---
title: Hermes-2-Theta-Llama-3-8B-8bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Hermes-2-Theta-Llama-3-8B-8bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Hermes-2-Theta-Llama-3-8B-8bit.md"
repository: mlx-community/Hermes-2-Theta-Llama-3-8B-8bit
last_updated: 2024-12-20
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - llama
architectures:
  - LlamaForCausalLM
base_model:
  - NousResearch/Hermes-2-Pro-Llama-3-8B
base_model_relation: finetune
parameters: 2.3B
tensor_type:
  - F16
  - U32
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 1007
stars: 0
tags:
  - gpt
  - llm
  - "large language model"
  - nous-research
  - nous-hermes
  - Llama-3
  - instruct
  - finetune
  - chatml
  - DPO
  - RLHF
  - gpt4
  - "synthetic data"
  - distillation
  - "function calling"
  - "json mode"
  - axolotl
  - merges
---

# Hermes-2-Theta-Llama-3-8B-8bit

> Hermes-2-Theta-Llama-3-8B-8bit - mlx-community 在 ModelScope 开源的模型。mlx-community/Hermes-2-Theta-Llama-3-8B-8bit

mlx-community/Hermes-2-Theta-Llama-3-8B-8bit 是 ModelScope 魔搭社区上的 2.3B 参数text-generation模型，采用 apache-2.0 许可，基于 NousResearch/Hermes-2-Pro-Llama-3-8B 构建，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: mlx-community/Hermes-2-Theta-Llama-3-8B-8bit
- **License**: apache-2.0
- **Tasks**: text-generation
- **Parameters**: 2.3B
- **Base model**: NousResearch/Hermes-2-Pro-Llama-3-8B
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: gpt, llm, large language model, nous-research, nous-hermes, Llama-3, instruct, finetune, chatml, DPO, RLHF, gpt4, synthetic data, distillation, function calling, json mode, axolotl, merges
- **Downloads**: 1007
- **Stars**: 0
- **Last updated**: 2024-12-20

Source: https://www.modelscope.cn/models/mlx-community/Hermes-2-Theta-Llama-3-8B-8bit

---

# mlx-community/Hermes-2-Theta-Llama-3-8B-8bit

Model was converted to MLX format from [`NousResearch/Hermes-2-Theta-Llama-3-8B`](https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-8B) using mlx-lm version **0.14.3**.

Converted & uploaded by: @ucheog ([Uche Ogbuji](https://ucheog.carrd.co/)).

Refer to the [original model card](https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-8B) for more details on the model.

## Use with mlx

```sh
pip install mlx-lm
```

```python
from mlx_lm import load, generate

model, tokenizer = load('mlx-community/Hermes-2-Theta-Llama-3-8B-8bit')
response = generate(model, tokenizer, prompt='Hello! Tell me something good.', verbose=True)
```

## Conversion command

```sh
python -m mlx_lm.convert --hf-path NousResearch/Hermes-2-Theta-Llama-3-8B --mlx-path ~/.local/share/models/mlx/Hermes-2-Theta-Llama-3-8B -q --q-bits 8
```