fin-laya is an open-weight model from Li, released under other. It has 421M parameters. At 16-bit it needs about 1 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
The card, configuration and files below were read at revision f1ae6c39e6db on 2026-10-17. The repository is now at revision 351b9f94f4d1, which SAVRN has not read yet.
Runs On
What it takes to serve fin-laya (421M 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 | 0.8 GB | 1.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.4 GB | 0.5 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.2 GB | 0.3 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 20, 2026.
fin-laya on every accelerator the SAVRN Index prices, at every precision
Model Card
By Li, published under apache-2.0, revision f1ae6c39e6db.
Read Li's full model card
Fin-Laya — 6-rounds
English financial decision model, approximately 0.42B parameters. This card describes the 6-rounds release (previously labeled four-source). Training data cover CHFS, CGSS, CFPS and CLDS.
Models collection · 3-rounds model card
Evaluation
| Test scope | Questions | Accuracy | Macro F1 |
|---|---|---|---|
| CHFS + CGSS | 240,458 | 74.5586% | 38.3986% |
| CHFS + CGSS + CFPS + CLDS | 418,597 | 67.2728% | 27.8355% |
Macro F1 averages over all candidate classes within each supported question version, then equally over versions.
Inference speed
8,885 input tokens/s, 26.75 ms mean latency, 37.38 decisions/s. Measured on one A100 40GB with FP16, batch and concurrency one, the same three requests, three warmups and 20 timed calls per request; input throughput uses a shared tokenizer.
Download and reproduce
hf download ya9919/fin-laya --revision four-source --local-dir fin-laya-6-rounds
cd fin-laya-6-rounds
python evaluate.py --output evaluation_reproduced.json
Evaluation report · Evaluation script · MAS Simulation
中文
本页为 6-rounds 训练版本，旧标签为 four-source；数据来源为 CHFS、CGSS、CFPS、CLDS。3-rounds 训练版本使用独立模型卡，下载链接指向对应历史权重。按训练轮次命名，数据来源单独说明。
Identity and Version
- Repository
- ya9919/fin-laya
- Publisher
- Li
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 421M parameters
- Languages
- en
- Revision
- 351b9f94f4d1ae74defe3db5db1109892dc1788b
- First published
- 2026-10-19
- Last updated
- 2026-10-20
Files and Weights
58 files, 892.9 MB in total. The weights are 1 file totalling 842.6 MB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 842.6 MB | 5b8cda43c63b |
| encoder/config.json | Configuration | 2.1 KB | — |
| evaluate.py | Configuration | 13.6 KB | — |
| evaluation_manifest.json | Configuration | 1.9 KB | — |
| evaluation_report.json | Configuration | 6.7 MB | — |
| example_request.json | Configuration | 1.1 KB | — |
| paired_release_report.json | Configuration | 4.2 KB | — |
| predict_example.py | Configuration | 979 B | — |
| question_registry.json | Configuration | 68.6 KB | — |
| release_manifest.json | Configuration | 639 B | — |
| reports/base_manifest.json | Configuration | 580 B | — |
| reports/data_export_report.json | Configuration | 1.2 MB | — |
| reports/data_manifest.json | Configuration | 973.3 KB | — |
| reports/data_snapshot.json | Configuration | 925 B | — |
| reports/data_statistics.json | Configuration | 443.9 KB | — |
| reports/encoding_report.json | Configuration | 3.7 KB | — |
| reports/final_report.json | Configuration | 27.4 MB | 5b8af8233dae |
| reports/mlx_renderer_verification.json | Configuration | 127 B | — |
| reports/mlx_test_report.json | Configuration | 9.6 MB | — |
| reports/old_test_regression_report.json | Configuration | 1.8 KB | — |
| reports/preflight_report.json | Configuration | 558 B | — |
| reports/rlcd_train_summary.json | Configuration | 959 B | — |
| reports/sft1_train_summary.json | Configuration | 459 B | — |
| reports/sft2_train_summary.json | Configuration | 960 B | — |
| reports/speed_base.json | Configuration | 67.3 KB | — |
| reports/speed_comparison.json | Configuration | 5.1 KB | — |
| reports/speed_fin.json | Configuration | 67.3 KB | — |
| reports/training_protocol.json | Configuration | 1.6 KB | — |
| reports/translation_report.json | Configuration | 3.9 KB | — |
| reproduction/benchmark_finance.py | Configuration | 6.8 KB | — |
| reproduction/durable.py | Configuration | 2.4 KB | — |
| reproduction/encode_data.py | Configuration | 2.2 KB | — |
| reproduction/encode_latest.py | Configuration | 6.1 KB | — |
| reproduction/evaluation_tools.py | Configuration | 7.3 KB | — |
| reproduction/experiment_common.py | Configuration | 8.2 KB | — |
| reproduction/mlx_worker.py | Configuration | 5.8 KB | — |
| reproduction/model_manifest.json | Configuration | 297 B | — |
| reproduction/original_base_manifest.json | Configuration | 364 B | — |
| reproduction/preflight_latest.py | Configuration | 3.6 KB | — |
| reproduction/prepare_fixtures.py | Configuration | 3.0 KB | — |
| reproduction/publish_versions.py | Configuration | 10.0 KB | — |
| reproduction/release_stages.py | Configuration | 14.2 KB | — |
| reproduction/run_english_experiment.py | Configuration | 8.2 KB | — |
| reproduction/run_experiment.py | Configuration | 10.6 KB | — |
| reproduction/training_core.py | Configuration | 5.6 KB | — |
| rl_agent_config.json | Configuration | 4.4 KB | — |
| tokenizer/special_tokens_map.json | Configuration | 694 B | — |
| versions.json | Configuration | 18.0 KB | — |
| LICENSE | Documentation | 10.2 KB | — |
| Model_Card_3_rounds.md | Documentation | 1.7 KB | — |
| Model_Card_EN.md | Documentation | 2.2 KB | — |
| Model_Card_ZH.md | Documentation | 2.0 KB | — |
| NOTICE | Documentation | 118 B | — |
| README.md | Documentation | 1.6 KB | — |
| requirements.txt | Other | 121 B | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer/tokenizer.json | Tokenizer | 3.6 MB | — |
| tokenizer/tokenizer_config.json | Tokenizer | 20.9 KB | — |
License and Download
- License
- other
- Access
- Open weights, no gate
Released by Li through its official repository on Hugging Face. Read the license.
Built From
- Derived from convaiinnovations/laya
Memory Requirements
| Precision | Weights in memory |
|---|---|
| 16-bit | 0.8 GB |
| 8-bit | 0.4 GB |
| 4-bit | 0.2 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About fin-laya
How much GPU memory does fin-laya need?
About 1 GB at 16-bit and 0.3 GB at 4-bit: the weights (421M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run fin-laya 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.
What license is fin-laya released under?
other, as its publisher declares it. Read the license text before commercial use.