 6.0 KB | c8b369e9e92d |
| all_results.json | Configuration | 696 B | — |
| checkpoint-1/config.json | Configuration | 874 B | — |
| checkpoint-1/generation_config.json | Configuration | 119 B | — |
| checkpoint-1/special_tokens_map.json | Configuration | 692 B | — |
| checkpoint-1/trainer_state.json | Configuration | 1.2 KB | — |
| checkpoint-1024/config.json | Configuration | 874 B | — |
| checkpoint-1024/generation_config.json | Configuration | 119 B | — |
| checkpoint-1024/special_tokens_map.json | Configuration | 692 B | — |
| checkpoint-1024/trainer_state.json | Configuration | 5.6 KB | — |
| checkpoint-128/config.json | Configuration | 874 B | — |
| checkpoint-128/generation_config.json | Configuration | 119 B | — |
| checkpoint-128/special_tokens_map.json | Configuration | 692 B | — |
| checkpoint-128/trainer_state.json | Configuration | 4.3 KB | — |
| checkpoint-16/config.json | Configuration | 874 B | — |
| checkpoint-16/generation_config.json | Configuration | 119 B | — |
| checkpoint-16/special_tokens_map.json | Configuration | 692 B | — |
| checkpoint-16/trainer_state.json | Configuration | 3.0 KB | — |
| checkpoint-16000/config.json | Configuration | 874 B | — |
| checkpoint-16000/generation_config.json | Configuration | 119 B | — |
| checkpoint-16000/special_tokens_map.json | Configuration | 692 B | — |
| checkpoint-16000/trainer_state.json | Configuration | 7.3 KB | — |
| checkpoint-17600/config.json | Configuration | 874 B | — |
| checkpoint-17600/generation_config.json | Configuration | 119 B | — |
| checkpoint-17600/special_tokens_map.json | Configuration | 692 B | — |
| checkpoint-17600/trainer_state.json | Configuration | 7.8 KB | — |
| checkpoint-18580/config.json | Configuration | 874 B | — |
| checkpoint-18580/generation_config.json | Configuration | 119 B | — |
| checkpoint-18580/special_tokens_map.json | Configuration | 692 B | — |
| checkpoint-18580/trainer_state.json | Configuration | 7.7 KB | — |
| checkpoint-2/config.json | Configuration | 874 B | — |
| checkpoint-2/generation_config.json | Configuration | 119 B | — |
| checkpoint-2/special_tokens_map.json | Configuration | 692 B | — |
| checkpoint-2/trainer_state.json | Configuration | 1.7 KB | — |
| checkpoint-2048/config.json | Configuration | 874 B | — |
| checkpoint-2048/generation_config.json | Configuration | 119 B | — |
| checkpoint-2048/special_tokens_map.json | Configuration | 692 B | — |
| checkpoint-2048/trainer_state.json | Configuration | 6.0 KB | — |
| checkpoint-256/config.json | Configuration | 874 B | — |
| checkpoint-256/generation_config.json | Configuration | 119 B | — |
| checkpoint-256/special_tokens_map.json | Configuration | 692 B | — |
| checkpoint-256/trainer_state.json | Configuration | 4.7 KB | — |
| checkpoint-32/config.json | Configuration | 874 B | — |
| checkpoint-32/generation_config.json | Configuration | 119 B | — |
| checkpoint-32/special_tokens_map.json | Configuration | 692 B | — |
| checkpoint-32/trainer_state.json | Configuration | 3.4 KB | — |
| checkpoint-4/config.json | Configuration | 874 B | — |
| checkpoint-4/generation_config.json | Configuration | 119 B | — |
| checkpoint-4/special_tokens_map.json | Configuration | 692 B | — |
| checkpoint-4/trainer_state.json | Configuration | 2.1 KB | — |
| checkpoint-4096/config.json | Configuration | 874 B | — |
| checkpoint-4096/generation_config.json | Configuration | 119 B | — |
| checkpoint-4096/special_tokens_map.json | Configuration | 692 B | — |
| checkpoint-4096/trainer_state.json | Configuration | 6.4 KB | — |
| checkpoint-512/config.json | Configuration | 874 B | — |
| checkpoint-512/generation_config.json | Configuration | 119 B | — |
| checkpoint-512/special_tokens_map.json | Configuration | 692 B | — |
| checkpoint-512/trainer_state.json | Configuration | 5.1 KB | — |
| checkpoint-64/config.json | Configuration | 874 B | — |
| checkpoint-64/generation_config.json | Configuration | 119 B | — |
| checkpoint-64/special_tokens_map.json | Configuration | 692 B | — |
| checkpoint-64/trainer_state.json | Configuration | 3.8 KB | — |
| checkpoint-8/config.json | Configuration | 874 B | — |
| checkpoint-8/generation_config.json | Configuration | 119 B | — |
| checkpoint-8/special_tokens_map.json | Configuration | 692 B | — |
| checkpoint-8/trainer_state.json | Configuration | 2.5 KB | — |
| checkpoint-8192/config.json | Configuration | 874 B | — |
| checkpoint-8192/generation_config.json | Configuration | 119 B | — |
| checkpoint-8192/special_tokens_map.json | Configuration | 692 B | — |
| checkpoint-8192/trainer_state.json | Configuration | 6.9 KB | — |
| config.json | Configuration | 874 B | — |
| eval_results.json | Configuration | 480 B | — |
| generation_config.json | Configuration | 119 B | — |
| special_tokens_map.json | Configuration | 692 B | — |
| train_results.json | Configuration | 236 B | — |
| trainer_state.json | Configuration | 8.0 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
| checkpoint-1/tokenizer.json | Tokenizer | 3.8 MB | — |
| checkpoint-1/tokenizer_config.json | Tokenizer | 1.1 KB | — |
| checkpoint-1024/tokenizer.json | Tokenizer | 3.8 MB | — |
| checkpoint-1024/tokenizer_config.json | Tokenizer | 1.1 KB | — |
| checkpoint-128/tokenizer.json | Tokenizer | 3.8 MB | — |
| checkpoint-128/tokenizer_config.json | Tokenizer | 1.1 KB | — |
| checkpoint-16/tokenizer.json | Tokenizer | 3.8 MB | — |
| checkpoint-16/tokenizer_config.json | Tokenizer | 1.1 KB | — |
| checkpoint-16000/tokenizer.json | Tokenizer | 3.8 MB | — |
| checkpoint-16000/tokenizer_config.json | Tokenizer | 1.1 KB | — |
| checkpoint-17600/tokenizer.json | Tokenizer | 3.8 MB | — |
| checkpoint-17600/tokenizer_config.json | Tokenizer | 1.1 KB | — |
| checkpoint-18580/tokenizer.json | Tokenizer | 3.8 MB | — |
| checkpoint-18580/tokenizer_config.json | Tokenizer | 1.1 KB | — |
| checkpoint-2/tokenizer.json | Tokenizer | 3.8 MB | — |
| checkpoint-2/tokenizer_config.json | Tokenizer | 1.1 KB | — |
| checkpoint-2048/tokenizer.json | Tokenizer | 3.8 MB | — |
| checkpoint-2048/tokenizer_config.json | Tokenizer | 1.1 KB | — |
| checkpoint-256/tokenizer.json | Tokenizer | 3.8 MB | — |
| checkpoint-256/tokenizer_config.json | Tokenizer | 1.1 KB | — |
| checkpoint-32/tokenizer.json | Tokenizer | 3.8 MB | — |
| checkpoint-32/tokenizer_config.json | Tokenizer | 1.1 KB | — |
| checkpoint-4/tokenizer.json | Tokenizer | 3.8 MB | — |
| checkpoint-4/tokenizer_config.json | Tokenizer | 1.1 KB | — |
| checkpoint-4096/tokenizer.json | Tokenizer | 3.8 MB | — |
| checkpoint-4096/tokenizer_config.json | Tokenizer | 1.1 KB | — |
| checkpoint-512/tokenizer.json | Tokenizer | 3.8 MB | — |
| checkpoint-512/tokenizer_config.json | Tokenizer | 1.1 KB | — |
| checkpoint-64/tokenizer.json | Tokenizer | 3.8 MB | — |
| checkpoint-64/tokenizer_config.json | Tokenizer | 1.1 KB | — |
| checkpoint-8/tokenizer.json | Tokenizer | 3.8 MB | — |
| checkpoint-8/tokenizer_config.json | Tokenizer | 1.1 KB | — |
| checkpoint-8192/tokenizer.json | Tokenizer | 3.8 MB | — |
| checkpoint-8192/tokenizer_config.json | Tokenizer | 1.1 KB | — |
| tokenizer.json | Tokenizer | 3.8 MB | — |
| tokenizer_config.json | Tokenizer | 1.1 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 9.8 GB
Released by Hongao through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 9.8 GB |
| 16-bit | 0.2 GB |
| 8-bit | 0.1 GB |
| 4-bit | 0.1 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About llmplasticity-en_zh_linear_8-d0.01-c0.9-r0.8-s42
How much GPU memory does llmplasticity-en_zh_linear_8-d0.01-c0.9-r0.8-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-en_zh_linear_8-d0.01-c0.9-r0.8-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.