Open-weight model
mainsweep4ep-kl10000-s1-logitrl120
by Julia Rezvani jlsrls/mainsweep4ep-kl10000-s1-logitrl120
mainsweep4ep-kl10000-s1-logitrl120 is an open-weight model from Julia Rezvani. Its published files total 1.7 GB.
This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model.
Model Card
This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
Excerpt from the card by Julia Rezvani.
Identity and Version
- Repository
- jlsrls/mainsweep4ep-kl10000-s1-logitrl120
- Publisher
- Julia Rezvani
- Task
- Not stated by the source
- Modality
- Other
- Library
- transformers
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- 38401346422885a30fa7c1f87d5717c4cd7ffc42
- First published
- 2026-09-25
- Last updated
- 2026-09-25
Files and Weights
101 files, 1.7 GB in total. The weights are 62 files totalling 1.7 GB in bin, pt, pth, safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| adapter_model.safetensors | Weights | 90.2 MB | a2ebccc492d6 |
| checkpoint-10/adapter_model.safetensors | Weights | 90.2 MB | 01ea55937b52 |
| checkpoint-10/optimizer.pt | Weights | 46.1 MB | 9a93f2265ee2 |
| checkpoint-10/rng_state.pth | Weights | 14.6 KB | 918e24cb285f |
| checkpoint-10/scheduler.pt | Weights | 1.5 KB | f47801d71158 |
| checkpoint-10/training_args.bin | Weights | 5.3 KB | 76dc0cc505c1 |
| checkpoint-100/adapter_model.safetensors | Weights | 90.2 MB | 5a3e63327f6b |
| checkpoint-100/optimizer.pt | Weights | 46.1 MB | 0a8f51ef1885 |
| checkpoint-100/rng_state.pth | Weights | 14.6 KB | b6955d5725b3 |
| checkpoint-100/scheduler.pt | Weights | 1.5 KB | cd4aad95257f |
| checkpoint-100/training_args.bin | Weights | 5.3 KB | 76dc0cc505c1 |
| checkpoint-110/adapter_model.safetensors | Weights | 90.2 MB | edcfeff65455 |
| checkpoint-110/optimizer.pt | Weights | 46.1 MB | d02dc51bbe31 |
| checkpoint-110/rng_state.pth | Weights | 14.6 KB | 34f601d16c4d |
| checkpoint-110/scheduler.pt | Weights | 1.5 KB | 7c63e4671f5c |
| checkpoint-110/training_args.bin | Weights | 5.3 KB | 76dc0cc505c1 |
| checkpoint-120/adapter_model.safetensors | Weights | 90.2 MB | a2ebccc492d6 |
| checkpoint-120/optimizer.pt | Weights | 46.1 MB | 7a1980f15dcd |
| checkpoint-120/rng_state.pth | Weights | 14.6 KB | 0291379080e6 |
| checkpoint-120/scheduler.pt | Weights | 1.5 KB | 8098b00a7c8d |
| checkpoint-120/training_args.bin | Weights | 5.3 KB | 76dc0cc505c1 |
| checkpoint-20/adapter_model.safetensors | Weights | 90.2 MB | a93a61093c67 |
| checkpoint-20/optimizer.pt | Weights | 46.1 MB | 406be7dc2075 |
| checkpoint-20/rng_state.pth | Weights | 14.6 KB | 66b5fecee4d7 |
| checkpoint-20/scheduler.pt | Weights | 1.5 KB | 0db5f604b963 |
| checkpoint-20/training_args.bin | Weights | 5.3 KB | 76dc0cc505c1 |
| checkpoint-30/adapter_model.safetensors | Weights | 90.2 MB | a1195bab21a7 |
| checkpoint-30/optimizer.pt | Weights | 46.1 MB | 171b736a9daf |
| checkpoint-30/rng_state.pth | Weights | 14.6 KB | 0f66068e2c4a |
| checkpoint-30/scheduler.pt | Weights | 1.5 KB | 0e64df414a9c |
| checkpoint-30/training_args.bin | Weights | 5.3 KB | 76dc0cc505c1 |
| checkpoint-40/adapter_model.safetensors | Weights | 90.2 MB | 56454654762a |
| checkpoint-40/optimizer.pt | Weights | 46.1 MB | 8febbe82c468 |
| checkpoint-40/rng_state.pth | Weights | 14.6 KB | 5a2499c4b3d0 |
| checkpoint-40/scheduler.pt | Weights | 1.5 KB | eeda7cfea60d |
| checkpoint-40/training_args.bin | Weights | 5.3 KB | 76dc0cc505c1 |
| checkpoint-50/adapter_model.safetensors | Weights | 90.2 MB | dda1d9626099 |
| checkpoint-50/optimizer.pt | Weights | 46.1 MB | 11ac22652a24 |
| checkpoint-50/rng_state.pth | Weights | 14.6 KB | 690c7d0f8a52 |
| checkpoint-50/scheduler.pt | Weights | 1.5 KB | d41630b9de17 |
| checkpoint-50/training_args.bin | Weights | 5.3 KB | 76dc0cc505c1 |
| checkpoint-60/adapter_model.safetensors | Weights | 90.2 MB | 6bac32a44b78 |
| checkpoint-60/optimizer.pt | Weights | 46.1 MB | 98f0426ce573 |
| checkpoint-60/rng_state.pth | Weights | 14.6 KB | 935b00d84e77 |
| checkpoint-60/scheduler.pt | Weights | 1.5 KB | 393bd8e22f04 |
| checkpoint-60/training_args.bin | Weights | 5.3 KB | 76dc0cc505c1 |
| checkpoint-70/adapter_model.safetensors | Weights | 90.2 MB | 7aef972d7f2f |
| checkpoint-70/optimizer.pt | Weights | 46.1 MB | 6d3f584fbcec |
| checkpoint-70/rng_state.pth | Weights | 14.6 KB | d5fff66cdd1b |
| checkpoint-70/scheduler.pt | Weights | 1.5 KB | 65033cb7e5ef |
| checkpoint-70/training_args.bin | Weights | 5.3 KB | 76dc0cc505c1 |
| checkpoint-80/adapter_model.safetensors | Weights | 90.2 MB | ff1b7a88436e |
| checkpoint-80/optimizer.pt | Weights | 46.1 MB | 582a27df05ba |
| checkpoint-80/rng_state.pth | Weights | 14.6 KB | f52747a87ef7 |
| checkpoint-80/scheduler.pt | Weights | 1.5 KB | 313bfb447631 |
| checkpoint-80/training_args.bin | Weights | 5.3 KB | 76dc0cc505c1 |
| checkpoint-90/adapter_model.safetensors | Weights | 90.2 MB | b618dac8ac61 |
| checkpoint-90/optimizer.pt | Weights | 46.1 MB | c0721b549d7e |
| checkpoint-90/rng_state.pth | Weights | 14.6 KB | 8ec25f2c61e8 |
| checkpoint-90/scheduler.pt | Weights | 1.5 KB | f3648bcd90e8 |
| checkpoint-90/training_args.bin | Weights | 5.3 KB | 76dc0cc505c1 |
| training_args.bin | Weights | 5.3 KB | 76dc0cc505c1 |
| adapter_config.json | Configuration | 1.3 KB | — |
| checkpoint-10/adapter_config.json | Configuration | 1.3 KB | — |
| checkpoint-10/trainer_state.json | Configuration | 8.3 KB | — |
| checkpoint-100/adapter_config.json | Configuration | 1.3 KB | — |
| checkpoint-100/trainer_state.json | Configuration | 72.3 KB | — |
| checkpoint-110/adapter_config.json | Configuration | 1.3 KB | — |
| checkpoint-110/trainer_state.json | Configuration | 78.8 KB | — |
| checkpoint-120/adapter_config.json | Configuration | 1.3 KB | — |
| checkpoint-120/trainer_state.json | Configuration | 86.5 KB | — |
| checkpoint-20/adapter_config.json | Configuration | 1.3 KB | — |
| checkpoint-20/trainer_state.json | Configuration | 16.0 KB | — |
| checkpoint-30/adapter_config.json | Configuration | 1.3 KB | — |
| checkpoint-30/trainer_state.json | Configuration | 22.4 KB | — |
| checkpoint-40/adapter_config.json | Configuration | 1.3 KB | — |
| checkpoint-40/trainer_state.json | Configuration | 30.0 KB | — |
| checkpoint-50/adapter_config.json | Configuration | 1.3 KB | — |
| checkpoint-50/trainer_state.json | Configuration | 36.4 KB | — |
| checkpoint-60/adapter_config.json | Configuration | 1.3 KB | — |
| checkpoint-60/trainer_state.json | Configuration | 44.1 KB | — |
| checkpoint-70/adapter_config.json | Configuration | 1.3 KB | — |
| checkpoint-70/trainer_state.json | Configuration | 50.5 KB | — |
| checkpoint-80/adapter_config.json | Configuration | 1.3 KB | — |
| checkpoint-80/trainer_state.json | Configuration | 58.2 KB | — |
| checkpoint-90/adapter_config.json | Configuration | 1.3 KB | — |
| checkpoint-90/trainer_state.json | Configuration | 64.7 KB | — |
| README.md | Documentation | 5.2 KB | — |
| checkpoint-10/README.md | Documentation | 5.2 KB | — |
| checkpoint-100/README.md | Documentation | 5.2 KB | — |
| checkpoint-110/README.md | Documentation | 5.2 KB | — |
| checkpoint-120/README.md | Documentation | 5.2 KB | — |
| checkpoint-20/README.md | Documentation | 5.2 KB | — |
| checkpoint-30/README.md | Documentation | 5.2 KB | — |
| checkpoint-40/README.md | Documentation | 5.2 KB | — |
| checkpoint-50/README.md | Documentation | 5.2 KB | — |
| checkpoint-60/README.md | Documentation | 5.2 KB | — |
| checkpoint-70/README.md | Documentation | 5.2 KB | — |
| checkpoint-80/README.md | Documentation | 5.2 KB | — |
| checkpoint-90/README.md | Documentation | 5.2 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 1.7 GB
Released by Julia Rezvani through its official repository on Hugging Face.
Built From
- Described by arXiv:1910.09700
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 1.7 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.