91 lines
4.2 KiB
Markdown
91 lines
4.2 KiB
Markdown
---
|
|
language:
|
|
- en
|
|
license: llama2
|
|
tags:
|
|
- facebook
|
|
- meta
|
|
- pytorch
|
|
- llama
|
|
- llama-2
|
|
model_name: Llama 2 7B Chat
|
|
arxiv: 2307.09288
|
|
base_model: meta-llama/Llama-2-7b-chat-hf
|
|
inference: false
|
|
model_creator: Meta Llama 2
|
|
model_type: llama
|
|
pipeline_tag: text-generation
|
|
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 -->
|
|
|
|
# Llama-2-7B-Chat-GGUF
|
|
|
|
## Original Model
|
|
|
|
[meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf)
|
|
|
|
## Run with LlamaEdge
|
|
|
|
- LlamaEdge version: [v0.2.8](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.2.8) and above
|
|
|
|
- Prompt template
|
|
|
|
- Prompt type: `llama-2-chat`
|
|
|
|
- Prompt string
|
|
|
|
```text
|
|
<s>[INST] <<SYS>>
|
|
{{ system_prompt }}
|
|
<</SYS>>
|
|
|
|
{{ user_msg_1 }} [/INST] {{ model_answer_1 }} </s><s>[INST] {{ user_msg_2 }} [/INST]
|
|
```
|
|
|
|
- Context size: `4096`
|
|
|
|
- Run as LlamaEdge service
|
|
|
|
```bash
|
|
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-2-7b-chat-hf-Q5_K_M.gguf \
|
|
llama-api-server.wasm \
|
|
--prompt-template llama-2-chat \
|
|
--ctx-size 4096 \
|
|
--model-name llama-2-7b-chat
|
|
```
|
|
|
|
- Run as LlamaEdge command app
|
|
|
|
```bash
|
|
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-2-7b-chat-hf-Q5_K_M.gguf \
|
|
llama-chat.wasm \
|
|
--prompt-template llama-2-chat \
|
|
--ctx-size 4096
|
|
```
|
|
|
|
## Quantized GGUF Models
|
|
|
|
| Name | Quant method | Bits | Size | Use case |
|
|
| ---- | ---- | ---- | ---- | ----- |
|
|
| [Llama-2-7b-chat-hf-Q2_K.gguf](https://huggingface.co/second-state/Llama-2-7B-Chat-GGUF/blob/main/Llama-2-7b-chat-hf-Q2_K.gguf) | Q2_K | 2 | 2.83 GB| smallest, significant quality loss - not recommended for most purposes |
|
|
| [Llama-2-7b-chat-hf-Q3_K_L.gguf](https://huggingface.co/second-state/Llama-2-7B-Chat-GGUF/blob/main/Llama-2-7b-chat-hf-Q3_K_L.gguf) | Q3_K_L | 3 | 3.6 GB| small, substantial quality loss |
|
|
| [Llama-2-7b-chat-hf-Q3_K_M.gguf](https://huggingface.co/second-state/Llama-2-7B-Chat-GGUF/blob/main/Llama-2-7b-chat-hf-Q3_K_M.gguf) | Q3_K_M | 3 | 3.3 GB| very small, high quality loss |
|
|
| [Llama-2-7b-chat-hf-Q3_K_S.gguf](https://huggingface.co/second-state/Llama-2-7B-Chat-GGUF/blob/main/Llama-2-7b-chat-hf-Q3_K_S.gguf) | Q3_K_S | 3 | 2.95 GB| very small, high quality loss |
|
|
| [Llama-2-7b-chat-hf-Q4_0.gguf](https://huggingface.co/second-state/Llama-2-7B-Chat-GGUF/blob/main/Llama-2-7b-chat-hf-Q4_0.gguf) | Q4_0 | 4 | 3.83 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
|
|
| [Llama-2-7b-chat-hf-Q4_K_M.gguf](https://huggingface.co/second-state/Llama-2-7B-Chat-GGUF/blob/main/Llama-2-7b-chat-hf-Q4_K_M.gguf) | Q4_K_M | 4 | 4.08 GB| medium, balanced quality - recommended |
|
|
| [Llama-2-7b-chat-hf-Q4_K_S.gguf](https://huggingface.co/second-state/Llama-2-7B-Chat-GGUF/blob/main/Llama-2-7b-chat-hf-Q4_K_S.gguf) | Q4_K_S | 4 | 3.86 GB| small, greater quality loss |
|
|
| [Llama-2-7b-chat-hf-Q5_0.gguf](https://huggingface.co/second-state/Llama-2-7B-Chat-GGUF/blob/main/Llama-2-7b-chat-hf-Q5_0.gguf) | Q5_0 | 5 | 4.65 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
|
|
| [Llama-2-7b-chat-hf-Q5_K_M.gguf](https://huggingface.co/second-state/Llama-2-7B-Chat-GGUF/blob/main/Llama-2-7b-chat-hf-Q5_K_M.gguf) | Q5_K_M | 5 | 4.78 GB| large, very low quality loss - recommended |
|
|
| [Llama-2-7b-chat-hf-Q5_K_S.gguf](https://huggingface.co/second-state/Llama-2-7B-Chat-GGUF/blob/main/Llama-2-7b-chat-hf-Q5_K_S.gguf) | Q5_K_S | 5 | 4.65 GB| large, low quality loss - recommended |
|
|
| [Llama-2-7b-chat-hf-Q6_K.gguf](https://huggingface.co/second-state/Llama-2-7B-Chat-GGUF/blob/main/Llama-2-7b-chat-hf-Q6_K.gguf) | Q6_K | 6 | 5.53 GB| very large, extremely low quality loss |
|
|
| [Llama-2-7b-chat-hf-Q8_0.gguf](https://huggingface.co/second-state/Llama-2-7B-Chat-GGUF/blob/main/Llama-2-7b-chat-hf-Q8_0.gguf) | Q8_0 | 8 | 7.16 GB| very large, extremely low quality loss - not recommended |
|
|
| [Llama-2-7b-chat-hf-f16.gguf](https://huggingface.co/second-state/Llama-2-7B-Chat-GGUF/blob/main/Llama-2-7b-chat-hf-f16.gguf) | f16 | 16 | 13.5 GB| |
|