dominant-strategies/quai-igemm-qwen2.5-7b-w8a8

Quai InferenceGemm Qwen2.5-7B W8A8

Built with Qwen.

This repository contains InferenceGemm/Tensor Work Proof W8A8 quantized checkpoint artifacts derived from Qwen/Qwen2.5-7B. It is not an official Qwen release.

Contents

• —igemm-quantized-*.safetensors: quantized tensor payloads.
• —manifest.json: verifier-facing tensor manifest and Merkle roots.
• —index.json: checkpoint index for the quantized tensor shards.
• —runtime-alias-audit.json, when present: runtime-to-manifest alias audit.
• —tokenizer/config files copied from the base model directory.

Benchmark Status

Quantized checkpoint prepared locally; not included in the paper benchmark table because no promoted strict-live accepted-receipt benchmark has been recorded for 7B yet.

The paper benchmark rows were produced with strict SGLang Tensor Work Receipt emission and Go verification. The raw benchmark logs, receipts, runtime attestation keys, and local evidence packet are intentionally not uploaded to this model repository.

Loading

These files are intended for the Quai InferenceGemm harness in this repository, not vanilla transformers weight loading:

checkpoints/<this-checkpoint>/

Use the base model tokenizer/config with the InferenceGemm quantized payloads and verifier manifest.

Upstream

• —Base model: Qwen/Qwen2.5-7B
• —Upstream license: apache-2.0

Redistribution must comply with the upstream model license and applicable export control restrictions.