---
license: llama3.1
model_name: Reflection-Llama-3.1-70B
base_model: mattshumer/ref_70_e3
inference: false
model_creator: Meta Llama3
model_type: llama
pipeline_tag: text-generation
library_name: transformers
quantized_by: Second State Inc.
---

<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->

# Reflection-Llama-3.1-70B-GGUF

## Original Model

[mattshumer/ref_70_e3](https://huggingface.co/mattshumer/ref_70_e3)

- The recommended system prompt for this model

```text
You are a world-class AI system, capable of complex reasoning and reflection. Reason through the query inside <thinking> tags, and then provide your final response inside <output> tags. If you detect that you made a mistake in your reasoning at any point, correct yourself inside <reflection> tags.
```

- Tips for performance

  - Recommended `temperature`: `0.5`
  - Recommended `top_p`: `0.95`
  - For increased accuracy, append `Think carefully.` at the end of your messages.


## Run with LlamaEdge

- LlamaEdge version: [v0.12.4](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.12.4) and above

- Prompt template

  - Prompt type: `llama-3-chat`

  - Prompt string

    ```text
    <|begin_of_text|><|start_header_id|>system<|end_header_id|>

    {{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>

    {{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

    {{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>

    {{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
    ```

- Context size: `128000`

- Run as LlamaEdge service

  ```bash
  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Reflection-Llama-3.1-70B-Q5_K_M.gguf \
    llama-api-server.wasm \
    --prompt-template llama-3-chat \
    --ctx-size 128000 \
    --model-name Llama-3.1-70b
  ```

- Run as LlamaEdge command app

  ```bash
  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Reflection-Llama-3.1-70B-Q5_K_M.gguf \
    llama-chat.wasm \
    --prompt-template llama-3-chat \
    --ctx-size 128000
  ```

## Quantized GGUF Models

| Name | Quant method | Bits | Size | Use case |
| ---- | ---- | ---- | ---- | ----- |
| [Reflection-Llama-3.1-70B-Q2_K.gguf](https://huggingface.co/second-state/Reflection-Llama-3.1-70B-GGUF/blob/main/Reflection-Llama-3.1-70B-Q2_K.gguf)     | Q2_K   | 2 | 26.4 GB| smallest, significant quality loss - not recommended for most purposes |
| [Reflection-Llama-3.1-70B-Q3_K_L.gguf](https://huggingface.co/second-state/Reflection-Llama-3.1-70B-GGUF/blob/main/Reflection-Llama-3.1-70B-Q3_K_L.gguf) | Q3_K_L | 3 | 37.1 GB| small, substantial quality loss |
| [Reflection-Llama-3.1-70B-Q3_K_M.gguf](https://huggingface.co/second-state/Reflection-Llama-3.1-70B-GGUF/blob/main/Reflection-Llama-3.1-70B-Q3_K_M.gguf) | Q3_K_M | 3 | 34.3 GB| very small, high quality loss |
| [Reflection-Llama-3.1-70B-Q3_K_S.gguf](https://huggingface.co/second-state/Reflection-Llama-3.1-70B-GGUF/blob/main/Reflection-Llama-3.1-70B-Q3_K_S.gguf) | Q3_K_S | 3 | 30.9 GB| very small, high quality loss |
| [Reflection-Llama-3.1-70B-Q4_0.gguf](https://huggingface.co/second-state/Reflection-Llama-3.1-70B-GGUF/blob/main/Reflection-Llama-3.1-70B-Q4_0.gguf)     | Q4_0   | 4 | 40 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
| [Reflection-Llama-3.1-70B-Q4_K_M.gguf](https://huggingface.co/second-state/Reflection-Llama-3.1-70B-GGUF/blob/main/Reflection-Llama-3.1-70B-Q4_K_M.gguf) | Q4_K_M | 4 | 42.5 GB| medium, balanced quality - recommended |
| [Reflection-Llama-3.1-70B-Q4_K_S.gguf](https://huggingface.co/second-state/Reflection-Llama-3.1-70B-GGUF/blob/main/Reflection-Llama-3.1-70B-Q4_K_S.gguf) | Q4_K_S | 4 | 40.3 GB| small, greater quality loss |
| [Reflection-Llama-3.1-70B-Q5_0.gguf](https://huggingface.co/second-state/Reflection-Llama-3.1-70B-GGUF/blob/main/Reflection-Llama-3.1-70B-Q5_0.gguf)     | Q5_0   | 5 | 48.7 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
| [Reflection-Llama-3.1-70B-Q5_K_M.gguf](https://huggingface.co/second-state/Reflection-Llama-3.1-70B-GGUF/blob/main/Reflection-Llama-3.1-70B-Q5_K_M.gguf) | Q5_K_M | 5 | 49.9 GB| large, very low quality loss - recommended |
| [Reflection-Llama-3.1-70B-Q5_K_S.gguf](https://huggingface.co/second-state/Reflection-Llama-3.1-70B-GGUF/blob/main/Reflection-Llama-3.1-70B-Q5_K_S.gguf) | Q5_K_S | 5 | 48.7 GB| large, low quality loss - recommended |
| [Reflection-Llama-3.1-70B-Q6_K-00001-of-00002.gguf](https://huggingface.co/second-state/Reflection-Llama-3.1-70B-GGUF/blob/main/Reflection-Llama-3.1-70B-Q6_K-00001-of-00002.gguf)     | Q6_K   | 6 | 29.8 GB| very large, extremely low quality loss |
| [Reflection-Llama-3.1-70B-Q6_K-00002-of-00002.gguf](https://huggingface.co/second-state/Reflection-Llama-3.1-70B-GGUF/blob/main/Reflection-Llama-3.1-70B-Q6_K-00002-of-00002.gguf)     | Q6_K   | 6 | 28.0 GB| very large, extremely low quality loss |
| [Reflection-Llama-3.1-70B-Q8_0-00001-of-00003.gguf](https://huggingface.co/second-state/Reflection-Llama-3.1-70B-GGUF/blob/main/Reflection-Llama-3.1-70B-Q8_0-00001-of-00003.gguf)     | Q8_0   | 8 | 29.8 GB| very large, extremely low quality loss - not recommended |
| [Reflection-Llama-3.1-70B-Q8_0-00002-of-00003.gguf](https://huggingface.co/second-state/Reflection-Llama-3.1-70B-GGUF/blob/main/Reflection-Llama-3.1-70B-Q8_0-00002-of-00003.gguf)     | Q8_0   | 8 | 29.8 GB| very large, extremely low quality loss - not recommended |
| [Reflection-Llama-3.1-70B-Q8_0-00003-of-00003.gguf](https://huggingface.co/second-state/Reflection-Llama-3.1-70B-GGUF/blob/main/Reflection-Llama-3.1-70B-Q8_0-00003-of-00003.gguf)     | Q8_0   | 8 | 15.4 GB| very large, extremely low quality loss - not recommended |
| [Reflection-Llama-3.1-70B-f16-00001-of-00005.gguf](https://huggingface.co/second-state/Reflection-Llama-3.1-70B-GGUF/blob/main/Reflection-Llama-3.1-70B-f16-00001-of-00005.gguf)     | f16   | 16 | 30.0 GB|  |
| [Reflection-Llama-3.1-70B-f16-00002-of-00005.gguf](https://huggingface.co/second-state/Reflection-Llama-3.1-70B-GGUF/blob/main/Reflection-Llama-3.1-70B-f16-00002-of-00005.gguf)     | f16   | 16 | 29.6 GB|  |
| [Reflection-Llama-3.1-70B-f16-00003-of-00005.gguf](https://huggingface.co/second-state/Reflection-Llama-3.1-70B-GGUF/blob/main/Reflection-Llama-3.1-70B-f16-00003-of-00005.gguf)     | f16   | 16 | 29.6 GB|  |
| [Reflection-Llama-3.1-70B-f16-00004-of-00005.gguf](https://huggingface.co/second-state/Reflection-Llama-3.1-70B-GGUF/blob/main/Reflection-Llama-3.1-70B-f16-00004-of-00005.gguf)     | f16   | 16 | 29.6 GB|  |
| [Reflection-Llama-3.1-70B-f16-00005-of-00005.gguf](https://huggingface.co/second-state/Reflection-Llama-3.1-70B-GGUF/blob/main/Reflection-Llama-3.1-70B-f16-00005-of-00005.gguf)     | f16   | 16 | 22.2 GB|  |

*Quantized with llama.cpp 3664.*