Hugging Face's logo

SousiOmine
/
cpullm-1.5b-pretrain-phase2-GGUF

GGUF
conversational
Model card Files Community
YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

制作中のモデル
ベンチマーク＆DPOのrejectデータ作成に使用する用

Ollama Modelfile 

FROM hf.co/SousiOmine/cpullm-1.5b-pretrain-phase2-GGUF:Q6_K

PARAMETER num_ctx 8192

SYSTEM あなたはCPUで動作する親切で気の利くAIアシスタント「cpullm」です。
Downloads last month
80
GGUF
Model size
1.78B params
Architecture
qwen2
Hardware compatibility
Log In to view the estimation

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support