Open-weight model
fa-llamafactory-qwen25-7b-finetome-saves-de822650e1f4
by Wang davidwdw/fa-llamafactory-qwen25-7b-finetome-saves-de822650e1f4
fa-llamafactory-qwen25-7b-finetome-saves-de822650e1f4 is an open-weight model from Wang. Its published files total 18.6 GB.
Tier: Qwen2.5-7B-Instruct LoRA SFT on FineTome-100k (checkpoints 500-2500, final adapter) + merged model Use the exact recorded revision and verify SHA256SUMS. This package is a snapshot, not a live directory mirror.
Parameters—
Context—
Weights18.5 GB
License—
AccessOpen weights
Monthly Downloads—
Model Card
Tier: Qwen2.5-7B-Instruct LoRA SFT on FineTome-100k (checkpoints 500-2500, final adapter) + merged model Use the exact recorded revision and verify SHA256SUMS. This package is a snapshot, not a live directory mirror.
Excerpt from the card by Wang.
Identity and Version
- Repository
- davidwdw/fa-llamafactory-qwen25-7b-finetome-saves-de822650e1f4
- Publisher
- Wang
- 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
- 354a80e70506ad0b68808ccd4af57adbd653da70
- First published
- 2026-09-30
- Last updated
- 2026-09-30
Files and Weights
110 files, 18.6 GB in total. The weights are 43 files totalling 18.5 GB in bin, pt, pth, safetensors.
Weights43 files · 18.5 GB
Configuration24 files · 220.7 KB
Tokenizer18 files · 102.8 MB
Documentation9 files · 34.4 KB
Other15 files · 181.6 KB
Repository1 file · 2.3 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| payload/Qwen2.5-7B/lora/sft/adapter_model.safetensors | Weights | 161.5 MB | e39bc25e2d4d |
| payload/Qwen2.5-7B/lora/sft/checkpoint-1000/adapter_model.safetensors | Weights | 161.5 MB | d430209e5934 |
| payload/Qwen2.5-7B/lora/sft/checkpoint-1000/optimizer.pt | Weights | 323.3 MB | cd435ffda12c |
| payload/Qwen2.5-7B/lora/sft/checkpoint-1000/rng_state.pth | Weights | 14.2 KB | 8762e1b17da4 |
| payload/Qwen2.5-7B/lora/sft/checkpoint-1000/scheduler.pt | Weights | 1.1 KB | dcb9bc14d703 |
| payload/Qwen2.5-7B/lora/sft/checkpoint-1000/training_args.bin | Weights | 5.5 KB | 45eb5996dc73 |
| payload/Qwen2.5-7B/lora/sft/checkpoint-1500/adapter_model.safetensors | Weights | 161.5 MB | 724bf0e80a20 |
| payload/Qwen2.5-7B/lora/sft/checkpoint-1500/optimizer.pt | Weights | 323.3 MB | a6c9bd9273d5 |
| payload/Qwen2.5-7B/lora/sft/checkpoint-1500/rng_state.pth | Weights | 14.2 KB | eadbbc7f4a1e |
| payload/Qwen2.5-7B/lora/sft/checkpoint-1500/scheduler.pt | Weights | 1.1 KB | 2ae2214585b9 |
| payload/Qwen2.5-7B/lora/sft/checkpoint-1500/training_args.bin | Weights | 5.5 KB | 45eb5996dc73 |
| payload/Qwen2.5-7B/lora/sft/checkpoint-2000/adapter_model.safetensors | Weights | 161.5 MB | 79f72de8fab3 |
| payload/Qwen2.5-7B/lora/sft/checkpoint-2000/optimizer.pt | Weights | 323.3 MB | c287a610e30d |
| payload/Qwen2.5-7B/lora/sft/checkpoint-2000/rng_state.pth | Weights | 14.2 KB | e0f97acf7169 |
| payload/Qwen2.5-7B/lora/sft/checkpoint-2000/scheduler.pt | Weights | 1.1 KB | 7eb96c3e282e |
| payload/Qwen2.5-7B/lora/sft/checkpoint-2000/training_args.bin | Weights | 5.5 KB | 45eb5996dc73 |
| payload/Qwen2.5-7B/lora/sft/checkpoint-2500/adapter_model.safetensors | Weights | 161.5 MB | e39bc25e2d4d |
| payload/Qwen2.5-7B/lora/sft/checkpoint-2500/optimizer.pt | Weights | 323.3 MB | ab3d9408c28c |
| payload/Qwen2.5-7B/lora/sft/checkpoint-2500/rng_state.pth | Weights | 14.2 KB | 0449b640afce |
| payload/Qwen2.5-7B/lora/sft/checkpoint-2500/scheduler.pt | Weights | 1.1 KB | f3560f9c3262 |
| payload/Qwen2.5-7B/lora/sft/checkpoint-2500/training_args.bin | Weights | 5.5 KB | 45eb5996dc73 |
| payload/Qwen2.5-7B/lora/sft/checkpoint-500/adapter_model.safetensors | Weights | 161.5 MB | c5829aa3b5b4 |
| payload/Qwen2.5-7B/lora/sft/checkpoint-500/optimizer.pt | Weights | 323.3 MB | a6f3eca63a8a |
| payload/Qwen2.5-7B/lora/sft/checkpoint-500/rng_state.pth | Weights | 14.2 KB | 6daa08c9b739 |
| payload/Qwen2.5-7B/lora/sft/checkpoint-500/scheduler.pt | Weights | 1.1 KB | 37ef695e836d |
| payload/Qwen2.5-7B/lora/sft/checkpoint-500/training_args.bin | Weights | 5.5 KB | 45eb5996dc73 |
| payload/Qwen2.5-7B/lora/sft/training_args.bin | Weights | 5.5 KB | 45eb5996dc73 |
| payload/Qwen2.5-7B/lora/sft_smoke/adapter_model.safetensors | Weights | 161.5 MB | dd86f7f095f3 |
| payload/Qwen2.5-7B/lora/sft_smoke/checkpoint-32/adapter_model.safetensors | Weights | 161.5 MB | dd86f7f095f3 |
| payload/Qwen2.5-7B/lora/sft_smoke/checkpoint-32/optimizer.pt | Weights | 323.3 MB | 1cb6cdb61940 |
| payload/Qwen2.5-7B/lora/sft_smoke/checkpoint-32/rng_state.pth | Weights | 14.2 KB | 47f6a645e0d7 |
| payload/Qwen2.5-7B/lora/sft_smoke/checkpoint-32/scheduler.pt | Weights | 1.1 KB | ffad90ba2d44 |
| payload/Qwen2.5-7B/lora/sft_smoke/checkpoint-32/training_args.bin | Weights | 5.5 KB | 61ff759beefb |
| payload/Qwen2.5-7B/lora/sft_smoke/training_args.bin | Weights | 5.5 KB | 61ff759beefb |
| payload/merged_qwen_model/model-00001-of-00009.safetensors | Weights | 1.1 GB | 06006972c3be |
| payload/merged_qwen_model/model-00002-of-00009.safetensors | Weights | 2.0 GB | 035e1950ab6e |
| payload/merged_qwen_model/model-00003-of-00009.safetensors | Weights | 1.9 GB | 6a0f7efb69ac |
| payload/merged_qwen_model/model-00004-of-00009.safetensors | Weights | 1.9 GB | 07bf12806afc |
| payload/merged_qwen_model/model-00005-of-00009.safetensors | Weights | 1.9 GB | a5fa05c6b0a8 |
| payload/merged_qwen_model/model-00006-of-00009.safetensors | Weights | 1.9 GB | e76e44f2256d |
| payload/merged_qwen_model/model-00007-of-00009.safetensors | Weights | 1.9 GB | abfb3118772f |
| payload/merged_qwen_model/model-00008-of-00009.safetensors | Weights | 1.9 GB | 84006e4a8af9 |
| payload/merged_qwen_model/model-00009-of-00009.safetensors | Weights | 932.2 MB | 069559d9de14 |
| PROVENANCE.json | Configuration | 615 B | — |
| payload/Qwen2.5-7B/lora/sft/adapter_config.json | Configuration | 1.1 KB | — |
| payload/Qwen2.5-7B/lora/sft/all_results.json | Configuration | 206 B | — |
| payload/Qwen2.5-7B/lora/sft/checkpoint-1000/adapter_config.json | Configuration | 1.1 KB | — |
| payload/Qwen2.5-7B/lora/sft/checkpoint-1000/trainer_state.json | Configuration | 17.9 KB | — |
| payload/Qwen2.5-7B/lora/sft/checkpoint-1500/adapter_config.json | Configuration | 1.1 KB | — |
| payload/Qwen2.5-7B/lora/sft/checkpoint-1500/trainer_state.json | Configuration | 26.6 KB | — |
| payload/Qwen2.5-7B/lora/sft/checkpoint-2000/adapter_config.json | Configuration | 1.1 KB | — |
| payload/Qwen2.5-7B/lora/sft/checkpoint-2000/trainer_state.json | Configuration | 35.3 KB | — |
| payload/Qwen2.5-7B/lora/sft/checkpoint-2500/adapter_config.json | Configuration | 1.1 KB | — |
| payload/Qwen2.5-7B/lora/sft/checkpoint-2500/trainer_state.json | Configuration | 44.2 KB | — |
| payload/Qwen2.5-7B/lora/sft/checkpoint-500/adapter_config.json | Configuration | 1.1 KB | — |
| payload/Qwen2.5-7B/lora/sft/checkpoint-500/trainer_state.json | Configuration | 9.3 KB | — |
| payload/Qwen2.5-7B/lora/sft/train_results.json | Configuration | 206 B | — |
| payload/Qwen2.5-7B/lora/sft/trainer_state.json | Configuration | 44.4 KB | — |
| payload/Qwen2.5-7B/lora/sft_smoke/adapter_config.json | Configuration | 1.1 KB | — |
| payload/Qwen2.5-7B/lora/sft_smoke/all_results.json | Configuration | 201 B | — |
| payload/Qwen2.5-7B/lora/sft_smoke/checkpoint-32/adapter_config.json | Configuration | 1.1 KB | — |
| payload/Qwen2.5-7B/lora/sft_smoke/checkpoint-32/trainer_state.json | Configuration | 1.8 KB | — |
| payload/Qwen2.5-7B/lora/sft_smoke/train_results.json | Configuration | 201 B | — |
| payload/Qwen2.5-7B/lora/sft_smoke/trainer_state.json | Configuration | 2.0 KB | — |
| payload/merged_qwen_model/config.json | Configuration | 1.4 KB | — |
| payload/merged_qwen_model/generation_config.json | Configuration | 242 B | — |
| payload/merged_qwen_model/model.safetensors.index.json | Configuration | 27.8 KB | — |
| README.md | Documentation | 350 B | — |
| payload/Qwen2.5-7B/lora/sft/README.md | Documentation | 1.3 KB | — |
| payload/Qwen2.5-7B/lora/sft/checkpoint-1000/README.md | Documentation | 5.2 KB | — |
| payload/Qwen2.5-7B/lora/sft/checkpoint-1500/README.md | Documentation | 5.2 KB | — |
| payload/Qwen2.5-7B/lora/sft/checkpoint-2000/README.md | Documentation | 5.2 KB | — |
| payload/Qwen2.5-7B/lora/sft/checkpoint-2500/README.md | Documentation | 5.2 KB | — |
| payload/Qwen2.5-7B/lora/sft/checkpoint-500/README.md | Documentation | 5.2 KB | — |
| payload/Qwen2.5-7B/lora/sft_smoke/README.md | Documentation | 1.4 KB | — |
| payload/Qwen2.5-7B/lora/sft_smoke/checkpoint-32/README.md | Documentation | 5.2 KB | — |
| SHA256SUMS | Other | 13.3 KB | — |
| payload/Qwen2.5-7B/lora/sft/chat_template.jinja | Other | 2.5 KB | — |
| payload/Qwen2.5-7B/lora/sft/checkpoint-1000/chat_template.jinja | Other | 2.5 KB | — |
| payload/Qwen2.5-7B/lora/sft/checkpoint-1500/chat_template.jinja | Other | 2.5 KB | — |
| payload/Qwen2.5-7B/lora/sft/checkpoint-2000/chat_template.jinja | Other | 2.5 KB | — |
| payload/Qwen2.5-7B/lora/sft/checkpoint-2500/chat_template.jinja | Other | 2.5 KB | — |
| payload/Qwen2.5-7B/lora/sft/checkpoint-500/chat_template.jinja | Other | 2.5 KB | — |
| payload/Qwen2.5-7B/lora/sft/trainer_log.jsonl | Other | 48.7 KB | — |
| payload/Qwen2.5-7B/lora/sft/training_loss.png | Other | 56.3 KB | — |
| payload/Qwen2.5-7B/lora/sft_smoke/chat_template.jinja | Other | 2.5 KB | — |
| payload/Qwen2.5-7B/lora/sft_smoke/checkpoint-32/chat_template.jinja | Other | 2.5 KB | — |
| payload/Qwen2.5-7B/lora/sft_smoke/trainer_log.jsonl | Other | 1.3 KB | — |
| payload/Qwen2.5-7B/lora/sft_smoke/training_loss.png | Other | 39.1 KB | — |
| payload/merged_qwen_model/Modelfile | Other | 464 B | — |
| payload/merged_qwen_model/chat_template.jinja | Other | 2.5 KB | — |
| .gitattributes | Repository | 2.3 KB | — |
| payload/Qwen2.5-7B/lora/sft/checkpoint-1000/tokenizer.json | Tokenizer | 11.4 MB | 3fd169731d2c |
| payload/Qwen2.5-7B/lora/sft/checkpoint-1000/tokenizer_config.json | Tokenizer | 721 B | — |
| payload/Qwen2.5-7B/lora/sft/checkpoint-1500/tokenizer.json | Tokenizer | 11.4 MB | 3fd169731d2c |
| payload/Qwen2.5-7B/lora/sft/checkpoint-1500/tokenizer_config.json | Tokenizer | 721 B | — |
| payload/Qwen2.5-7B/lora/sft/checkpoint-2000/tokenizer.json | Tokenizer | 11.4 MB | 3fd169731d2c |
| payload/Qwen2.5-7B/lora/sft/checkpoint-2000/tokenizer_config.json | Tokenizer | 721 B | — |
| payload/Qwen2.5-7B/lora/sft/checkpoint-2500/tokenizer.json | Tokenizer | 11.4 MB | 3fd169731d2c |
| payload/Qwen2.5-7B/lora/sft/checkpoint-2500/tokenizer_config.json | Tokenizer | 721 B | — |
| payload/Qwen2.5-7B/lora/sft/checkpoint-500/tokenizer.json | Tokenizer | 11.4 MB | 3fd169731d2c |
| payload/Qwen2.5-7B/lora/sft/checkpoint-500/tokenizer_config.json | Tokenizer | 721 B | — |
| payload/Qwen2.5-7B/lora/sft/tokenizer.json | Tokenizer | 11.4 MB | 3fd169731d2c |
| payload/Qwen2.5-7B/lora/sft/tokenizer_config.json | Tokenizer | 721 B | — |
| payload/Qwen2.5-7B/lora/sft_smoke/checkpoint-32/tokenizer.json | Tokenizer | 11.4 MB | 3fd169731d2c |
| payload/Qwen2.5-7B/lora/sft_smoke/checkpoint-32/tokenizer_config.json | Tokenizer | 721 B | — |
| payload/Qwen2.5-7B/lora/sft_smoke/tokenizer.json | Tokenizer | 11.4 MB | 3fd169731d2c |
| payload/Qwen2.5-7B/lora/sft_smoke/tokenizer_config.json | Tokenizer | 721 B | — |
| payload/merged_qwen_model/tokenizer.json | Tokenizer | 11.4 MB | 3fd169731d2c |
| payload/merged_qwen_model/tokenizer_config.json | Tokenizer | 720 B | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 18.5 GB
Download from Wang
Released by Wang through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 18.5 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.