---
title: Mantis-8B-clip-llama3-pretraind
canonical_url: "https://www.modelscope.cn/models/TIGER-Lab/Mantis-8B-clip-llama3-pretraind"
md_url: "https://www.modelscope.cn/models/TIGER-Lab/Mantis-8B-clip-llama3-pretraind.md"
repository: TIGER-Lab/Mantis-8B-clip-llama3-pretraind
last_updated: 2024-05-29
license: llama3
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - llava
architectures:
  - LlavaForConditionalGeneration
parameters: 8.4B
tensor_type:
  - BF16
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task vlm/text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 2833
stars: 0
tags:
  - generated_from_trainer
---

# Mantis-8B-clip-llama3-pretraind

> Mantis-8B-clip-llama3-pretraind - TIGER-Lab 在 ModelScope 开源的模型。See the Mantis-Instruct fine-tuned version here TIGER-Lab/Mantis-8B-clip-llama3. This checkpoint is just for experiments reproduction and does not serve as a functional model

TIGER-Lab/Mantis-8B-clip-llama3-pretraind 是 ModelScope 魔搭社区上的 8.4B 参数text-generation模型，采用 llama3 许可，可用 deploy_task vlm/text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: TIGER-Lab/Mantis-8B-clip-llama3-pretraind
- **License**: llama3
- **Tasks**: text-generation
- **Parameters**: 8.4B
- **Inference backends**: deploy_task vlm/text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: generated_from_trainer
- **Downloads**: 2833
- **Stars**: 0
- **Last updated**: 2024-05-29

Source: https://www.modelscope.cn/models/TIGER-Lab/Mantis-8B-clip-llama3-pretraind

---

**See the Mantis-Instruct fine-tuned version here [TIGER-Lab/Mantis-8B-clip-llama3](https://huggingface.co/TIGER-Lab/Mantis-8B-clip-llama3). This checkpoint is just for experiments reproduction and does not serve as a functional model**