“私密离线聊天新体验!llama-gpt聊天机器人:极速、安全、搭载Llama 2,尽享Code Llama支持!”
一个自托管的、离线的、类似chatgpt的聊天机器人。由美洲驼提供动力。100%私密,没有数据离开您的设备。
Demo
https://github.com/getumbrel/llama-gpt/assets/10330103/5d1a76b8-ed03-4a51-90bd-12ebfaf1e6cd
1.支持模型
Currently, LlamaGPT supports the following models. Support for running custom models is on the roadmap.
Model name | Model size | Model download size | Memory required |
---|---|---|---|
Nous Hermes Llama 2 7B Chat (GGML q4_0) | 7B | 3.79GB | 6.29GB |
Nous Hermes Llama 2 13B Chat (GGML q4_0) | 13B | 7.32GB | 9.82GB |
Nous Hermes Llama 2 70B Chat (GGML q4_0) | 70B | 38.87GB | 41.37GB |
Code Llama 7B Chat (GGUF Q4_K_M) | 7B | 4.24GB | 6.74GB |
Code Llama 13B Chat (GGUF Q4_K_M) | 13B | 8.06GB | 10.56GB |
Phind Code Llama 34B Chat (GGUF Q4_K_M) | 34B | 20.22GB | 22.72GB |
1.1 安装LlamaGPT 在 umbrelOS
Running LlamaGPT on an umbrelOS home server is one click. Simply install it from the Umbrel App Store.
1.2 安装LlamaGPT on M1/M2 Mac
Make sure your have Docker and Xcode installed.
Then, clone this repo and cd
into it:
git clone https://github.com/getumbrel/llama-gpt.git
cd llama-gpt
Run LlamaGPT with the following command:
./run-mac.sh --model 7b
You can access LlamaGPT at http://localhost:3000.
To run 13B or 70B chat models, replace
7b
with13b
or70b
respectively.
To run 7B, 13B or 34B Code Llama models, replace7b
withcode-7b
,code-13b
orcode-34b
respectively.
To stop LlamaGPT, do Ctrl + C
in Terminal.
1.3 在 Docker上安装
You can run LlamaGPT on any x86 or arm64 system. Make sure you have Docker installed.
Then, clone this repo and cd
into it:
git clone https://github.com/getumbrel/llama-gpt.git
cd llama-gpt
Run LlamaGPT with the following command:
./run.sh --model 7b
Or if you have an Nvidia GPU, you can run LlamaGPT with CUDA support using the --with-cuda
flag, like:
./run.sh --model 7b --with-cuda
You can access LlamaGPT at http://localhost:3000
.
To run 13B or 70B chat models, replace
7b
with13b
or70b
respectively.
To run Code Llama 7B, 13B or 34B models, replace7b
withcode-7b
,code-13b
orcode-34b
respectively.
To stop LlamaGPT, do Ctrl + C
in Terminal.
Note: On the first run, it may take a while for the model to be downloaded to the
/models
directory. You may also see lots of output like this for a few minutes, which is normal:llama-gpt-llama-gpt-ui-1 | [INFO wait] Host [llama-gpt-api-13b:8000] not yet available...
After the model has been automatically downloaded and loaded, and the API server is running, you'll see an output like:
llama-gpt-ui_1 | ready - started server on 0.0.0.0:3000, url: http://localhost:3000
You can then access LlamaGPT at http://localhost:3000.
1.4 在Kubernetes安装
First, make sure you have a running Kubernetes cluster and kubectl
is configured to interact with it.
Then, clone this repo and cd
into it.
To deploy to Kubernetes first create a namespace:
kubectl create ns llama
Then apply the manifests under the /deploy/kubernetes
directory with
kubectl apply -k deploy/kubernetes/. -n llama
Expose your service however you would normally do that.
2.OpenAI兼容API
Thanks to llama-cpp-python, a drop-in replacement for OpenAI API is available at http://localhost:3001
. Open http://localhost:3001/docs to see the API documentation.
- 基线
We've tested LlamaGPT models on the following hardware with the default system prompt, and user prompt: "How does the universe expand?" at temperature 0 to guarantee deterministic results. Generation speed is averaged over the first 10 generations.
Feel free to add your own benchmarks to this table by opening a pull request.
2.1 Nous Hermes Llama 2 7B Chat (GGML q4_0)
Device | Generation speed |
---|---|
M1 Max MacBook Pro (64GB RAM) | 54 tokens/sec |
GCP c2-standard-16 vCPU (64 GB RAM) | 16.7 tokens/sec |
Ryzen 5700G 4.4GHz 4c (16 GB RAM) | 11.50 tokens/sec |
GCP c2-standard-4 vCPU (16 GB RAM) | 4.3 tokens/sec |
Umbrel Home (16GB RAM) | 2.7 tokens/sec |
Raspberry Pi 4 (8GB RAM) | 0.9 tokens/sec |
2.2 Nous Hermes Llama 2 13B Chat (GGML q4_0)
Device | Generation speed |
---|---|
M1 Max MacBook Pro (64GB RAM) | 20 tokens/sec |
GCP c2-standard-16 vCPU (64 GB RAM) | 8.6 tokens/sec |
GCP c2-standard-4 vCPU (16 GB RAM) | 2.2 tokens/sec |
Umbrel Home (16GB RAM) | 1.5 tokens/sec |
2.3 Nous Hermes Llama 2 70B Chat (GGML q4_0)
Device | Generation speed |
---|---|
M1 Max MacBook Pro (64GB RAM) | 4.8 tokens/sec |
GCP e2-standard-16 vCPU (64 GB RAM) | 1.75 tokens/sec |
GCP c2-standard-16 vCPU (64 GB RAM) | 1.62 tokens/sec |
2.4 Code Llama 7B Chat (GGUF Q4_K_M)
Device | Generation speed |
---|---|
M1 Max MacBook Pro (64GB RAM) | 41 tokens/sec |
2.5 Code Llama 13B Chat (GGUF Q4_K_M)
Device | Generation speed |
---|---|
M1 Max MacBook Pro (64GB RAM) | 25 tokens/sec |
2.6 Phind Code Llama 34B Chat (GGUF Q4_K_M)
Device | Generation speed |
---|---|
M1 Max MacBook Pro (64GB RAM) | 10.26 tokens/sec |
更多优质内容请关注公号:汀丶人工智能;会提供一些相关的资源和优质文章,免费获取阅读。
标签:llama,新体验,RAM,离线,tokens,sec,聊天,Llama,GB From: https://www.cnblogs.com/ting1/p/17756541.html