Correct card to the corrected Ollama record: remove Aider 73.7 / GPT-4o catalog claims and concurrency figures, correct Files table to actual repo contents, correct license from MIT to Apache-2.0

README.md

@@ -33,18 +33,21 @@ tags:
 
 ## Summary
 
-Code-specialized distributed AI supporting 15-30 concurrent engineers across 4-8 edge devices. Built on Qwen2.5-Coder 32B with 92 programming languages and complete IP protection: the team's codebase never leaves its own infrastructure.
+A THOX configuration and distribution of Qwen2.5-Coder 32B for local software-engineering work and MeshStack deployments. Configuration-derived: THOX did not train these weights. Qwen2.5-Coder is Alibaba's code-specialized model family; per Alibaba's model record it covers 92 programming languages.
+
+> **Correction notice.** This card previously described the model as "GPT-4o competitive" and quoted an Aider score and team ROI figures; those were inherited catalog claims with no THOX-run evaluation behind them and have been removed. No benchmark, throughput, latency, concurrency, uptime, cost-saving, or compliance figure is claimed for this release. Earlier versions of this card also stated the license as MIT; that was incorrect (see License Terms).
 
 **Model ID:** Thox-ai/thox-cluster-code
 **Base model:** Qwen2.5-Coder 32B by Alibaba Cloud
 **Runnable build:** Ollama - `ollama run Thox-ai/thox-cluster-code`
-**License (THOX material):** MIT, Copyright 2025-2026 Thox.ai LLC (see License Terms)
+**License:** Apache License 2.0 (see License Terms)
 
 ## Files
 
 | File | Size | Purpose |
 |---|---:|---|
 | `.gitattributes` | 1,519 B | Repository file |
+| `README.md` | 7,711 | This model card |
 
 
 ## MeshStack Origin
@@ -80,17 +83,16 @@ runtime configuration, and this documentation.
 | Base model | Qwen2.5-Coder 32B (Alibaba Cloud) |
 | Parameters | 32B |
 | Size | 20 GB (Ollama listing) |
-| Deployment | 4-8 THOX edge devices, 10 Gbps interconnect, engineering VLAN |
+| Deployment | Local inference via Ollama; distributed orchestration via MeshStack (separate from this download) |
 | Context window | 128K tokens (served num_ctx 131072 in the Ollama configuration; the Ollama latest-tag figure of 32K is a display artifact) |
 | Quantization | Q4_K_M (GGUF) |
-| Concurrent users | 15-30 engineers |
-| Languages | 92 programming languages |
+| Languages | 92 programming languages (per Alibaba's model record) |
 
 ## Intended Use
 
-- Software teams: repository analysis, code review, architecture design, and test generation across a shared cluster
-- Startups and DevOps teams needing rapid prototyping and IaC/CI-CD help without sending code to a cloud assistant
-- QA engineering: test automation, coverage analysis, and security testing with complete IP protection
+- Software teams analysing repositories and reviewing code locally
+- Startups and DevOps teams prototyping and working with infrastructure-as-code
+- QA and test-automation assistance on private codebases
 
 ## How to Use
 
@@ -124,12 +126,12 @@ section will be updated with method and results when a THOX-run
 evaluation lands; until then, treat quoted figures as the original
 catalog's claims, not as independently verified measurements.
 
-Catalog notes for this model: Catalog-reported: Aider benchmark 73.7 for code repair, described on the original card as GPT-4o competitive.
+Catalog notes for this model: No THOX-run evaluation has been published for this model. Catalog claims that appeared here previously (an Aider score and a GPT-4o comparison) were removed; they were inherited catalog claims with no THOX-run evaluation behind them.
 
 ## Limitations
 
 - Specialized for software engineering; not a general-purpose chat model
-- Cluster size 4-8 devices; requires 10 Gbps managed switching
+- Local deployment only in this distribution; behavior and speed depend entirely on the operator's hardware and configuration
 - Generated code requires human review before production use
 
 - All processing is local by design; the model has no access to online
@@ -139,7 +141,7 @@ Catalog notes for this model: Catalog-reported: Aider benchmark 73.7 for code re
 
 ## Hardware Reference (from the original card)
 
-Per device: minimum 32 GB RAM, 30 GB storage, NVIDIA Jetson Orin AGX (32GB VRAM), 10 Gbps network. Recommended 64 GB RAM, 50 GB NVMe SSD, dual 10 Gbps paths.
+Per device: minimum 32 GB RAM, 30 GB storage, NVIDIA Jetson Orin AGX class GPU (32GB VRAM), 10 Gbps network for clustered use. Recommended 64 GB RAM, 50 GB NVMe SSD.
 
 ## License Terms