初始化项目,由ModelHub XC社区提供模型

Model: kagelabs/KageAI-7B-v1.2
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-26 09:20:18 +08:00
commit 54f3e0cc6e
11 changed files with 282382 additions and 0 deletions

57
README.md Normal file
View File

@@ -0,0 +1,57 @@
---
base_model:
- kagelabs/KageAI-7B-v1.1
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- galore
- tech-specialist
license: apache-2.0
language:
- en
datasets:
- teknium/OpenHermes-2.5
---
# KageAI-7B-v1.2 (Technical Specialist)
Developed by **KageLabs**, KageAI-7B-v1.2 is the second iteration of the KageAI series. This version marks a significant shift from general purpose chat to **Specialized Technical Intelligence**.
This model was trained using **GaLore (Gradient Low-Rank Projection)**, allowing for deeper weight updates and superior technical reasoning compared to standard LoRA fine-tuning.
## 🚀 Model Details
- **Version:** 1.2
- **Developed by:** [KageLabs](https://huggingface.co/kagelabs)
- **Base Model:** Mistral-7B-v0.3
- **Training Method:** GaLore (Rank 128)
- **Primary Focus:** Hardware Architecture, Semiconductors, and System Troubleshooting.
## 🧠 Training Focus & Knowledge Base
v1.2 has been optimized to act as a **High-End Tech Guru**. Its internal knowledge base has been refined for:
- **Semiconductors:** Deep understanding of 3nm/2nm architectures, FinFET vs. GAA, and EUV lithography.
- **Hardware Engineering:** GPU tensor cores, VRAM banking, and micro-architecture bottlenecks.
- **PC & Infrastructure:** Thermal management, overclocking logic, and custom workstation builds.
- **Instruction Following:** Enforces a **Brevity Rule** for simple queries while providing exhaustive breakdowns for complex engineering problems.
## 🧪 Version Status & Known Gaps
- **Identity:** v1.2 has a strong technical core but may occasionally show identity drift (legacy data influence).
- **Brevity:** High success rate in 1-sentence responses, but complex reasoning can sometimes be verbose.
- **v1.3 Preview:** The upcoming v1.3 update will patch identity consistency and merge this technical depth with advanced coding logic.
## 🛠 Usage
This model uses the **ChatML** prompt format:
```text
<|im_start|>system
You are KageAI by KageLabs, a High-End Technology and Hardware Specialist.<|im_end|>
<|im_start|>user
{query}<|im_end|>
<|im_start|>assistant
```
---
*Developed with ❤️ by KageLabs using Unsloth.*