btfox

tencent__Hy-MT2-1.8B

File list

  • model.safetensors-3.8 GB
  • tokenizer.json-9.09 MB
  • imgs/main_result.png-3.66 MB
  • tokenizer_config.json-161.93 KB
  • imgs/logo-zh.png-68.27 KB
  • imgs/logo-en.png-64.32 KB
  • train/data/example_data.jsonl-27.1 KB
  • train/deepspeed_support/train.py-25.06 KB
  • train/tools/convert_ckpt_to_outer.py-22.99 KB
  • train/tools/check_converted.py-15.2 KB
  • train/README.md-15.06 KB
  • train/deepspeed_support/train_dense.py-14.56 KB
  • README.md-14.42 KB
  • train/README_CN.md-13.83 KB
  • README_CN.md-13.44 KB
  • LICENSE.txt-11.36 KB
  • train/llama_factory_support/hy_v3_patches.py-8.58 KB
  • train/llama_factory_support/convert_zero_to_hf.sh-5.79 KB
  • train/deepspeed_support/train_dense_lora.sh-4.96 KB
  • train/deepspeed_support/train_dense.sh-4.74 KB
  • train/llama_factory_support/train_lf_dense.sh-4.1 KB
  • train/llama_factory_support/train_lf.sh-3.81 KB
  • train/llama_factory_support/hy_dense_template.py-3.53 KB
  • train/deepspeed_support/train_lora.sh-3.52 KB
  • train/deepspeed_support/train.sh-3.39 KB
  • train/llama_factory_support/train_hy_dense.py-2.91 KB
  • train/deepspeed_support/merge_lora_weight.py-2.45 KB
  • train/llama_factory_support/train_hy_v3.py-2.42 KB
  • train/llama_factory_support/hy_v3_template.py-1.89 KB
  • config.json-1.32 KB
  • train/llama_factory_support/hy_v3_lora_sft.yaml-1.2 KB
  • train/llama_factory_support/hy_dense_1_8b_lora_sft.yaml-1.17 KB
  • train/llama_factory_support/hy_dense_7b_lora_sft.yaml-1.16 KB
  • train/deepspeed_support/ds_zero3_no_offload.json-1.07 KB
  • train/deepspeed_support/ds_zero3_offload.json-1.07 KB
  • train/llama_factory_support/hy_dense_1_8b_full_sft.yaml-1.05 KB
  • train/llama_factory_support/hy_v3_full_sft.yaml-1.05 KB
  • train/llama_factory_support/hy_dense_7b_full_sft.yaml-1.05 KB
  • train/llama_factory_support/dataset_info.json-974 Bytes
  • train/llama_factory_support/ds_zero3_offload.json-954 Bytes
  • train/deepspeed_support/ds_zero3_offload_no_auto.json-944 Bytes
  • train/llama_factory_support/ds_zero2_offload.json-892 Bytes
  • train/llama_factory_support/ds_zero2_offload_lora.json-795 Bytes
  • train/deepspeed_support/ds_zero2_offload.json-676 Bytes
  • chat_template.jinja-654 Bytes
  • train/deepspeed_support/ds_zero2_no_offload.json-528 Bytes
  • special_tokens_map.json-488 Bytes
  • train/deepspeed_support/merge_lora_weight.sh-269 Bytes
  • generation_config.json-221 Bytes
  • train/requirements.txt-159 Bytes