Open-weight model
Nemotron-Mini-4B-Instruct_ckpt_SFT_baseline
by Rajat Ghosh rghosh8/Nemotron-Mini-4B-Instruct_ckpt_SFT_baseline
Nemotron-Mini-4B-Instruct_ckpt_SFT_baseline is an open-weight model from Rajat Ghosh. Its published files total 33.8 GB.
Parameters—
Context—
Weights33.7 GB
License—
AccessOpen weights
Monthly Downloads—
Model Card
The publisher has not written a card for this model.
Identity and Version
- Repository
- rghosh8/Nemotron-Mini-4B-Instruct_ckpt_SFT_baseline
- Publisher
- Rajat Ghosh
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- 6f6960179ef6bcd5f6935bfb42c4f610c54709d3
- First published
- 2026-10-13
- Last updated
- 2026-10-13
Files and Weights
32 files, 33.8 GB in total. The weights are 6 files totalling 33.7 GB in bin, safetensors.
Weights6 files · 33.7 GB
Configuration8 files · 38.1 KB
Tokenizer8 files · 139.2 MB
Documentation4 files · 13.3 KB
Other5 files · 21.2 KB
Repository1 file · 1.8 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| arc/checkpoint-140/adapter_model.safetensors | Weights | 92.3 MB | 5db16606284b |
| arc/checkpoint-140/training_args.bin | Weights | 5.8 KB | 9af297d25066 |
| arc/model.safetensors | Weights | 16.8 GB | 0c6a8ba97ea3 |
| sft-gsm8k/checkpoint-936/adapter_model.safetensors | Weights | 92.3 MB | f2d66c53a678 |
| sft-gsm8k/checkpoint-936/training_args.bin | Weights | 5.7 KB | 4e5a10f0519d |
| sft-gsm8k/model.safetensors | Weights | 16.8 GB | c8d1b3d3be1e |
| arc/checkpoint-140/adapter_config.json | Configuration | 1.2 KB | — |
| arc/checkpoint-140/trainer_state.json | Configuration | 4.9 KB | — |
| arc/config.json | Configuration | 793 B | — |
| arc/generation_config.json | Configuration | 163 B | — |
| sft-gsm8k/checkpoint-936/adapter_config.json | Configuration | 1.2 KB | — |
| sft-gsm8k/checkpoint-936/trainer_state.json | Configuration | 28.9 KB | — |
| sft-gsm8k/config.json | Configuration | 793 B | — |
| sft-gsm8k/generation_config.json | Configuration | 163 B | — |
| arc/README.md | Documentation | 1.4 KB | — |
| arc/checkpoint-140/README.md | Documentation | 5.2 KB | — |
| sft-gsm8k/README.md | Documentation | 1.4 KB | — |
| sft-gsm8k/checkpoint-936/README.md | Documentation | 5.2 KB | — |
| arc/chat_template.jinja | Other | 876 B | — |
| arc/checkpoint-140/chat_template.jinja | Other | 876 B | — |
| arc/train.log | Other | 17.7 KB | — |
| sft-gsm8k/chat_template.jinja | Other | 876 B | — |
| sft-gsm8k/checkpoint-936/chat_template.jinja | Other | 876 B | — |
| .gitattributes | Repository | 1.8 KB | — |
| arc/checkpoint-140/tokenizer.json | Tokenizer | 34.8 MB | b6ad04b2b067 |
| arc/checkpoint-140/tokenizer_config.json | Tokenizer | 353 B | — |
| arc/tokenizer.json | Tokenizer | 34.8 MB | b6ad04b2b067 |
| arc/tokenizer_config.json | Tokenizer | 353 B | — |
| sft-gsm8k/checkpoint-936/tokenizer.json | Tokenizer | 34.8 MB | b6ad04b2b067 |
| sft-gsm8k/checkpoint-936/tokenizer_config.json | Tokenizer | 353 B | — |
| sft-gsm8k/tokenizer.json | Tokenizer | 34.8 MB | b6ad04b2b067 |
| sft-gsm8k/tokenizer_config.json | Tokenizer | 353 B | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 33.7 GB
Download from Rajat Ghosh
Released by Rajat Ghosh through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 33.7 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.