---
title: granite-prisma-ft
canonical_url: "https://www.modelscope.cn/models/mlx-community/granite-prisma-ft"
md_url: "https://www.modelscope.cn/models/mlx-community/granite-prisma-ft.md"
repository: mlx-community/granite-prisma-ft
last_updated: 2026-01-11
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - granitemoehybrid
architectures:
  - GraniteMoeHybridForCausalLM
parameters: 352.4M
tensor_type:
  - F32
  - BF16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
inference_backends:
  - "deploy_task text/emb"
  - "vllm 0.9.2"
downloads: 26
stars: 0
tags:
  - mlx
---

# granite-prisma-ft

> granite-prisma-ft - mlx-community 在 ModelScope 开源的模型。mstyslavity/granite-finetuned-prisma-mergeshard2

mlx-community/granite-prisma-ft 是 ModelScope 魔搭社区上的 352.4M 参数text-generation模型，可用 deploy_task text/emb、vllm 0.9.2 部署。

- **Repository**: mlx-community/granite-prisma-ft
- **Tasks**: text-generation
- **Parameters**: 352.4M
- **Inference backends**: deploy_task text/emb, vllm 0.9.2
- **Tags**: mlx
- **Downloads**: 26
- **Stars**: 0
- **Last updated**: 2026-01-11

Source: https://www.modelscope.cn/models/mlx-community/granite-prisma-ft

---

# mstyslavity/granite-finetuned-prisma-mergeshard2

## Use with mlx

```bash
pip install mlx-lm
```

```python
from mlx_lm import load, generate

model, tokenizer = load("mstyslavity/granite-finetuned-prisma-mergeshard2")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```