From d13686107a05c1ba4577d906a3929c2aefdd90b7 Mon Sep 17 00:00:00 2001 From: BarfingLemurs <128182951+BarfingLemurs@users.noreply.github.com> Date: Fri, 13 Oct 2023 09:35:29 -0400 Subject: [PATCH 1/4] Update README.md --- README.md | 24 ++++++++++++++++++------ 1 file changed, 18 insertions(+), 6 deletions(-) diff --git a/README.md b/README.md index 60f14a1fbf585..0a9d0bad93a0e 100644 --- a/README.md +++ b/README.md @@ -10,7 +10,7 @@ Inference of [LLaMA](https://arxiv.org/abs/2302.13971) model in pure C/C++ ### Hot topics - +- ‼️ BPE tokenizer update: existing Falcon 180B `.gguf` models will need to be reconverted - ‼️ Breaking change: `rope_freq_base` and `rope_freq_scale` must be set to zero to use the model default values: [#3401](https://github.com/ggerganov/llama.cpp/pull/3401) - Parallel decoding + continuous batching support added: [#3228](https://github.com/ggerganov/llama.cpp/pull/3228) \ **Devs should become familiar with the new API** @@ -89,15 +89,17 @@ as the main playground for developing new features for the [ggml](https://github - [X] [Vicuna](https://github.com/ggerganov/llama.cpp/discussions/643#discussioncomment-5533894) - [X] [Koala](https://bair.berkeley.edu/blog/2023/04/03/koala/) - [X] [OpenBuddy 🐶 (Multilingual)](https://github.com/OpenBuddy/OpenBuddy) -- [X] [Pygmalion 7B / Metharme 7B](#using-pygmalion-7b--metharme-7b) +- [X] [Pygmalion/Metharme](#using-pygmalion-7b--metharme-7b) - [X] [WizardLM](https://github.com/nlpxucan/WizardLM) -- [X] [Baichuan-7B](https://huggingface.co/baichuan-inc/baichuan-7B) and its derivations (such as [baichuan-7b-sft](https://huggingface.co/hiyouga/baichuan-7b-sft)) -- [X] [Aquila-7B](https://huggingface.co/BAAI/Aquila-7B) / [AquilaChat-7B](https://huggingface.co/BAAI/AquilaChat-7B) +- [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] [Starcoder models](https://github.com/ggerganov/llama.cpp/pull/3187) - [X] [Mistral AI v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) - [X] [Refact](https://huggingface.co/smallcloudai/Refact-1_6B-fim) -- [X] [Bloom](https://github.com/ggerganov/llama.cpp/pull/3553) +- [X] [Persimmon 8B](https://github.com/ggerganov/llama.cpp/pull/3410) - [X] [MPT](https://github.com/ggerganov/llama.cpp/pull/3417) +- [X] [Bloom](https://github.com/ggerganov/llama.cpp/pull/3553) + **Bindings:** @@ -206,7 +208,17 @@ https://user-images.githubusercontent.com/1991296/224442907-7693d4be-acaa-4e01-8 ## Usage -Here are the steps for the LLaMA-7B model. +**Quickstart:** You will find prebuilt Windows binaries on the release page. + +Simply download and extract the zip package of choice (e.g. `llama-b1380-bin-win-avx2-x64.zip`) + +From the unzipped folder, open a terminal/cmd window here and place a pre-converted .`gguf` model file. Test out the main example like so: + +``` +.\main -m llama-2-7b.Q4_0.gguf -n 128 +``` + +**Build:** Here are the end-to-end binary build and model conversion steps for the LLaMA-7B model. ### Get the Code From dfa380dff4a85daccab82d294456463210c10924 Mon Sep 17 00:00:00 2001 From: BarfingLemurs <128182951+BarfingLemurs@users.noreply.github.com> Date: Fri, 13 Oct 2023 19:45:27 -0400 Subject: [PATCH 2/4] Update README.md --- README.md | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index 0a9d0bad93a0e..1d9288516e419 100644 --- a/README.md +++ b/README.md @@ -10,7 +10,7 @@ Inference of [LLaMA](https://arxiv.org/abs/2302.13971) model in pure C/C++ ### Hot topics -- ‼️ BPE tokenizer update: existing Falcon 180B `.gguf` models will need to be reconverted +- ‼️ BPE tokenizer update: existing Falcon and Starcoder `.gguf` models will need to be reconverted - ‼️ Breaking change: `rope_freq_base` and `rope_freq_scale` must be set to zero to use the model default values: [#3401](https://github.com/ggerganov/llama.cpp/pull/3401) - Parallel decoding + continuous batching support added: [#3228](https://github.com/ggerganov/llama.cpp/pull/3228) \ **Devs should become familiar with the new API** @@ -91,7 +91,7 @@ as the main playground for developing new features for the [ggml](https://github - [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] [Starcoder models](https://github.com/ggerganov/llama.cpp/pull/3187) - [X] [Mistral AI v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) @@ -208,7 +208,8 @@ https://user-images.githubusercontent.com/1991296/224442907-7693d4be-acaa-4e01-8 ## Usage -**Quickstart:** You will find prebuilt Windows binaries on the release page. +#### **Quickstart:** +You will find prebuilt Windows binaries on the release page. Simply download and extract the zip package of choice (e.g. `llama-b1380-bin-win-avx2-x64.zip`) @@ -218,7 +219,8 @@ From the unzipped folder, open a terminal/cmd window here and place a pre-conver .\main -m llama-2-7b.Q4_0.gguf -n 128 ``` -**Build:** Here are the end-to-end binary build and model conversion steps for the LLaMA-7B model. +#### **Build:** +Here are the end-to-end binary build and model conversion steps for the LLaMA-7B model. ### Get the Code From 9cddae25122694fcb723f05b16b3d18d407f6977 Mon Sep 17 00:00:00 2001 From: BarfingLemurs <128182951+BarfingLemurs@users.noreply.github.com> Date: Fri, 13 Oct 2023 20:35:49 -0400 Subject: [PATCH 3/4] Update README.md --- README.md | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/README.md b/README.md index 1d9288516e419..610bd259a95f0 100644 --- a/README.md +++ b/README.md @@ -10,7 +10,7 @@ Inference of [LLaMA](https://arxiv.org/abs/2302.13971) model in pure C/C++ ### Hot topics -- ‼️ BPE tokenizer update: existing Falcon and Starcoder `.gguf` models will need to be reconverted +- ‼️ BPE tokenizer update: existing Falcon and Starcoder `.gguf` models will need to be reconverted: [#3252](https://github.com/ggerganov/llama.cpp/pull/3252) - ‼️ Breaking change: `rope_freq_base` and `rope_freq_scale` must be set to zero to use the model default values: [#3401](https://github.com/ggerganov/llama.cpp/pull/3401) - Parallel decoding + continuous batching support added: [#3228](https://github.com/ggerganov/llama.cpp/pull/3228) \ **Devs should become familiar with the new API** @@ -91,8 +91,8 @@ as the main playground for developing new features for the [ggml](https://github - [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] [Aquila 1&2](https://huggingface.co/models?search=BAAI/Aquila) +- [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] [Starcoder models](https://github.com/ggerganov/llama.cpp/pull/3187) - [X] [Mistral AI v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) - [X] [Refact](https://huggingface.co/smallcloudai/Refact-1_6B-fim) @@ -208,18 +208,19 @@ https://user-images.githubusercontent.com/1991296/224442907-7693d4be-acaa-4e01-8 ## Usage -#### **Quickstart:** +### Quickstart You will find prebuilt Windows binaries on the release page. -Simply download and extract the zip package of choice (e.g. `llama-b1380-bin-win-avx2-x64.zip`) +Simply download and extract the latest zip package of choice: (e.g. `llama-b1380-bin-win-avx2-x64.zip`) -From the unzipped folder, open a terminal/cmd window here and place a pre-converted .`gguf` model file. Test out the main example like so: +From the unzipped folder, open a terminal/cmd window here and place a pre-converted `.gguf` model file. Test out the main example like so: ``` .\main -m llama-2-7b.Q4_0.gguf -n 128 ``` -#### **Build:** +### Full Instructions + Here are the end-to-end binary build and model conversion steps for the LLaMA-7B model. ### Get the Code From 1e1490f1abc6b88a1894d0f5eb8e02fb71e4cf2c Mon Sep 17 00:00:00 2001 From: BarfingLemurs <128182951+BarfingLemurs@users.noreply.github.com> Date: Sun, 15 Oct 2023 15:18:45 -0400 Subject: [PATCH 4/4] move "Running on Windows" section below "Prepare data and run" --- README.md | 25 ++++++++++++------------- 1 file changed, 12 insertions(+), 13 deletions(-) diff --git a/README.md b/README.md index 610bd259a95f0..4fd4bd427c3d3 100644 --- a/README.md +++ b/README.md @@ -208,19 +208,6 @@ https://user-images.githubusercontent.com/1991296/224442907-7693d4be-acaa-4e01-8 ## Usage -### Quickstart -You will find prebuilt Windows binaries on the release page. - -Simply download and extract the latest zip package of choice: (e.g. `llama-b1380-bin-win-avx2-x64.zip`) - -From the unzipped folder, open a terminal/cmd window here and place a pre-converted `.gguf` model file. Test out the main example like so: - -``` -.\main -m llama-2-7b.Q4_0.gguf -n 128 -``` - -### Full Instructions - Here are the end-to-end binary build and model conversion steps for the LLaMA-7B model. ### Get the Code @@ -588,6 +575,18 @@ python3 convert.py models/7B/ When running the larger models, make sure you have enough disk space to store all the intermediate files. +### Running on Windows with prebuilt binaries + +You will find prebuilt Windows binaries on the release page. + +Simply download and extract the latest zip package of choice: (e.g. `llama-b1380-bin-win-avx2-x64.zip`) + +From the unzipped folder, open a terminal/cmd window here and place a pre-converted `.gguf` model file. Test out the main example like so: + +``` +.\main -m llama-2-7b.Q4_0.gguf -n 128 +``` + ### Memory/Disk Requirements 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.