Downloads · 30 days
0
superhot-30b-8k-no-rlhf-test-GGML
tmpupload/superhot-30b-8k-no-rlhf-test-GGML
superhot-30b-8k-no-rlhf-test-GGML is a machine learning model from tmpupload. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as other.
Note: LLAMAROPESCALE from PR 1967 needs to be set to 0.25
Access
Public
Updated Jun 27, 2023
Repo size
291 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin291 GB · 100%
At a glance
- License
- other
- Access
- Public
- Created
- Jun 26, 2023
- Updated
- Jun 27, 2023
- SHA
- 4250648b
Model card
From the Hugging Face model README
superhot-30b-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 30B: https://huggingface.co/huggyllama/llama-30b
SuperHOT 30B 8k no-rlhf-test LoRA: https://huggingface.co/kaiokendev/superhot-30b-8k-no-rlhf-test
BASE_MODEL=huggyllama_llama-30b LORA=kaiokendev_superhot-30b-8k-no-rlhf-test python export_hf_checkpoint.py
Converted and quantized with llama.cpp commit 447ccbe:
python convert.py superhot-30b-8k-safetensors --outtype f32 --outfile superhot-30b-8k-no-rlhf-test.ggmlv3.f32.bin
./bin/quantize superhot-30b-8k-no-rlhf-test.ggmlv3.f32.bin superhot-30b-8k-no-rlhf-test.ggmlv3.Q2_K.bin Q2_K
- License
- other
- Created
- Jun 26, 2023
- Updated
- Jun 27, 2023