root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-25 10:54:36 +00:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

readme : modernize (#5379)

Browse Source 
* first cleanup, update everything to Llama 2 and remove outdated content

* Delete SHA256SUMS

* make build instructions generic

* recommend Q4_K_M quantization method

* Update README.md
This commit is contained in:
Eve 2024-02-07 06:21:30 +00:00 committed by GitHub
parent 9a697d842b
commit ed0bf32290
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 36 additions and 131 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

127
README.md
View File

@ -33,17 +33,14 @@ Inference of Meta's [LLaMA](https://arxiv.org/abs/2302.13971) model (and others)
<li><a href="#get-the-code">Get the Code</a></li> <li><a href="#get-the-code">Get the Code</a></li>
<li><a href="#build">Build</a></li> <li><a href="#build">Build</a></li>
<li><a href="#blas-build">BLAS Build</a></li> <li><a href="#blas-build">BLAS Build</a></li>
<li><a href="#prepare-data--run">Prepare Data & Run</a></li> <li><a href="#prepare-and-quantize">Prepare and Quantize</a></li>
<li><a href="#run-the-quantized-model">Run the quantized model</a></li>
<li><a href="#memorydisk-requirements">Memory/Disk Requirements</a></li> <li><a href="#memorydisk-requirements">Memory/Disk Requirements</a></li>
<li><a href="#quantization">Quantization</a></li> <li><a href="#quantization">Quantization</a></li>
<li><a href="#interactive-mode">Interactive mode</a></li> <li><a href="#interactive-mode">Interactive mode</a></li>
<li><a href="#constrained-output-with-grammars">Constrained output with grammars</a></li> <li><a href="#constrained-output-with-grammars">Constrained output with grammars</a></li>
<li><a href="#instruction-mode-with-alpaca">Instruction mode with Alpaca</a></li> <li><a href="#instruct-mode">Instruct mode</a></li>
<li><a href="#using-openllama">Using OpenLLaMA</a></li> <li><a href="#obtaining-and-using-the-facebook-llama-2-model">Obtaining and using the Facebook LLaMA 2 model</a></li>
<li><a href="#using-gpt4all">Using GPT4All</a></li>
<li><a href="#using-pygmalion-7b--metharme-7b">Using Pygmalion 7B & Metharme 7B</a></li>
<li><a href="#obtaining-the-facebook-llama-original-model-and-stanford-alpaca-model-data">Obtaining the Facebook LLaMA original model and Stanford Alpaca model data</a></li>
<li><a href="#verifying-the-model-files">Verifying the model files</a></li>
<li><a href="#seminal-papers-and-background-on-the-models">Seminal papers and background on the models</a></li> <li><a href="#seminal-papers-and-background-on-the-models">Seminal papers and background on the models</a></li>
<li><a href="#perplexity-measuring-model-quality">Perplexity (measuring model quality)</a></li> <li><a href="#perplexity-measuring-model-quality">Perplexity (measuring model quality)</a></li>
<li><a href="#android">Android</a></li> <li><a href="#android">Android</a></li>
@ -83,20 +80,16 @@ improved significantly thanks to many contributions. It is the main playground f
**Supported models:** **Supported models:**
Typically finetunes of the base models below are supported as well.
- [X] LLaMA 🦙 - [X] LLaMA 🦙
- [x] LLaMA 2 🦙🦙 - [x] LLaMA 2 🦙🦙
- [X] [Mistral AI v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) - [X] [Mistral 7B](https://huggingface.co/mistralai/Mistral-7B-v0.1)
- [x] [Mixtral MoE](https://huggingface.co/models?search=mistral-ai/Mixtral) - [x] [Mixtral MoE](https://huggingface.co/models?search=mistral-ai/Mixtral)
- [X] Falcon - [X] Falcon
- [X] [Alpaca](https://github.com/ggerganov/llama.cpp#instruction-mode-with-alpaca)
- [X] [GPT4All](https://github.com/ggerganov/llama.cpp#using-gpt4all)
- [X] [Chinese LLaMA / Alpaca](https://github.com/ymcui/Chinese-LLaMA-Alpaca) and [Chinese LLaMA-2 / Alpaca-2](https://github.com/ymcui/Chinese-LLaMA-Alpaca-2) - [X] [Chinese LLaMA / Alpaca](https://github.com/ymcui/Chinese-LLaMA-Alpaca) and [Chinese LLaMA-2 / Alpaca-2](https://github.com/ymcui/Chinese-LLaMA-Alpaca-2)
- [X] [Vigogne (French)](https://github.com/bofenghuang/vigogne) - [X] [Vigogne (French)](https://github.com/bofenghuang/vigogne)
- [X] [Vicuna](https://github.com/ggerganov/llama.cpp/discussions/643#discussioncomment-5533894)
- [X] [Koala](https://bair.berkeley.edu/blog/2023/04/03/koala/) - [X] [Koala](https://bair.berkeley.edu/blog/2023/04/03/koala/)
- [X] [OpenBuddy 🐶 (Multilingual)](https://github.com/OpenBuddy/OpenBuddy)
- [X] [Pygmalion/Metharme](#using-pygmalion-7b--metharme-7b)
- [X] [WizardLM](https://github.com/nlpxucan/WizardLM)
- [X] [Baichuan 1 & 2](https://huggingface.co/models?search=baichuan-inc/Baichuan) + [derivations](https://huggingface.co/hiyouga/baichuan-7b-sft) - [X] [Baichuan 1 & 2](https://huggingface.co/models?search=baichuan-inc/Baichuan) + [derivations](https://huggingface.co/hiyouga/baichuan-7b-sft)
- [X] [Aquila 1 & 2](https://huggingface.co/models?search=BAAI/Aquila) - [X] [Aquila 1 & 2](https://huggingface.co/models?search=BAAI/Aquila)
- [X] [Starcoder models](https://github.com/ggerganov/llama.cpp/pull/3187) - [X] [Starcoder models](https://github.com/ggerganov/llama.cpp/pull/3187)
@ -166,7 +159,7 @@ Unless otherwise noted these projects are open-source with permissive licensing:
Here is a typical run using LLaMA v2 13B on M2 Ultra: Here is a typical run using LLaMA v2 13B on M2 Ultra:
```java ```
$ make -j && ./main -m models/llama-13b-v2/ggml-model-q4_0.gguf -p "Building a website can be done in 10 simple steps:\nStep 1:" -n 400 -e $ make -j && ./main -m models/llama-13b-v2/ggml-model-q4_0.gguf -p "Building a website can be done in 10 simple steps:\nStep 1:" -n 400 -e
I llama.cpp build info: I llama.cpp build info:
I UNAME_S: Darwin I UNAME_S: Darwin
@ -250,7 +243,7 @@ https://user-images.githubusercontent.com/1991296/224442907-7693d4be-acaa-4e01-8
## Usage ## Usage
Here are the end-to-end binary build and model conversion steps for the LLaMA-7B model. Here are the end-to-end binary build and model conversion steps for most supported models.
### Get the Code ### Get the Code
@ -635,7 +628,7 @@ Building the program with BLAS support may lead to some performance improvements
**Without docker**: **Without docker**:
Firstly, you need to make sure you installed [Vulkan SDK](https://vulkan.lunarg.com/doc/view/latest/linux/getting_started_ubuntu.html) Firstly, you need to make sure you have installed [Vulkan SDK](https://vulkan.lunarg.com/doc/view/latest/linux/getting_started_ubuntu.html)
For example, on Ubuntu 22.04 (jammy), use the command below: For example, on Ubuntu 22.04 (jammy), use the command below:
@ -648,6 +641,8 @@ Building the program with BLAS support may lead to some performance improvements
vulkaninfo vulkaninfo
``` ```
Alternatively your package manager might be able to provide the appropiate libraries. For example for Ubuntu 22.04 you can install `libvulkan-dev` instead.
Then, build llama.cpp using the cmake command below: Then, build llama.cpp using the cmake command below:
```bash ```bash
@ -662,34 +657,42 @@ Building the program with BLAS support may lead to some performance improvements
# ggml_vulkan: Using Intel(R) Graphics (ADL GT2) | uma: 1 | fp16: 1 | warp size: 32 # ggml_vulkan: Using Intel(R) Graphics (ADL GT2) | uma: 1 | fp16: 1 | warp size: 32
``` ```
### Prepare Data & Run ### Prepare and Quantize
To obtain the official LLaMA 2 weights please see the <a href="#obtaining-and-using-the-facebook-llama-2-model">Obtaining and using the Facebook LLaMA 2 model</a> section. There is also a large selection of pre-quantized `gguf` models available on Hugging Face.
```bash ```bash
# obtain the original LLaMA model weights and place them in ./models # obtain the official LLaMA model weights and place them in ./models
ls ./models ls ./models
65B 30B 13B 7B tokenizer_checklist.chk tokenizer.model llama-2-7b tokenizer_checklist.chk tokenizer.model
# [Optional] for models using BPE tokenizers # [Optional] for models using BPE tokenizers
ls ./models ls ./models
65B 30B 13B 7B vocab.json <folder containing weights and tokenizer json> vocab.json
# [Optional] for PyTorch .bin models like Mistral-7B
ls ./models
<folder containing weights and tokenizer json>
# install Python dependencies # install Python dependencies
python3 -m pip install -r requirements.txt python3 -m pip install -r requirements.txt
# convert the 7B model to ggml FP16 format # convert the model to ggml FP16 format
python3 convert.py models/7B/ python3 convert.py models/mymodel/
# [Optional] for models using BPE tokenizers # [Optional] for models using BPE tokenizers
python convert.py models/7B/ --vocabtype bpe python convert.py models/mymodel/ --vocabtype bpe
# quantize the model to 4-bits (using q4_0 method) # quantize the model to 4-bits (using Q4_K_M method)
./quantize ./models/7B/ggml-model-f16.gguf ./models/7B/ggml-model-q4_0.gguf q4_0 ./quantize ./models/mymodel/ggml-model-f16.gguf ./models/mymodel/ggml-model-Q4_K_M.gguf Q4_K_M
# update the gguf filetype to current if older version is unsupported by another application # update the gguf filetype to current version if older version is now unsupported
./quantize ./models/7B/ggml-model-q4_0.gguf ./models/7B/ggml-model-q4_0-v2.gguf COPY ./quantize ./models/mymodel/ggml-model-Q4_K_M.gguf ./models/mymodel/ggml-model-Q4_K_M-v2.gguf COPY
```
### Run the quantized model
# run the inference ```bash
./main -m ./models/7B/ggml-model-q4_0.gguf -n 128 # start inference on a gguf model
./main -m ./models/mymodel/ggml-model-Q4_K_M.gguf -n 128
``` ```
When running the larger models, make sure you have enough disk space to store all the intermediate files. When running the larger models, make sure you have enough disk space to store all the intermediate files.
@ -710,7 +713,7 @@ From the unzipped folder, open a terminal/cmd window here and place a pre-conver
As the models are currently fully loaded into memory, you will need adequate disk space to save them and sufficient RAM to load them. At the moment, memory and disk requirements are the same. As the models are currently fully loaded into memory, you will need adequate disk space to save them and sufficient RAM to load them. At the moment, memory and disk requirements are the same.
| Model | Original size | Quantized size (4-bit) | | Model | Original size | Quantized size (Q4_0) |
|------:|--------------:|-----------------------:| |------:|--------------:|-----------------------:|
| 7B | 13 GB | 3.9 GB | | 7B | 13 GB | 3.9 GB |
| 13B | 24 GB | 7.8 GB | | 13B | 24 GB | 7.8 GB |
@ -826,9 +829,9 @@ The `grammars/` folder contains a handful of sample grammars. To write your own,
For authoring more complex JSON grammars, you can also check out https://grammar.intrinsiclabs.ai/, a browser app that lets you write TypeScript interfaces which it compiles to GBNF grammars that you can save for local use. Note that the app is built and maintained by members of the community, please file any issues or FRs on [its repo](http://github.com/intrinsiclabsai/gbnfgen) and not this one. For authoring more complex JSON grammars, you can also check out https://grammar.intrinsiclabs.ai/, a browser app that lets you write TypeScript interfaces which it compiles to GBNF grammars that you can save for local use. Note that the app is built and maintained by members of the community, please file any issues or FRs on [its repo](http://github.com/intrinsiclabsai/gbnfgen) and not this one.
### Instruction mode with Alpaca ### Instruct mode
1. First, download the `ggml` Alpaca model into the `./models` folder 1. First, download and place the `ggml` model into the `./models` folder
2. Run the `main` tool like this: 2. Run the `main` tool like this:
``` ```
@ -854,50 +857,6 @@ cadaver, cauliflower, cabbage (vegetable), catalpa (tree) and Cailleach.
> >
``` ```
### Using [OpenLLaMA](https://github.com/openlm-research/open_llama)
OpenLLaMA is an openly licensed reproduction of Meta's original LLaMA model. It uses the same architecture and is a drop-in replacement for the original LLaMA weights.
- Download the [3B](https://huggingface.co/openlm-research/open_llama_3b), [7B](https://huggingface.co/openlm-research/open_llama_7b), or [13B](https://huggingface.co/openlm-research/open_llama_13b) model from Hugging Face.
- Convert the model to ggml FP16 format using `python convert.py <path to OpenLLaMA directory>`
### Using [GPT4All](https://github.com/nomic-ai/gpt4all)
*Note: these instructions are likely obsoleted by the GGUF update*
- Obtain the `tokenizer.model` file from LLaMA model and put it to `models`
- Obtain the `added_tokens.json` file from Alpaca model and put it to `models`
- Obtain the `gpt4all-lora-quantized.bin` file from GPT4All model and put it to `models/gpt4all-7B`
- It is distributed in the old `ggml` format which is now obsoleted
- You have to convert it to the new format using `convert.py`:
```bash
python3 convert.py models/gpt4all-7B/gpt4all-lora-quantized.bin
```
- You can now use the newly generated `models/gpt4all-7B/ggml-model-q4_0.bin` model in exactly the same way as all other models
- The newer GPT4All-J model is not yet supported!
### Using Pygmalion 7B & Metharme 7B
- Obtain the [LLaMA weights](#obtaining-the-facebook-llama-original-model-and-stanford-alpaca-model-data)
- Obtain the [Pygmalion 7B](https://huggingface.co/PygmalionAI/pygmalion-7b/) or [Metharme 7B](https://huggingface.co/PygmalionAI/metharme-7b) XOR encoded weights
- Convert the LLaMA model with [the latest HF convert script](https://github.com/huggingface/transformers/blob/main/src/transformers/models/llama/convert_llama_weights_to_hf.py)
- Merge the XOR files with the converted LLaMA weights by running the [xor_codec](https://huggingface.co/PygmalionAI/pygmalion-7b/blob/main/xor_codec.py) script
- Convert to `ggml` format using the `convert.py` script in this repo:
```bash
python3 convert.py pygmalion-7b/ --outtype q4_1
```
> The Pygmalion 7B & Metharme 7B weights are saved in [bfloat16](https://en.wikipedia.org/wiki/Bfloat16_floating-point_format) precision. If you wish to convert to `ggml` without quantizating, please specify the `--outtype` as `f32` instead of `f16`.
### Obtaining the Facebook LLaMA original model and Stanford Alpaca model data
- **Under no circumstances should IPFS, magnet links, or any other links to model downloads be shared anywhere in this repository, including in issues, discussions, or pull requests. They will be immediately deleted.**
- The LLaMA models are officially distributed by Facebook and will **never** be provided through this repository.
- Refer to [Facebook's LLaMA repository](https://github.com/facebookresearch/llama/pull/73/files) if you need to request access to the model data.
### Obtaining and using the Facebook LLaMA 2 model ### Obtaining and using the Facebook LLaMA 2 model
- Refer to [Facebook's LLaMA download page](https://ai.meta.com/resources/models-and-libraries/llama-downloads/) if you want to access the model data. - Refer to [Facebook's LLaMA download page](https://ai.meta.com/resources/models-and-libraries/llama-downloads/) if you want to access the model data.
@ -909,20 +868,6 @@ python3 convert.py pygmalion-7b/ --outtype q4_1
- [LLaMA 2 13B chat](https://huggingface.co/TheBloke/Llama-2-13B-chat-GGUF) - [LLaMA 2 13B chat](https://huggingface.co/TheBloke/Llama-2-13B-chat-GGUF)
- [LLaMA 2 70B chat](https://huggingface.co/TheBloke/Llama-2-70B-chat-GGUF) - [LLaMA 2 70B chat](https://huggingface.co/TheBloke/Llama-2-70B-chat-GGUF)
### Verifying the model files
Please verify the [sha256 checksums](SHA256SUMS) of all downloaded model files to confirm that you have the correct model data files before creating an issue relating to your model files.
- The following python script will verify if you have all possible latest files in your self-installed `./models` subdirectory:
```bash
# run the verification script
./scripts/verify-checksum-models.py
```
- On linux or macOS it is also possible to run the following commands to verify if you have all possible latest files in your self-installed `./models` subdirectory:
- On Linux: `sha256sum --ignore-missing -c SHA256SUMS`
- on macOS: `shasum -a 256 --ignore-missing -c SHA256SUMS`
### Seminal papers and background on the models ### Seminal papers and background on the models
If your issue is with model generation quality, then please at least scan the following links and papers to understand the limitations of LLaMA models. This is especially important when choosing an appropriate model size and appreciating both the significant and subtle differences between LLaMA models and ChatGPT: If your issue is with model generation quality, then please at least scan the following links and papers to understand the limitations of LLaMA models. This is especially important when choosing an appropriate model size and appreciating both the significant and subtle differences between LLaMA models and ChatGPT:

40
SHA256SUMS
View File

@ -1,40 +0,0 @@
700df0d3013b703a806d2ae7f1bfb8e59814e3d06ae78be0c66368a50059f33d models/7B/consolidated.00.pth
666a4bb533b303bdaf89e1b6a3b6f93535d868de31d903afdc20983dc526c847 models/7B/ggml-model-f16.bin
ec2f2d1f0dfb73b72a4cbac7fa121abbe04c37ab327125a38248f930c0f09ddf models/7B/ggml-model-q4_0.bin
ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff models/7B/ggml-model-q4_1.bin
ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff models/7B/ggml-model-q5_0.bin
ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff models/7B/ggml-model-q5_1.bin
7e89e242ddc0dd6f060b43ca219ce8b3e8f08959a72cb3c0855df8bb04d46265 models/7B/params.json
745bf4e29a4dd6f411e72976d92b452da1b49168a4f41c951cfcc8051823cf08 models/13B/consolidated.00.pth
d5ccbcc465c71c0de439a5aeffebe8344c68a519bce70bc7f9f92654ee567085 models/13B/consolidated.01.pth
2b206e9b21fb1076f11cafc624e2af97c9e48ea09312a0962153acc20d45f808 models/13B/ggml-model-f16.bin
fad169e6f0f575402cf75945961cb4a8ecd824ba4da6be2af831f320c4348fa5 models/13B/ggml-model-q4_0.bin
ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff models/13B/ggml-model-q4_1.bin
ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff models/13B/ggml-model-q5_0.bin
ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff models/13B/ggml-model-q5_1.bin
4ab77bec4d4405ccb66a97b282574c89a94417e3c32e5f68f37e2876fc21322f models/13B/params.json
e23294a58552d8cdec5b7e8abb87993b97ea6eced4178ff2697c02472539d067 models/30B/consolidated.00.pth
4e077b7136c7ae2302e954860cf64930458d3076fcde9443f4d0e939e95903ff models/30B/consolidated.01.pth
24a87f01028cbd3a12de551dcedb712346c0b5cbdeff1454e0ddf2df9b675378 models/30B/consolidated.02.pth
1adfcef71420886119544949767f6a56cb6339b4d5fcde755d80fe68b49de93b models/30B/consolidated.03.pth
7e1b524061a9f4b27c22a12d6d2a5bf13b8ebbea73e99f218809351ed9cf7d37 models/30B/ggml-model-f16.bin
d2a441403944819492ec8c2002cc36fa38468149bfb4b7b4c52afc7bd9a7166d models/30B/ggml-model-q4_0.bin
ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff models/30B/ggml-model-q4_1.bin
ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff models/30B/ggml-model-q5_0.bin
ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff models/30B/ggml-model-q5_1.bin
2c07118ea98d69dbe7810d88520e30288fa994751b337f8fca02b171955f44cb models/30B/params.json
135c563f6b3938114458183afb01adc9a63bef3d8ff7cccc3977e5d3664ecafe models/65B/consolidated.00.pth
9a600b37b19d38c7e43809485f70d17d1dc12206c07efa83bc72bb498a568bde models/65B/consolidated.01.pth
e7babf7c5606f165a3756f527cb0fedc4f83e67ef1290391e52fb1cce5f26770 models/65B/consolidated.02.pth
73176ffb426b40482f2aa67ae1217ef79fbbd1fff5482bae5060cdc5a24ab70e models/65B/consolidated.03.pth
882e6431d0b08a8bc66261a0d3607da21cbaeafa96a24e7e59777632dbdac225 models/65B/consolidated.04.pth
a287c0dfe49081626567c7fe87f74cce5831f58e459b427b5e05567641f47b78 models/65B/consolidated.05.pth
72b4eba67a1a3b18cb67a85b70f8f1640caae9b40033ea943fb166bd80a7b36b models/65B/consolidated.06.pth
d27f5b0677d7ff129ceacd73fd461c4d06910ad7787cf217b249948c3f3bc638 models/65B/consolidated.07.pth
60758f2384d74e423dffddfd020ffed9d3bb186ebc54506f9c4a787d0f5367b0 models/65B/ggml-model-f16.bin
cde053439fa4910ae454407e2717cc46cc2c2b4995c00c93297a2b52e790fa92 models/65B/ggml-model-q4_0.bin
ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff models/65B/ggml-model-q4_1.bin
ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff models/65B/ggml-model-q5_0.bin
ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff models/65B/ggml-model-q5_1.bin
999ed1659b469ccc2a941714c0a9656fa571d17c9f7c8c7589817ca90edef51b models/65B/params.json
9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 models/tokenizer.model