---
title: llamaphi-3-128k-instruct
canonical_url: "https://www.modelscope.ai/models/mrfakename/llamaphi-3-128k-instruct"
md_url: "https://www.modelscope.ai/models/mrfakename/llamaphi-3-128k-instruct.md"
repository: mrfakename/llamaphi-3-128k-instruct
last_updated: 2025-12-16
license: mit
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - llama
architectures:
  - LlamaForCausalLM
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 128
stars: 0
---

# llamaphi-3-128k-instruct

> llamaphi-3-128k-instruct - An open-source model by mrfakename on ModelScope. Phi 3 128K instruct weights in the Llama format.

mrfakename/llamaphi-3-128k-instruct is a text-generation model on ModelScope. licensed under mit.

- **Repository**: mrfakename/llamaphi-3-128k-instruct
- **License**: mit
- **Tasks**: text-generation
- **Downloads**: 128
- **Stars**: 0
- **Last updated**: 2025-12-16

Source: https://www.modelscope.ai/models/mrfakename/llamaphi-3-128k-instruct

---

[Phi 3 128K instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct) weights in the Llama format.

All credit goes to @vonjack for their useful [conversion script](https://huggingface.co/vonjack/Phi-3-mini-4k-instruct-LLaMAfied) as well as index files which were used to make this.

Check out their version for the [4k model](https://huggingface.co/vonjack/Phi-3-mini-4k-instruct-LLaMAfied)!