Open-weight model
DeepSeek-R1-Distill-Qwen-1.5B_ckpt_SFT_baseline
by Rajat Ghosh rghosh8/DeepSeek-R1-Distill-Qwen-1.5B_ckpt_SFT_baseline
DeepSeek-R1-Distill-Qwen-1.5B_ckpt_SFT_baseline is an open-weight model from Rajat Ghosh. Its published files total 7.2 GB.
Parameters—
Context—
Weights7.2 GB
License—
AccessOpen weights
Monthly Downloads—
Model Card
The publisher has not written a card for this model.
Identity and Version
- Repository
- rghosh8/DeepSeek-R1-Distill-Qwen-1.5B_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
- a9956f7dda53a10fd23916bcbc1992f0dab0906f
- First published
- 2026-10-13
- Last updated
- 2026-10-13
Files and Weights
17 files, 7.2 GB in total. The weights are 3 files totalling 7.2 GB in bin, safetensors.
Weights3 files · 7.2 GB
Configuration4 files · 7.8 KB
Tokenizer4 files · 22.8 MB
Documentation2 files · 6.7 KB
Other3 files · 24.1 KB
Repository1 file · 1.6 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| arc/checkpoint-140/adapter_model.safetensors | Weights | 73.9 MB | 0f5f63c1208f |
| arc/checkpoint-140/training_args.bin | Weights | 5.8 KB | 6b03e4f91616 |
| arc/model.safetensors | Weights | 7.1 GB | 4c75fef7a070 |
| arc/checkpoint-140/adapter_config.json | Configuration | 1.2 KB | — |
| arc/checkpoint-140/trainer_state.json | Configuration | 5.0 KB | — |
| arc/config.json | Configuration | 1.4 KB | — |
| arc/generation_config.json | Configuration | 217 B | — |
| arc/README.md | Documentation | 1.4 KB | — |
| arc/checkpoint-140/README.md | Documentation | 5.2 KB | — |
| arc/chat_template.jinja | Other | 2.2 KB | — |
| arc/checkpoint-140/chat_template.jinja | Other | 2.2 KB | — |
| arc/train.log | Other | 19.6 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| arc/checkpoint-140/tokenizer.json | Tokenizer | 11.4 MB | f624f8136bc5 |
| arc/checkpoint-140/tokenizer_config.json | Tokenizer | 421 B | — |
| arc/tokenizer.json | Tokenizer | 11.4 MB | f624f8136bc5 |
| arc/tokenizer_config.json | Tokenizer | 421 B | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 7.2 GB
Download from Rajat Ghosh
Released by Rajat Ghosh through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 7.2 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.