Models

trained_llama_stanford_format

alpaca-base-7b

TestU

alpaca-doctor-7b

alpaca-doctor-7b-v2

kamll

llama_7b_ru_turbo_alpaca_lora_merged

llama-7b-hf

llama-se-rl-finetune-128-8-8-1.4e-5step_1200-adapter-merged

llama-7B-alpaca-30p

alpaca-lora

llama-se-rl-finetune-128-8-8-1.4e-5_adamstep_600-adapter-merged

llama-se-rl-finetune-128-8-8-1.4e-5_adamstep_1000-adapter-merged

llama-se-rl-finetune-128-8-8-1.4e-5_adamstep_1100-adapter-merged

llama-se-rl-finetune-128-8-8-1.4e-5_adamstep_800-adapter-merged

vicuna-7b

llama-7b

llama-7b-hf-20230407

LGeM-7B

koala-7b

llama-vicuna-7b

pretrained7b-v1

pretrained7b-bfloat16-cuda

vicuna-7b

vicuna-7b

vicuna-7b

vicuna-7b

llama-7B-sparsetest-c4-25pct-128blksz

llama-7B-sparsetest-c4-75pct-128blksz

vicuna_7B_vanilla

koala_7B_vanilla

chimera-inst-chat-7b-delta

wombat-7b-delta

wombat-7b-gpt4-delta

llama-rl-peft

Vicuna-7B

llama-7b-hf-baize-lora-bf16

Stack-LLAMA-merged-Adapter

Vicuna-7B

llama-7b-hf-20230416

alpaca-loraa

Linly-Chinese-LLaMA-7b-hf