vipsehgal/qwen3-8b-jee-sft at main

qwen3-8b-jee-sft

16.4 GB

1 contributor

History: 12 commits

vipsehgal's picture

Add project report with full training and evaluation details

09508ee verified 16 days ago

sdpo_data
Add SDPO data files (rl_prompts, eval_prompts, judge_config, train) 18 days ago
.gitattributes
1.63 kB

Add SDPO data files (rl_prompts, eval_prompts, judge_config, train) 18 days ago
PROJECT_REPORT.md
18.4 kB

Add project report with full training and evaluation details 16 days ago
README.md
5.28 kB

Remove SDPO references from model card 17 days ago
chat_template.jinja
4.1 kB

Upload SFT fine-tuned Qwen3-8B for IIT JEE 23 days ago
config.json
786 Bytes

Upload SFT fine-tuned Qwen3-8B for IIT JEE 23 days ago
model-00001-of-00004.safetensors
5.29 GB
xet

Upload SFT fine-tuned Qwen3-8B for IIT JEE 23 days ago
model-00002-of-00004.safetensors
5.3 GB
xet

Upload SFT fine-tuned Qwen3-8B for IIT JEE 23 days ago
model-00003-of-00004.safetensors
4.55 GB
xet

jee finetune v2: retrained SFT on corrected Phase 2 data (14k examples, mojibake/PhysReason/PhysicsEval fixes) 18 days ago
model-00004-of-00004.safetensors
1.24 GB
xet

Upload SFT fine-tuned Qwen3-8B for IIT JEE 23 days ago
model.safetensors.index.json
34.5 kB

Upload SFT fine-tuned Qwen3-8B for IIT JEE 23 days ago
tokenizer.json
11.4 MB
xet

Upload SFT fine-tuned Qwen3-8B for IIT JEE 23 days ago
tokenizer_config.json
384 Bytes

Upload SFT fine-tuned Qwen3-8B for IIT JEE 23 days ago