Spaces:

build-small-hackathon
/

AI-Puppet-Theater

Paused

App Files Files Community

AI-Puppet-Theater / finetune /scripts

170 kB

Ctrl+K

Ctrl+K

3 contributors

History: 10 commits

ShubhamSetia's picture

finetune: add GGUF publish prep workflow

9ff127f about 2 months ago

audit_actor_sft.py

11.9 kB
finetune: add Actor SFT v1 audit and eval hardening about 2 months ago
convert_actor_merged_to_gguf.sh

3.31 kB
finetune: add merge and GGUF conversion tooling about 2 months ago
eval_actor_gguf.py

19 kB
finetune: add GGUF eval harness with chatml prompt about 2 months ago
eval_minicpm5_actor_lora.py

23.6 kB
finetune: add merge and GGUF conversion tooling about 2 months ago
generate_actor_sft_v0.py

68.8 kB
finetune: add Actor SFT v1 audit and eval hardening about 2 months ago
merge_actor_lora.py

3.45 kB
finetune: add merge and GGUF conversion tooling about 2 months ago
prepare_gguf_publish.py

5.44 kB
finetune: add GGUF publish prep workflow about 2 months ago
publish_actor_lora_adapter.py

4.18 kB
finetune: add Hugging Face publish tooling about 2 months ago
publish_actor_sft_dataset.py

3.68 kB
finetune: add Hugging Face publish tooling about 2 months ago
train_minicpm5_actor_lora.py

12.7 kB
finetune: add Modal actor LoRA training pipeline about 2 months ago
validate_actor_sft.py

13.6 kB
finetune: add Actor SFT v1 audit and eval hardening about 2 months ago