---
title: Nemo-Humanities
canonical_url: "https://www.modelscope.cn/models/ConicCat/Nemo-Humanities"
md_url: "https://www.modelscope.cn/models/ConicCat/Nemo-Humanities.md"
repository: ConicCat/Nemo-Humanities
last_updated: 2026-03-17
license: apache-2.0
model_type:
  - mistral
architectures:
  - MistralForCausalLM
base_model:
  - mistralai/Mistral-Nemo-Instruct-2407
base_model_relation: finetune
parameters: 12.2B
tensor_type:
  - BF16
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 12
stars: 0
---

# Nemo-Humanities

> Nemo-Humanities - ConicCat 在 ModelScope 开源的模型。A finetune of nemo produced to test the theory that because the humanities (writing, social intelligence, roleplay, and theory of mind) seem to cross generalize, training all of them at once is superior to…

ConicCat/Nemo-Humanities 是 ModelScope 魔搭社区上的 12.2B 参数机器学习模型，采用 apache-2.0 许可，基于 mistralai/Mistral-Nemo-Instruct-2407 构建，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: ConicCat/Nemo-Humanities
- **License**: apache-2.0
- **Parameters**: 12.2B
- **Base model**: mistralai/Mistral-Nemo-Instruct-2407
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Downloads**: 12
- **Stars**: 0
- **Last updated**: 2026-03-17

Source: https://www.modelscope.cn/models/ConicCat/Nemo-Humanities

---

A finetune of nemo produced to test the theory that because the humanities (writing, social intelligence, roleplay, and theory of mind) seem to cross generalize, training all of them at once is superior to focusing on any one field.