Downloads · 30 days
9
9% of all-time downloads
YAESEONG/rag-note-gguf
rag-note-gguf is a machine learning model from YAESEONG. 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 llama3.2.
--- language: - ko - en license: llama3.2 tags: - gguf - ollama - llama.cpp - fine-tuned - instruction-tuning pipelinetag: text-generation basemodel: unsloth/Llama-3.2-1B-Instruct ---
Downloads · 30 days
9
9% of all-time downloads
All-time downloads
105
Public
Repo size
2.4 GB
Likes
0
Public
Click a slice to open those files.
.gguf808 MB · 100%
From the Hugging Face model README
language:
논문 method 텍스트를 입력하면 Workflow + Unit Operation(JSON) 형태로 정리해 주는 모델입니다.
RAG 결과를 연구노트 템플릿으로 빠르게 변환하고, 사람이 수정하는 흐름(MVP)을 목표로 합니다.
merged_model_fp32.Q4_K_M.ggufFROM ./merged_model_fp32.Q4_K_M.gguf
ollama create rag-note-gguf -f Modelfile
ollama run rag-note-gguf "Instruction:
Extract workflow and equipment/software into JSON with the given schema.
Input:
PCR amplification at 95C for 30s...
Output:"
./llama-cli \
-m merged_model_fp32.Q4_K_M.gguf \
-p "Instruction:\nExtract workflow and equipment/software into JSON with the given schema.\n\nInput:\nPCR amplification...\n\nOutput:\n" \
-n 512
Instruction:
Extract workflow and equipment/software into JSON with the given schema.
Input:
<method text>
Output:
이 모델은 base model 라이선스에 따릅니다.
※ base model이 Llama 3.2 계열이면 보통 llama3.2로 맞춰야 합니다.
run_ollama_and_build.py)에서 처리합니다.
---