-
Restore v1.1-DPO model card (was overwritten by PEFT auto-generated card)
-
Upload tokenizer_config.json with huggingface_hub
-
Upload tokenizer.json with huggingface_hub
-
Upload ref/adapter_model.safetensors with huggingface_hub
-
Upload ref/adapter_config.json with huggingface_hub
-
Upload chat_template.jinja with huggingface_hub
-
Upload adapter_model.safetensors with huggingface_hub
-
Upload adapter_config.json with huggingface_hub
-
Upload README.md with huggingface_hub
-
Delete tokenizer_config.json with huggingface_hub
-
Delete tokenizer.json with huggingface_hub
-
Delete ref/adapter_model.safetensors with huggingface_hub
-
Delete ref/adapter_config.json with huggingface_hub
-
Delete processor_config.json with huggingface_hub
-
Delete model.safetensors with huggingface_hub
-
Delete generation_config.json with huggingface_hub
-
Delete config.json with huggingface_hub
-
Delete chat_template.jinja with huggingface_hub
-
Delete adapter_model.safetensors with huggingface_hub
-
Delete adapter_config.json with huggingface_hub
-
Upload tokenizer_config.json with huggingface_hub
-
Upload model.safetensors with huggingface_hub
-
Upload generation_config.json with huggingface_hub
-
Upload config.json with huggingface_hub
-
Upload chat_template.jinja with huggingface_hub
-
Upload README.md with huggingface_hub
-
Update README for v1.1-DPO release
-
Upload folder using huggingface_hub
-
Update model card: set base_model to Qwen/Qwen3.5-9B, add full dataset lineage
-
Add sampling settings, KV cache benchmarks, and temp warning
-
Fix base_model relation format to structured list
-
Add sampling settings, KV cache benchmarks, and base_model_relation
-
Add model card
-
Add LoRA adapter (r=64, CoderForge 50K)
-
initial commit
