File size: 6,633 Bytes
baeb1b4 4931687 baeb1b4 d41827f baeb1b4 d41827f baeb1b4 7b39624 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 |
---
license: llama3.1
model_name: Meta-Llama-3.1-70B-Instruct
base_model: meta-llama/Meta-Llama-3.1-70B-Instruct
inference: false
model_creator: Meta Llama3
model_type: llama
pipeline_tag: text-generation
quantized_by: Second State Inc.
language:
- en
- de
- fr
- it
- pt
- hi
- es
- th
tags:
- facebook
- meta
- pytorch
- llama
- llama-3
---
<!-- 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 -->
# Meta-Llama-3.1-70B-Instruct-GGUF
## Original Model
[meta-llama/Meta-Llama-3.1-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct)
## 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:Meta-Llama-3.1-70B-Instruct-Q4_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:Meta-Llama-3.1-70B-Instruct-Q4_K_M.gguf \
llama-chat.wasm \
--prompt-template llama-3-chat \
--ctx-size 128000
```
## Quantized GGUF Models
| Name | Quant method | Bits | Size | Use case |
| ---- | ---- | ---- | ---- | ----- |
| [Meta-Llama-3.1-70B-Instruct-Q2_K.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-70B-Instruct-GGUF/blob/main/Meta-Llama-3.1-70B-Instruct-Q2_K.gguf) | Q2_K | 2 | 26.4 GB| smallest, significant quality loss - not recommended for most purposes |
| [Meta-Llama-3.1-70B-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-70B-Instruct-GGUF/blob/main/Meta-Llama-3.1-70B-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 37.1 GB| small, substantial quality loss |
| [Meta-Llama-3.1-70B-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-70B-Instruct-GGUF/blob/main/Meta-Llama-3.1-70B-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 34.3 GB| very small, high quality loss |
| [Meta-Llama-3.1-70B-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-70B-Instruct-GGUF/blob/main/Meta-Llama-3.1-70B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 30.9 GB| very small, high quality loss |
| [Meta-Llama-3.1-70B-Instruct-Q4_0.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-70B-Instruct-GGUF/blob/main/Meta-Llama-3.1-70B-Instruct-Q4_0.gguf) | Q4_0 | 4 | 40 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
| [Meta-Llama-3.1-70B-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-70B-Instruct-GGUF/blob/main/Meta-Llama-3.1-70B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 42.5 GB| medium, balanced quality - recommended |
<!-- | [Meta-Llama-3.1-70B-Instruct-Q5_0.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-70B-Instruct-GGUF/blob/main/Meta-Llama-3.1-70B-Instruct-Q5_0.gguf) | Q5_0 | 5 | 48.7 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
| [Meta-Llama-3.1-70B-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-70B-Instruct-GGUF/blob/main/Meta-Llama-3.1-70B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 50 GB| large, very low quality loss - recommended |
| [Meta-Llama-3.1-70B-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-70B-Instruct-GGUF/blob/main/Meta-Llama-3.1-70B-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 48.7 GB| large, low quality loss - recommended |
| [Meta-Llama-3.1-70B-Instruct-Q6_K-00001-of-00002.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-70B-Instruct-GGUF/blob/main/Meta-Llama-3.1-70B-Instruct-Q6_K-00001-of-00002.gguf) | Q6_K | 6 | 32.1 GB| very large, extremely low quality loss |
| [Meta-Llama-3.1-70B-Instruct-Q6_K-00002-of-00002.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-70B-Instruct-GGUF/blob/main/Meta-Llama-3.1-70B-Instruct-Q6_K-00002-of-00002.gguf) | Q6_K | 6 | 25.7 GB| very large, extremely low quality loss |
| [Meta-Llama-3.1-70B-Instruct-Q8_0-00001-of-00003.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-70B-Instruct-GGUF/blob/main/Meta-Llama-3.1-70B-Instruct-Q8_0-00001-of-00003.gguf) | Q8_0 | 8 | 32 GB| very large, extremely low quality loss - not recommended |
| [Meta-Llama-3.1-70B-Instruct-Q8_0-00002-of-00003.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-70B-Instruct-GGUF/blob/main/Meta-Llama-3.1-70B-Instruct-Q8_0-00002-of-00003.gguf) | Q8_0 | 8 | 32.1 GB| very large, extremely low quality loss - not recommended |
| [Meta-Llama-3.1-70B-Instruct-Q8_0-00003-of-00003.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-70B-Instruct-GGUF/blob/main/Meta-Llama-3.1-70B-Instruct-Q8_0-00003-of-00003.gguf) | Q8_0 | 8 | 10.9 GB| very large, extremely low quality loss - not recommended |
| [Meta-Llama-3.1-70B-Instruct-f16-00001-of-00005.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-70B-Instruct-GGUF/blob/main/Meta-Llama-3.1-70B-Instruct-f16-00001-of-00005.gguf) | f16 | 16 | 32.1 GB| |
| [Meta-Llama-3.1-70B-Instruct-f16-00002-of-00005.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-70B-Instruct-GGUF/blob/main/Meta-Llama-3.1-70B-Instruct-f16-00002-of-00005.gguf) | f16 | 16 | 32 GB| |
| [Meta-Llama-3.1-70B-Instruct-f16-00003-of-00005.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-70B-Instruct-GGUF/blob/main/Meta-Llama-3.1-70B-Instruct-f16-00003-of-00005.gguf) | f16 | 16 | 32 GB| |
| [Meta-Llama-3.1-70B-Instruct-f16-00004-of-00005.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-70B-Instruct-GGUF/blob/main/Meta-Llama-3.1-70B-Instruct-f16-00004-of-00005.gguf) | f16 | 16 | 31.7 GB| |
| [Meta-Llama-3.1-70B-Instruct-f16-00005-of-00005.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-70B-Instruct-GGUF/blob/main/Meta-Llama-3.1-70B-Instruct-f16-00005-of-00005.gguf) | f16 | 16 | 13.1 GB| | -->
*Quantized with llama.cpp 3445.* |