Skip to page content
SAVRN
Search Plan a project

Open-weight model

sft_200m_generated_fixed_pe

by Pre-to-Post-2 Pre-to-Post-2/sft_200m_generated_fixed_pe

sft_200m_generated_fixed_pe is an open-weight model from Pre-to-Post-2. Its published files total 8.9 GB.

Multi-turn chess SFT checkpoints trained after the YaRN positional-encoding fix in sfttrainer.py (2026-09).

Parameters—
Context—
Weights8.9 GB
License—
AccessOpen weights
Monthly Downloads—

Model Card

Multi-turn chess SFT checkpoints trained after the YaRN positional-encoding fix in sfttrainer.py (2026-09). Before the fix, the blocksize / ropescaling change was applied after frompretrained(), so runs with a 3072-token context trained with plain RoPE extrapolation while their saved config claimed YaRN. These runs load the config first and build the model from it, so training and inference both use YaRN (factor 3, 1024 → 3072). Thanks to Jens Tuyls for spotting the bug. Folders mirror the local save tree. Each model lives at /final/, where modelid = C{compute}{size}alpha{α}beta{β}. Alongside final/ are combinedeval.json (when evaluated) and configsnapshot/ (training config). Optimizer…

Excerpt from the card by Pre-to-Post-2.

Identity and Version

Repository
Pre-to-Post-2/sft_200m_generated_fixed_pe
Publisher
Pre-to-Post-2
Task
Not stated by the source
Modality
Other
Library
transformers
Parameters
Not stated by the source
Languages
sft
Revision
ff58254dfe211d5bb2bc258b7caf889dc27189d2
First published
2026-10-12
Last updated
2026-10-12

Files and Weights

260 files, 8.9 GB in total. The weights are 26 files totalling 8.9 GB in safetensors.

Weights26 files · 8.9 GB
Configuration154 files · 160.5 KB
Tokenizer78 files · 832.0 KB
Documentation1 file · 2.6 KB
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
C6p5e18_200m_alpha0.100_beta0.100/final/model.safetensorsWeights812.1 MB 4de4064ce460
C6p5e18_200m_alpha0.200_beta0.100/final/model.safetensorsWeights812.1 MB 7fcfb70ed9df
C6p5e18_200m_alpha0.750_beta0.100/final/model.safetensorsWeights812.1 MB 0374a695717f
C6p5e18_200m_alpha1.000_beta0.100/final/model.safetensorsWeights812.1 MB 27642052c367
C6p5e18_20m_alpha0.010_beta0.008/final/model.safetensorsWeights82.0 MB e8cd311b0993
C6p5e18_20m_alpha0.030_beta0.008/final/model.safetensorsWeights82.0 MB f09023ae346f
C6p5e18_20m_alpha0.050_beta0.008/final/model.safetensorsWeights82.0 MB bcd1992b39c1
C6p5e18_20m_alpha0.100_beta0.008/final/model.safetensorsWeights82.0 MB 784266356dca
C6p5e18_20m_alpha0.200_beta0.008/final/model.safetensorsWeights82.0 MB f35e17676729
C6p5e18_20m_alpha0.300_beta0.008/final/model.safetensorsWeights82.0 MB 2718ba447fd6
C6p5e18_20m_alpha0.600_beta0.008/final/model.safetensorsWeights82.0 MB 703e019964b7
C6p5e18_20m_alpha0.750_beta0.008/final/model.safetensorsWeights82.0 MB 6d48bce1b284
C6p5e18_20m_alpha1.000_beta0.008/final/model.safetensorsWeights82.0 MB 67f3efbc704e
C6p5e18_50m_alpha0.010_beta0.023/final/model.safetensorsWeights189.0 MB 7702ebc44855
C6p5e18_50m_alpha0.030_beta0.023/final/model.safetensorsWeights189.0 MB cbb40c9eac75
C6p5e18_50m_alpha0.050_beta0.023/final/model.safetensorsWeights189.0 MB 989377aa90c5
C6p5e18_50m_alpha0.100_beta0.023/final/model.safetensorsWeights189.0 MB be08e8c94068
C6p5e18_50m_alpha0.200_beta0.023/final/model.safetensorsWeights189.0 MB 36ebca975fa3
C6p5e18_50m_alpha0.400_beta0.023/final/model.safetensorsWeights189.0 MB 98c8b86bb2ca
C6p5e18_50m_alpha0.750_beta0.023/final/model.safetensorsWeights189.0 MB 78d38bdb7862
C6p5e18_50m_alpha1.000_beta0.023/final/model.safetensorsWeights189.0 MB 06ee0b30ade8
C6p5e19_200m_alpha0.200_beta0.007/final/model.safetensorsWeights812.1 MB ee1cc0f9a1fa
C6p5e19_200m_alpha0.400_beta0.007/final/model.safetensorsWeights812.1 MB c0364f966e7c
C6p5e19_200m_alpha0.750_beta0.007/final/model.safetensorsWeights812.1 MB 63db6383cc43
C6p5e19_200m_alpha1.000_beta0.007/final/model.safetensorsWeights812.1 MB e2d33be20616
C6p5e19_50m_alpha0.180_beta0.002/final/model.safetensorsWeights189.0 MB c8c51f4c2f20
C6p5e18_200m_alpha0.100_beta0.100/combined_eval.jsonConfiguration1.2 KB —
C6p5e18_200m_alpha0.100_beta0.100/config_snapshot/sft_config_multi_path_2048.yamlConfiguration3.6 KB —
C6p5e18_200m_alpha0.100_beta0.100/final/config.jsonConfiguration1.5 KB —
C6p5e18_200m_alpha0.100_beta0.100/final/generation_config.jsonConfiguration128 B —
C6p5e18_200m_alpha0.100_beta0.100/final/special_tokens_map.jsonConfiguration127 B —
C6p5e18_200m_alpha0.100_beta0.100/final/training_state.jsonConfiguration25 B —
C6p5e18_200m_alpha0.200_beta0.100/combined_eval.jsonConfiguration1.2 KB —
C6p5e18_200m_alpha0.200_beta0.100/config_snapshot/sft_config_multi_path_2048.yamlConfiguration3.6 KB —
C6p5e18_200m_alpha0.200_beta0.100/final/config.jsonConfiguration1.4 KB —
C6p5e18_200m_alpha0.200_beta0.100/final/generation_config.jsonConfiguration128 B —
C6p5e18_200m_alpha0.200_beta0.100/final/special_tokens_map.jsonConfiguration127 B —
C6p5e18_200m_alpha0.200_beta0.100/final/training_state.jsonConfiguration25 B —
C6p5e18_200m_alpha0.750_beta0.100/combined_eval.jsonConfiguration1.2 KB —
C6p5e18_200m_alpha0.750_beta0.100/config_snapshot/sft_config_multi_path_2048.yamlConfiguration3.6 KB —
C6p5e18_200m_alpha0.750_beta0.100/final/config.jsonConfiguration1.4 KB —
C6p5e18_200m_alpha0.750_beta0.100/final/generation_config.jsonConfiguration128 B —
C6p5e18_200m_alpha0.750_beta0.100/final/special_tokens_map.jsonConfiguration127 B —
C6p5e18_200m_alpha0.750_beta0.100/final/training_state.jsonConfiguration25 B —
C6p5e18_200m_alpha1.000_beta0.100/combined_eval.jsonConfiguration1.2 KB —
C6p5e18_200m_alpha1.000_beta0.100/config_snapshot/sft_config_multi_path_2048.yamlConfiguration3.6 KB —
C6p5e18_200m_alpha1.000_beta0.100/final/config.jsonConfiguration1.5 KB —
C6p5e18_200m_alpha1.000_beta0.100/final/generation_config.jsonConfiguration128 B —
C6p5e18_200m_alpha1.000_beta0.100/final/special_tokens_map.jsonConfiguration127 B —
C6p5e18_200m_alpha1.000_beta0.100/final/training_state.jsonConfiguration25 B —
C6p5e18_20m_alpha0.010_beta0.008/combined_eval.jsonConfiguration1.2 KB —
C6p5e18_20m_alpha0.010_beta0.008/config_snapshot/sft_config_multi_path_2048.yamlConfiguration3.6 KB —
C6p5e18_20m_alpha0.010_beta0.008/final/config.jsonConfiguration1.1 KB —
C6p5e18_20m_alpha0.010_beta0.008/final/generation_config.jsonConfiguration128 B —
C6p5e18_20m_alpha0.010_beta0.008/final/special_tokens_map.jsonConfiguration127 B —
C6p5e18_20m_alpha0.010_beta0.008/final/training_state.jsonConfiguration25 B —
C6p5e18_20m_alpha0.030_beta0.008/combined_eval.jsonConfiguration1.2 KB —
C6p5e18_20m_alpha0.030_beta0.008/config_snapshot/sft_config_multi_path_2048.yamlConfiguration3.6 KB —
C6p5e18_20m_alpha0.030_beta0.008/final/config.jsonConfiguration1.1 KB —
C6p5e18_20m_alpha0.030_beta0.008/final/generation_config.jsonConfiguration128 B —
C6p5e18_20m_alpha0.030_beta0.008/final/special_tokens_map.jsonConfiguration127 B —
C6p5e18_20m_alpha0.030_beta0.008/final/training_state.jsonConfiguration25 B —
C6p5e18_20m_alpha0.050_beta0.008/combined_eval.jsonConfiguration1.2 KB —
C6p5e18_20m_alpha0.050_beta0.008/config_snapshot/sft_config_multi_path_2048.yamlConfiguration3.6 KB —
C6p5e18_20m_alpha0.050_beta0.008/final/config.jsonConfiguration1.1 KB —
C6p5e18_20m_alpha0.050_beta0.008/final/generation_config.jsonConfiguration128 B —
C6p5e18_20m_alpha0.050_beta0.008/final/special_tokens_map.jsonConfiguration127 B —
C6p5e18_20m_alpha0.050_beta0.008/final/training_state.jsonConfiguration25 B —
C6p5e18_20m_alpha0.100_beta0.008/combined_eval.jsonConfiguration1.2 KB —
C6p5e18_20m_alpha0.100_beta0.008/config_snapshot/sft_config_multi_path_2048.yamlConfiguration3.6 KB —
C6p5e18_20m_alpha0.100_beta0.008/final/config.jsonConfiguration1.1 KB —
C6p5e18_20m_alpha0.100_beta0.008/final/generation_config.jsonConfiguration128 B —
C6p5e18_20m_alpha0.100_beta0.008/final/special_tokens_map.jsonConfiguration127 B —
C6p5e18_20m_alpha0.100_beta0.008/final/training_state.jsonConfiguration25 B —
C6p5e18_20m_alpha0.200_beta0.008/combined_eval.jsonConfiguration1.2 KB —
C6p5e18_20m_alpha0.200_beta0.008/config_snapshot/sft_config_multi_path_2048.yamlConfiguration3.6 KB —
C6p5e18_20m_alpha0.200_beta0.008/final/config.jsonConfiguration1.1 KB —
C6p5e18_20m_alpha0.200_beta0.008/final/generation_config.jsonConfiguration128 B —
C6p5e18_20m_alpha0.200_beta0.008/final/special_tokens_map.jsonConfiguration127 B —
C6p5e18_20m_alpha0.200_beta0.008/final/training_state.jsonConfiguration25 B —
C6p5e18_20m_alpha0.300_beta0.008/combined_eval.jsonConfiguration1.2 KB —
C6p5e18_20m_alpha0.300_beta0.008/config_snapshot/sft_config_multi_path_2048.yamlConfiguration3.6 KB —
C6p5e18_20m_alpha0.300_beta0.008/final/config.jsonConfiguration1.1 KB —
C6p5e18_20m_alpha0.300_beta0.008/final/generation_config.jsonConfiguration128 B —
C6p5e18_20m_alpha0.300_beta0.008/final/special_tokens_map.jsonConfiguration127 B —
C6p5e18_20m_alpha0.300_beta0.008/final/training_state.jsonConfiguration25 B —
C6p5e18_20m_alpha0.600_beta0.008/combined_eval.jsonConfiguration1.2 KB —
C6p5e18_20m_alpha0.600_beta0.008/config_snapshot/sft_config_multi_path_2048.yamlConfiguration3.6 KB —
C6p5e18_20m_alpha0.600_beta0.008/final/config.jsonConfiguration1.1 KB —
C6p5e18_20m_alpha0.600_beta0.008/final/generation_config.jsonConfiguration128 B —
C6p5e18_20m_alpha0.600_beta0.008/final/special_tokens_map.jsonConfiguration127 B —
C6p5e18_20m_alpha0.600_beta0.008/final/training_state.jsonConfiguration25 B —
C6p5e18_20m_alpha0.750_beta0.008/combined_eval.jsonConfiguration1.2 KB —
C6p5e18_20m_alpha0.750_beta0.008/config_snapshot/sft_config_multi_path_2048.yamlConfiguration3.6 KB —
C6p5e18_20m_alpha0.750_beta0.008/final/config.jsonConfiguration1.1 KB —
C6p5e18_20m_alpha0.750_beta0.008/final/generation_config.jsonConfiguration128 B —
C6p5e18_20m_alpha0.750_beta0.008/final/special_tokens_map.jsonConfiguration127 B —
C6p5e18_20m_alpha0.750_beta0.008/final/training_state.jsonConfiguration25 B —
C6p5e18_20m_alpha1.000_beta0.008/config_snapshot/sft_config_multi_path_2048.yamlConfiguration3.6 KB —
C6p5e18_20m_alpha1.000_beta0.008/final/config.jsonConfiguration1.1 KB —
C6p5e18_20m_alpha1.000_beta0.008/final/generation_config.jsonConfiguration128 B —
C6p5e18_20m_alpha1.000_beta0.008/final/special_tokens_map.jsonConfiguration127 B —
C6p5e18_20m_alpha1.000_beta0.008/final/training_state.jsonConfiguration25 B —
C6p5e18_50m_alpha0.010_beta0.023/combined_eval.jsonConfiguration1.2 KB —
C6p5e18_50m_alpha0.010_beta0.023/config_snapshot/sft_config_multi_path_2048.yamlConfiguration3.6 KB —
C6p5e18_50m_alpha0.010_beta0.023/final/config.jsonConfiguration1.2 KB —
C6p5e18_50m_alpha0.010_beta0.023/final/generation_config.jsonConfiguration128 B —
C6p5e18_50m_alpha0.010_beta0.023/final/special_tokens_map.jsonConfiguration127 B —
C6p5e18_50m_alpha0.010_beta0.023/final/training_state.jsonConfiguration25 B —
C6p5e18_50m_alpha0.030_beta0.023/combined_eval.jsonConfiguration1.2 KB —
C6p5e18_50m_alpha0.030_beta0.023/config_snapshot/sft_config_multi_path_2048.yamlConfiguration3.6 KB —
C6p5e18_50m_alpha0.030_beta0.023/final/config.jsonConfiguration1.2 KB —
C6p5e18_50m_alpha0.030_beta0.023/final/generation_config.jsonConfiguration128 B —
C6p5e18_50m_alpha0.030_beta0.023/final/special_tokens_map.jsonConfiguration127 B —
C6p5e18_50m_alpha0.030_beta0.023/final/training_state.jsonConfiguration25 B —
C6p5e18_50m_alpha0.050_beta0.023/combined_eval.jsonConfiguration1.2 KB —
C6p5e18_50m_alpha0.050_beta0.023/config_snapshot/sft_config_multi_path_2048.yamlConfiguration3.6 KB —
C6p5e18_50m_alpha0.050_beta0.023/final/config.jsonConfiguration1.2 KB —
C6p5e18_50m_alpha0.050_beta0.023/final/generation_config.jsonConfiguration128 B —
C6p5e18_50m_alpha0.050_beta0.023/final/special_tokens_map.jsonConfiguration127 B —
C6p5e18_50m_alpha0.050_beta0.023/final/training_state.jsonConfiguration25 B —
C6p5e18_50m_alpha0.100_beta0.023/combined_eval.jsonConfiguration1.2 KB —
C6p5e18_50m_alpha0.100_beta0.023/config_snapshot/sft_config_multi_path_2048.yamlConfiguration3.6 KB —
C6p5e18_50m_alpha0.100_beta0.023/final/config.jsonConfiguration1.2 KB —
C6p5e18_50m_alpha0.100_beta0.023/final/generation_config.jsonConfiguration128 B —
C6p5e18_50m_alpha0.100_beta0.023/final/special_tokens_map.jsonConfiguration127 B —
C6p5e18_50m_alpha0.100_beta0.023/final/training_state.jsonConfiguration25 B —
C6p5e18_50m_alpha0.200_beta0.023/config_snapshot/sft_config_multi_path_2048.yamlConfiguration3.6 KB —
C6p5e18_50m_alpha0.200_beta0.023/final/config.jsonConfiguration1.2 KB —
C6p5e18_50m_alpha0.200_beta0.023/final/generation_config.jsonConfiguration128 B —
C6p5e18_50m_alpha0.200_beta0.023/final/special_tokens_map.jsonConfiguration127 B —
C6p5e18_50m_alpha0.200_beta0.023/final/training_state.jsonConfiguration25 B —
C6p5e18_50m_alpha0.400_beta0.023/combined_eval.jsonConfiguration1.2 KB —
C6p5e18_50m_alpha0.400_beta0.023/config_snapshot/sft_config_multi_path_2048.yamlConfiguration3.6 KB —
C6p5e18_50m_alpha0.400_beta0.023/final/config.jsonConfiguration1.1 KB —
C6p5e18_50m_alpha0.400_beta0.023/final/generation_config.jsonConfiguration128 B —
C6p5e18_50m_alpha0.400_beta0.023/final/special_tokens_map.jsonConfiguration127 B —
C6p5e18_50m_alpha0.400_beta0.023/final/training_state.jsonConfiguration25 B —
C6p5e18_50m_alpha0.750_beta0.023/combined_eval.jsonConfiguration1.2 KB —
C6p5e18_50m_alpha0.750_beta0.023/config_snapshot/sft_config_multi_path_2048.yamlConfiguration3.6 KB —
C6p5e18_50m_alpha0.750_beta0.023/final/config.jsonConfiguration1.2 KB —
C6p5e18_50m_alpha0.750_beta0.023/final/generation_config.jsonConfiguration128 B —
C6p5e18_50m_alpha0.750_beta0.023/final/special_tokens_map.jsonConfiguration127 B —
C6p5e18_50m_alpha0.750_beta0.023/final/training_state.jsonConfiguration25 B —
C6p5e18_50m_alpha1.000_beta0.023/combined_eval.jsonConfiguration1.2 KB —
C6p5e18_50m_alpha1.000_beta0.023/config_snapshot/sft_config_multi_path_2048.yamlConfiguration3.6 KB —
C6p5e18_50m_alpha1.000_beta0.023/final/config.jsonConfiguration1.2 KB —
C6p5e18_50m_alpha1.000_beta0.023/final/generation_config.jsonConfiguration128 B —
C6p5e18_50m_alpha1.000_beta0.023/final/special_tokens_map.jsonConfiguration127 B —
C6p5e18_50m_alpha1.000_beta0.023/final/training_state.jsonConfiguration25 B —
C6p5e19_200m_alpha0.200_beta0.007/combined_eval.jsonConfiguration1.2 KB —
C6p5e19_200m_alpha0.200_beta0.007/config_snapshot/sft_config_multi_path_2048.yamlConfiguration3.6 KB —
C6p5e19_200m_alpha0.200_beta0.007/final/config.jsonConfiguration1.4 KB —
C6p5e19_200m_alpha0.200_beta0.007/final/generation_config.jsonConfiguration128 B —
C6p5e19_200m_alpha0.200_beta0.007/final/special_tokens_map.jsonConfiguration127 B —
C6p5e19_200m_alpha0.200_beta0.007/final/training_state.jsonConfiguration25 B —
C6p5e19_200m_alpha0.400_beta0.007/combined_eval.jsonConfiguration1.2 KB —
C6p5e19_200m_alpha0.400_beta0.007/config_snapshot/sft_config_multi_path_2048.yamlConfiguration3.6 KB —
C6p5e19_200m_alpha0.400_beta0.007/final/config.jsonConfiguration1.4 KB —
C6p5e19_200m_alpha0.400_beta0.007/final/generation_config.jsonConfiguration128 B —
C6p5e19_200m_alpha0.400_beta0.007/final/special_tokens_map.jsonConfiguration127 B —
C6p5e19_200m_alpha0.400_beta0.007/final/training_state.jsonConfiguration25 B —
C6p5e19_200m_alpha0.750_beta0.007/combined_eval.jsonConfiguration1.2 KB —
C6p5e19_200m_alpha0.750_beta0.007/config_snapshot/sft_config_multi_path_2048.yamlConfiguration3.6 KB —
C6p5e19_200m_alpha0.750_beta0.007/final/config.jsonConfiguration1.5 KB —
C6p5e19_200m_alpha0.750_beta0.007/final/generation_config.jsonConfiguration128 B —
C6p5e19_200m_alpha0.750_beta0.007/final/special_tokens_map.jsonConfiguration127 B —
C6p5e19_200m_alpha0.750_beta0.007/final/training_state.jsonConfiguration25 B —
C6p5e19_200m_alpha1.000_beta0.007/combined_eval.jsonConfiguration1.2 KB —
C6p5e19_200m_alpha1.000_beta0.007/config_snapshot/sft_config_multi_path_2048.yamlConfiguration3.6 KB —
C6p5e19_200m_alpha1.000_beta0.007/final/config.jsonConfiguration1.5 KB —
C6p5e19_200m_alpha1.000_beta0.007/final/generation_config.jsonConfiguration128 B —
C6p5e19_200m_alpha1.000_beta0.007/final/special_tokens_map.jsonConfiguration127 B —
C6p5e19_200m_alpha1.000_beta0.007/final/training_state.jsonConfiguration25 B —
C6p5e19_50m_alpha0.180_beta0.002/combined_eval.jsonConfiguration1.2 KB —
C6p5e19_50m_alpha0.180_beta0.002/config_snapshot/sft_config_multi_path_2048.yamlConfiguration3.6 KB —
C6p5e19_50m_alpha0.180_beta0.002/final/config.jsonConfiguration1.2 KB —
C6p5e19_50m_alpha0.180_beta0.002/final/generation_config.jsonConfiguration128 B —
C6p5e19_50m_alpha0.180_beta0.002/final/special_tokens_map.jsonConfiguration127 B —
C6p5e19_50m_alpha0.180_beta0.002/final/training_state.jsonConfiguration25 B —
README.mdDocumentation2.6 KB —
.gitattributesRepository1.5 KB —
C6p5e18_200m_alpha0.100_beta0.100/final/tokenizer.pyTokenizer30.3 KB —
C6p5e18_200m_alpha0.100_beta0.100/final/tokenizer_config.jsonTokenizer623 B —
C6p5e18_200m_alpha0.100_beta0.100/final/vocab.jsonTokenizer1.0 KB —
C6p5e18_200m_alpha0.200_beta0.100/final/tokenizer.pyTokenizer30.3 KB —
C6p5e18_200m_alpha0.200_beta0.100/final/tokenizer_config.jsonTokenizer623 B —
C6p5e18_200m_alpha0.200_beta0.100/final/vocab.jsonTokenizer1.0 KB —
C6p5e18_200m_alpha0.750_beta0.100/final/tokenizer.pyTokenizer30.3 KB —
C6p5e18_200m_alpha0.750_beta0.100/final/tokenizer_config.jsonTokenizer623 B —
C6p5e18_200m_alpha0.750_beta0.100/final/vocab.jsonTokenizer1.0 KB —
C6p5e18_200m_alpha1.000_beta0.100/final/tokenizer.pyTokenizer30.3 KB —
C6p5e18_200m_alpha1.000_beta0.100/final/tokenizer_config.jsonTokenizer623 B —
C6p5e18_200m_alpha1.000_beta0.100/final/vocab.jsonTokenizer1.0 KB —
C6p5e18_20m_alpha0.010_beta0.008/final/tokenizer.pyTokenizer30.3 KB —
C6p5e18_20m_alpha0.010_beta0.008/final/tokenizer_config.jsonTokenizer623 B —
C6p5e18_20m_alpha0.010_beta0.008/final/vocab.jsonTokenizer1.0 KB —
C6p5e18_20m_alpha0.030_beta0.008/final/tokenizer.pyTokenizer30.3 KB —
C6p5e18_20m_alpha0.030_beta0.008/final/tokenizer_config.jsonTokenizer623 B —
C6p5e18_20m_alpha0.030_beta0.008/final/vocab.jsonTokenizer1.0 KB —
C6p5e18_20m_alpha0.050_beta0.008/final/tokenizer.pyTokenizer30.3 KB —
C6p5e18_20m_alpha0.050_beta0.008/final/tokenizer_config.jsonTokenizer623 B —
C6p5e18_20m_alpha0.050_beta0.008/final/vocab.jsonTokenizer1.0 KB —
C6p5e18_20m_alpha0.100_beta0.008/final/tokenizer.pyTokenizer30.3 KB —
C6p5e18_20m_alpha0.100_beta0.008/final/tokenizer_config.jsonTokenizer623 B —
C6p5e18_20m_alpha0.100_beta0.008/final/vocab.jsonTokenizer1.0 KB —
C6p5e18_20m_alpha0.200_beta0.008/final/tokenizer.pyTokenizer30.3 KB —
C6p5e18_20m_alpha0.200_beta0.008/final/tokenizer_config.jsonTokenizer623 B —
C6p5e18_20m_alpha0.200_beta0.008/final/vocab.jsonTokenizer1.0 KB —
C6p5e18_20m_alpha0.300_beta0.008/final/tokenizer.pyTokenizer30.3 KB —
C6p5e18_20m_alpha0.300_beta0.008/final/tokenizer_config.jsonTokenizer623 B —
C6p5e18_20m_alpha0.300_beta0.008/final/vocab.jsonTokenizer1.0 KB —
C6p5e18_20m_alpha0.600_beta0.008/final/tokenizer.pyTokenizer30.3 KB —
C6p5e18_20m_alpha0.600_beta0.008/final/tokenizer_config.jsonTokenizer623 B —
C6p5e18_20m_alpha0.600_beta0.008/final/vocab.jsonTokenizer1.0 KB —
C6p5e18_20m_alpha0.750_beta0.008/final/tokenizer.pyTokenizer30.3 KB —
C6p5e18_20m_alpha0.750_beta0.008/final/tokenizer_config.jsonTokenizer623 B —
C6p5e18_20m_alpha0.750_beta0.008/final/vocab.jsonTokenizer1.0 KB —
C6p5e18_20m_alpha1.000_beta0.008/final/tokenizer.pyTokenizer30.3 KB —
C6p5e18_20m_alpha1.000_beta0.008/final/tokenizer_config.jsonTokenizer623 B —
C6p5e18_20m_alpha1.000_beta0.008/final/vocab.jsonTokenizer1.0 KB —
C6p5e18_50m_alpha0.010_beta0.023/final/tokenizer.pyTokenizer30.3 KB —
C6p5e18_50m_alpha0.010_beta0.023/final/tokenizer_config.jsonTokenizer623 B —
C6p5e18_50m_alpha0.010_beta0.023/final/vocab.jsonTokenizer1.0 KB —
C6p5e18_50m_alpha0.030_beta0.023/final/tokenizer.pyTokenizer30.3 KB —
C6p5e18_50m_alpha0.030_beta0.023/final/tokenizer_config.jsonTokenizer623 B —
C6p5e18_50m_alpha0.030_beta0.023/final/vocab.jsonTokenizer1.0 KB —
C6p5e18_50m_alpha0.050_beta0.023/final/tokenizer.pyTokenizer30.3 KB —
C6p5e18_50m_alpha0.050_beta0.023/final/tokenizer_config.jsonTokenizer623 B —
C6p5e18_50m_alpha0.050_beta0.023/final/vocab.jsonTokenizer1.0 KB —
C6p5e18_50m_alpha0.100_beta0.023/final/tokenizer.pyTokenizer30.3 KB —
C6p5e18_50m_alpha0.100_beta0.023/final/tokenizer_config.jsonTokenizer623 B —
C6p5e18_50m_alpha0.100_beta0.023/final/vocab.jsonTokenizer1.0 KB —
C6p5e18_50m_alpha0.200_beta0.023/final/tokenizer.pyTokenizer30.3 KB —
C6p5e18_50m_alpha0.200_beta0.023/final/tokenizer_config.jsonTokenizer623 B —
C6p5e18_50m_alpha0.200_beta0.023/final/vocab.jsonTokenizer1.0 KB —
C6p5e18_50m_alpha0.400_beta0.023/final/tokenizer.pyTokenizer30.3 KB —
C6p5e18_50m_alpha0.400_beta0.023/final/tokenizer_config.jsonTokenizer623 B —
C6p5e18_50m_alpha0.400_beta0.023/final/vocab.jsonTokenizer1.0 KB —
C6p5e18_50m_alpha0.750_beta0.023/final/tokenizer.pyTokenizer30.3 KB —
C6p5e18_50m_alpha0.750_beta0.023/final/tokenizer_config.jsonTokenizer623 B —
C6p5e18_50m_alpha0.750_beta0.023/final/vocab.jsonTokenizer1.0 KB —
C6p5e18_50m_alpha1.000_beta0.023/final/tokenizer.pyTokenizer30.3 KB —
C6p5e18_50m_alpha1.000_beta0.023/final/tokenizer_config.jsonTokenizer623 B —
C6p5e18_50m_alpha1.000_beta0.023/final/vocab.jsonTokenizer1.0 KB —
C6p5e19_200m_alpha0.200_beta0.007/final/tokenizer.pyTokenizer30.3 KB —
C6p5e19_200m_alpha0.200_beta0.007/final/tokenizer_config.jsonTokenizer623 B —
C6p5e19_200m_alpha0.200_beta0.007/final/vocab.jsonTokenizer1.0 KB —
C6p5e19_200m_alpha0.400_beta0.007/final/tokenizer.pyTokenizer30.3 KB —
C6p5e19_200m_alpha0.400_beta0.007/final/tokenizer_config.jsonTokenizer623 B —
C6p5e19_200m_alpha0.400_beta0.007/final/vocab.jsonTokenizer1.0 KB —
C6p5e19_200m_alpha0.750_beta0.007/final/tokenizer.pyTokenizer30.3 KB —
C6p5e19_200m_alpha0.750_beta0.007/final/tokenizer_config.jsonTokenizer623 B —
C6p5e19_200m_alpha0.750_beta0.007/final/vocab.jsonTokenizer1.0 KB —
C6p5e19_200m_alpha1.000_beta0.007/final/tokenizer.pyTokenizer30.3 KB —
C6p5e19_200m_alpha1.000_beta0.007/final/tokenizer_config.jsonTokenizer623 B —
C6p5e19_200m_alpha1.000_beta0.007/final/vocab.jsonTokenizer1.0 KB —
C6p5e19_50m_alpha0.180_beta0.002/final/tokenizer.pyTokenizer30.3 KB —
C6p5e19_50m_alpha0.180_beta0.002/final/tokenizer_config.jsonTokenizer623 B —
C6p5e19_50m_alpha0.180_beta0.002/final/vocab.jsonTokenizer1.0 KB —

License and Download

License
Not stated by the source
Access
Open weights, no gate
Download size
8.9 GB
Download from Pre-to-Post-2

Released by Pre-to-Post-2 through its official repository on Hugging Face.

Memory Requirements

PrecisionWeights in memory
As published8.9 GB

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