superhot-13b-8k-no-rlhf-test-GGML

Note: LLAMA_ROPE_SCALE from PR #1967 needs to be set to 0.25

Merged base LLaMA and LoRA with this: https://github.com/tloen/alpaca-lora

Base LLaMA 13B: https://huggingface.co/huggyllama/llama-13b

SuperHOT 13B 8k no-rlhf-test LoRA: https://huggingface.co/kaiokendev/superhot-13b-8k-no-rlhf-test

BASE_MODEL=huggyllama_llama-13b LORA=kaiokendev_superhot-13b-8k-no-rlhf-test python export_hf_checkpoint.py

Converted and quantized with llama.cpp commit 447ccbe:

python convert.py superhot-13b-8k-safetensors --outtype f32 --outfile superhot-13b-8k-no-rlhf-test.ggmlv3.f32.bin
./bin/quantize superhot-13b-8k-no-rlhf-test.ggmlv3.f32.bin superhot-13b-8k-no-rlhf-test.ggmlv3.Q2_K.bin Q2_K
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.