deepseek-r1:70b-llama-distill-q4_K_M - Ollama 框架

deepseek-r1

DeepSeek 的第一代推理模型，在數學、程式碼和推理任務方面，效能可與 OpenAI-o1 相媲美，包括六個從 DeepSeek-R1 基於 Llama 和 Qwen 提煉出的密集模型。

1.5b 7b 8b 14b 32b 70b 671b

25.5M 下載次數更新於 4 週前

更新於 7 週前

7 週前

0c1615a8ca32 · 43GB

{ "stop": [ "<｜句子開頭｜>", "<｜句子結尾｜>",

{{- if .System }}{{ .System }}{{ end }} {{- range $i, $_ := .Messages }} {{- $last := eq (len (slice

MIT License Copyright (c) 2023 DeepSeek Permission is hereby granted, free of charge, to any perso

Readme

DeepSeek 的第一代推理模型，在數學、程式碼和推理任務中，效能可與 OpenAI-o1 相媲美。

模型

DeepSeek-R1

ollama run deepseek-r1:671b

提煉模型

DeepSeek 團隊已證明，大型模型的推理模式可以提煉到較小的模型中，相較於透過強化學習在小型模型上發現的推理模式，可以產生更好的效能。

以下是透過微調針對研究社群廣泛使用的幾個密集模型，並使用 DeepSeek-R1 產生的推理資料所建立的模型。評估結果表明，提煉後較小的密集模型在基準測試中表現非常出色。

DeepSeek-R1-Distill-Qwen-1.5B

ollama run deepseek-r1:1.5b

DeepSeek-R1-Distill-Qwen-7B

ollama run deepseek-r1:7b

DeepSeek-R1-Distill-Llama-8B

ollama run deepseek-r1:8b

DeepSeek-R1-Distill-Qwen-14B

ollama run deepseek-r1:14b

DeepSeek-R1-Distill-Qwen-32B

ollama run deepseek-r1:32b

DeepSeek-R1-Distill-Llama-70B

ollama run deepseek-r1:70b

授權條款

模型權重根據 MIT 授權條款授權。DeepSeek-R1 系列支援商業用途，允許任何修改和衍生作品，包括但不限於為了訓練其他 LLM 而進行的提煉。請注意

Qwen 提煉模型衍生自最初根據 Apache 2.0 授權條款授權的 Qwen-2.5 系列，現在使用 DeepSeek-R1 精選的 80 萬個樣本進行微調。

Llama 8B 提煉模型衍生自最初根據 llama3.1 授權條款授權的 Llama3.1-8B-Base。

Llama 70B 提煉模型衍生自最初根據 llama3.3 授權條款授權的 Llama3.3-70B-Instruct。

<img src="/assets/library/deepseek-v3/069ccc94-63b0-41e6-b2b3-e8e56068ab1a" width="320" />

DeepSeek's first-generation reasoning models, achieving performance comparable to OpenAI-o1 across math, code, and reasoning tasks.

## Models

**DeepSeek-R1**

```
ollama run deepseek-r1:671b
```

### Distilled models

DeepSeek team has demonstrated that the reasoning patterns of larger models can be distilled into smaller models, resulting in better performance compared to the reasoning patterns discovered through RL on small models.

Below are the models created via fine-tuning against several dense models widely used in the research community using reasoning data generated by DeepSeek-R1. The evaluation results demonstrate that the distilled smaller dense models perform exceptionally well on benchmarks.

**DeepSeek-R1-Distill-Qwen-1.5B**

```
ollama run deepseek-r1:1.5b
```

**DeepSeek-R1-Distill-Qwen-7B**

```
ollama run deepseek-r1:7b
```

**DeepSeek-R1-Distill-Llama-8B**

```
ollama run deepseek-r1:8b
```

**DeepSeek-R1-Distill-Qwen-14B**

```
ollama run deepseek-r1:14b
```

**DeepSeek-R1-Distill-Qwen-32B**

```
ollama run deepseek-r1:32b
```

**DeepSeek-R1-Distill-Llama-70B**

```
ollama run deepseek-r1:70b
```

![deepseek](/assets/library/deepseek-r1/e44d096e-fa46-4cae-b2f2-53991e8c8da0)

### License

The model weights are licensed under the MIT License. DeepSeek-R1 series support commercial use, allow for any modifications and derivative works, including, but not limited to, distillation for training other LLMs. Please note that:

The Qwen distilled models are derived from Qwen-2.5 series, which are originally licensed under Apache 2.0 License, and now finetuned with 800k samples curated with DeepSeek-R1.

The Llama 8B distilled model is derived from Llama3.1-8B-Base and is originally licensed under llama3.1 license.

The Llama 70B distilled model is derived from Llama3.3-70B-Instruct and is originally licensed under llama3.3 license.

貼上、拖曳或點擊以上傳圖片 (.png, .jpeg, .jpg, .svg, .gif)