Downloads · 30 days
11
20% of all-time downloads
jeongseokoh/llama3.1_8b_sft_SPEED-16-BoS_HotpotQA_lower_freeze
llama3.1_8b_sft_SPEED-16-BoS_HotpotQA_lower_freeze is a machine learning model from jeongseokoh. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
- Base model: jeongseokoh/llama3.18bsft-llopa-k16-nosystem - Source checkpoint: /data3/LLoPA/Capsule/modelfromdownstream/llama3.18bsft-llopa-k16-nosystem-teachercacheoverall.correctonly.all.q60000.r1-llopa-freeze-lowe…
Downloads · 30 days
11
20% of all-time downloads
All-time downloads
55
Public
Repo size
2.3 GB
Likes
0
Public
Click a slice to open those files.
.safetensors2.3 GB · 99%
From the Hugging Face model README
jeongseokoh/llama3.1_8b_sft-llopa-k16-no_system/data3/LLoPA/Capsule/model_from_downstream/llama3.1_8b_sft-llopa-k16-no_system-teacher_cache_overall.correct_only.all.q60000.r1-llopa-freeze-lower-k16-no_system/epoch_0train_upper_only=16) and resized tokenizer embeddings are included.