qwen3-14b-cpt-checkpoints is an open-weight model from icivilab (Alex). Its published files total 14.9 GB.
This model is a fine-tuned version of unsloth/Qwen3-14B-bnb-4bit. It has been trained using TRL. This model was trained with SFT.
Parameters—
Context—
Weights14.9 GB
License—
AccessOpen weights
Monthly Downloads—
Model Card
This model is a fine-tuned version of unsloth/Qwen3-14B-bnb-4bit. It has been trained using TRL. This model was trained with SFT.
Excerpt from the card by icivilab (Alex).
Identity and Version
- Repository
- tatoy/qwen3-14b-cpt-checkpoints
- Publisher
- icivilab (Alex)
- Task
- Not stated by the source
- Modality
- Other
- Library
- transformers
- Parameters
- Not stated by the source
- Languages
- sft, trl
- Revision
- b222c3521ad6121c901a85fb06f54d82a8246656
- First published
- 2026-10-10
- Last updated
- 2026-10-12
Files and Weights
56 files, 14.9 GB in total. The weights are 20 files totalling 14.9 GB in bin, pt, pth, safetensors.
Weights20 files · 14.9 GB
Configuration15 files · 34.9 KB
Tokenizer4 files · 22.9 MB
Documentation14 files · 69.4 KB
Other2 files · 9.3 KB
Repository1 file · 1.6 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| adapter_model.safetensors | Weights | 1.0 GB | 4ff462e73a85 |
| last-checkpoint/adapter_model.safetensors | Weights | 1.0 GB | 4ff462e73a85 |
| last-checkpoint/optimizer.pt | Weights | 524.0 MB | c27dc4f071a2 |
| last-checkpoint/rng_state.pth | Weights | 14.6 KB | 89645f9f6a2a |
| last-checkpoint/scaler.pt | Weights | 1.4 KB | d7367a712e23 |
| last-checkpoint/scheduler.pt | Weights | 1.5 KB | 4fb2cc878fde |
| last-checkpoint/training_args.bin | Weights | 6.0 KB | daa00fdcdb97 |
| loss-1.84/adapter_model.safetensors | Weights | 1.0 GB | 0290e50e4af8 |
| loss-1.86/adapter_model.safetensors | Weights | 1.0 GB | 0290e50e4af8 |
| loss-1.88/adapter_model.safetensors | Weights | 1.0 GB | dd20b9fe5e6f |
| loss-1.90/adapter_model.safetensors | Weights | 1.0 GB | dd20b9fe5e6f |
| loss-1.92/adapter_model.safetensors | Weights | 1.0 GB | dd20b9fe5e6f |
| loss-1.95/adapter_model.safetensors | Weights | 1.0 GB | 475e994359f0 |
| loss-2.00/adapter_model.safetensors | Weights | 1.0 GB | 71f6ccda623e |
| loss-2.05/adapter_model.safetensors | Weights | 1.0 GB | 1285288e104d |
| loss-2.10/adapter_model.safetensors | Weights | 1.0 GB | 5c4d0e7564ef |
| loss-2.20/adapter_model.safetensors | Weights | 1.0 GB | 17f039a80184 |
| loss-2.30/adapter_model.safetensors | Weights | 1.0 GB | d32b95732f66 |
| loss-2.40/adapter_model.safetensors | Weights | 1.0 GB | d32b95732f66 |
| training_args.bin | Weights | 6.0 KB | daa00fdcdb97 |
| adapter_config.json | Configuration | 1.3 KB | — |
| last-checkpoint/adapter_config.json | Configuration | 1.3 KB | — |
| last-checkpoint/trainer_state.json | Configuration | 16.5 KB | — |
| loss-1.84/adapter_config.json | Configuration | 1.3 KB | — |
| loss-1.86/adapter_config.json | Configuration | 1.3 KB | — |
| loss-1.88/adapter_config.json | Configuration | 1.3 KB | — |
| loss-1.90/adapter_config.json | Configuration | 1.3 KB | — |
| loss-1.92/adapter_config.json | Configuration | 1.3 KB | — |
| loss-1.95/adapter_config.json | Configuration | 1.3 KB | — |
| loss-2.00/adapter_config.json | Configuration | 1.3 KB | — |
| loss-2.05/adapter_config.json | Configuration | 1.3 KB | — |
| loss-2.10/adapter_config.json | Configuration | 1.3 KB | — |
| loss-2.20/adapter_config.json | Configuration | 1.3 KB | — |
| loss-2.30/adapter_config.json | Configuration | 1.3 KB | — |
| loss-2.40/adapter_config.json | Configuration | 1.3 KB | — |
| README.md | Documentation | 1.5 KB | — |
| last-checkpoint/README.md | Documentation | 5.2 KB | — |
| loss-1.84/README.md | Documentation | 5.2 KB | — |
| loss-1.86/README.md | Documentation | 5.2 KB | — |
| loss-1.88/README.md | Documentation | 5.2 KB | — |
| loss-1.90/README.md | Documentation | 5.2 KB | — |
| loss-1.92/README.md | Documentation | 5.2 KB | — |
| loss-1.95/README.md | Documentation | 5.2 KB | — |
| loss-2.00/README.md | Documentation | 5.2 KB | — |
| loss-2.05/README.md | Documentation | 5.2 KB | — |
| loss-2.10/README.md | Documentation | 5.2 KB | — |
| loss-2.20/README.md | Documentation | 5.2 KB | — |
| loss-2.30/README.md | Documentation | 5.2 KB | — |
| loss-2.40/README.md | Documentation | 5.2 KB | — |
| chat_template.jinja | Other | 4.7 KB | — |
| last-checkpoint/chat_template.jinja | Other | 4.7 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| last-checkpoint/tokenizer.json | Tokenizer | 11.4 MB | 476870a1f2fb |
| last-checkpoint/tokenizer_config.json | Tokenizer | 5.4 KB | — |
| tokenizer.json | Tokenizer | 11.4 MB | 476870a1f2fb |
| tokenizer_config.json | Tokenizer | 5.4 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 14.9 GB
Download from icivilab (Alex)
Released by icivilab (Alex) through its official repository on Hugging Face.
Built From
- Derived from unsloth/Qwen3-14B-bnb-4bit
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 14.9 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.