ecommerce_ops · ecommerce · workflow
eBay develops e-Llama: continued pretraining of Llama 3.1 for e-commerce domain adaptation
General-purpose LLMs like GPT-4 and Claude are too costly and introduce data security risks for eBay's scale; they also lack e-commerce domain knowledge, while training a new LLM from scratch is prohibitively time- and resource-intensive.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Identify LLM adaptation need
eBay identifies the need for cost-effective, domain-specific LLMs as third-party services are impractical at scale.
Tools used
Llama 3.1Megatron-LMflash-attention-2NVIDIA H100NVLinkInfiniBand
Outcome
The e-Llama models achieve approximately 25% improvement in e-commerce benchmarks for English and about 30% for non-English, while retaining general-domain performance with only 1% degradation on NLU benchmarks for the 70B model.
What failed first
Third-party LLMs such as GPT-4 and Claude were found impractical for eBay's needs due to cost, data security risks, and limited fine-tuning on proprietary data.
Results
Time savedaround one month
Volumeapproximately 25%
Grounding & classification
Source type: technical build writeup
22 fields verified against source quotes.
content generationproduct catalogmetric backednamed customersource backedtools describedworkflow describedecommerceaccuracy improvementtechnical build writeupecommerce ops