Modelpublic

TribeBlend/tribeblend-etl-deepseek-r1-distill-llama-8b

sourceHugging Facemitupdated 3mo agoView on Hugging Face

1likes27downloads

Model Card

tribeblend-etl-deepseek-r1-distill-llama-8b

DeepSeek R1 Distill Llama 8B fine-tuned for local self-correcting analytics.

Direct base-model GGUF (Q4KM) of deepseek-ai/DeepSeek-R1-Distill-Llama-8B, published for TribeBlend's local Data Chat runtime. TribeBlend grounds answers with Knowledge Graph context at prompt time and a model-aware agent harness, so the base instruction/reasoning model ships as-is (no fine-tuning).

—Base model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
—Provider / family: deepseek / deepseek-r1-distill
—Local runtime arch: llama
—Recommended profile: advanced
—Quantization: Q4KM
—Native context window: 131072

Usage

Designed for TribeBlend Data Chat, loaded via llama-cpp-2.

License

Inherits the upstream base-model license (mit); verify upstream terms before redistribution.