TheBloke/juanako-7B-v1-GGUF
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

Upload README.md

Browse Source
This commit is contained in:
ai-modelscope
2025-02-12 04:27:23 +08:00
parent d67361ee1b
commit 76d9a58ae9
16 changed files with 571 additions and 57 deletions
Download Patch File Download Diff File Expand all files Collapse all files

44
.gitattributes vendored
View File

@@ -1,47 +1,47 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bin.* filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zstandard filter=lfs diff=lfs merge=lfs -text
*.tfevents* filter=lfs diff=lfs merge=lfs -text
*.db* filter=lfs diff=lfs merge=lfs -text
*.ark* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.gguf* filter=lfs diff=lfs merge=lfs -text
*.ggml filter=lfs diff=lfs merge=lfs -text
*.llamafile* filter=lfs diff=lfs merge=lfs -text
*.pt2 filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
juanako-7b-v1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
juanako-7b-v1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
juanako-7b-v1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
juanako-7b-v1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
juanako-7b-v1.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
juanako-7b-v1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
juanako-7b-v1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
juanako-7b-v1.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
juanako-7b-v1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
juanako-7b-v1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
juanako-7b-v1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
juanako-7b-v1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

544
README.md
View File

@@ -1,47 +1,521 @@
---
license: Apache License 2.0
base_model: fblgit/juanako-7b-v1
datasets:
- HuggingFaceH4/ultrafeedback_binarized
inference: false
license: artistic-2.0
model-index:
- name: juanako-7b-v1
results: []
model_creator: FBL
model_name: Juanako 7B V1
model_type: mistral
prompt_template: '<|im_start|>system
#model-type:
##如 gpt、phi、llama、chatglm、baichuan 等
#- gpt
{system_message}<|im_end|>
#domain:
##如 nlp、cv、audio、multi-modal
#- nlp
<|im_start|>user
#language:
##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
#- cn
{prompt}<|im_end|>
#metrics:
##如 CIDEr、Blue、ROUGE 等
#- CIDEr
<|im_start|>assistant
#tags:
##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他
#- pretrained
#tools:
##如 vllm、fastchat、llamacpp、AdaSeq 等
#- vllm
'
quantized_by: TheBloke
tags:
- alignment-handbook
- generated_from_trainer
---
### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。
#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型
<!-- markdownlint-disable MD041 -->
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Juanako 7B V1 - GGUF
- Model creator: [FBL](https://huggingface.co/fblgit)
- Original model: [Juanako 7B V1](https://huggingface.co/fblgit/juanako-7b-v1)
<!-- description start -->
## Description
This repo contains GGUF format model files for [FBL's Juanako 7B V1](https://huggingface.co/fblgit/juanako-7b-v1).
These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplete list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/juanako-7B-v1-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/juanako-7B-v1-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/juanako-7B-v1-GGUF)
* [FBL's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/fblgit/juanako-7b-v1)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: ChatML
SDK下载
```bash
#安装ModelScope
pip install modelscope
```
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
<!-- prompt-template end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [juanako-7b-v1.Q2_K.gguf](https://huggingface.co/TheBloke/juanako-7B-v1-GGUF/blob/main/juanako-7b-v1.Q2_K.gguf) | Q2_K | 2 | 3.08 GB| 5.58 GB | smallest, significant quality loss - not recommended for most purposes |
| [juanako-7b-v1.Q3_K_S.gguf](https://huggingface.co/TheBloke/juanako-7B-v1-GGUF/blob/main/juanako-7b-v1.Q3_K_S.gguf) | Q3_K_S | 3 | 3.16 GB| 5.66 GB | very small, high quality loss |
| [juanako-7b-v1.Q3_K_M.gguf](https://huggingface.co/TheBloke/juanako-7B-v1-GGUF/blob/main/juanako-7b-v1.Q3_K_M.gguf) | Q3_K_M | 3 | 3.52 GB| 6.02 GB | very small, high quality loss |
| [juanako-7b-v1.Q3_K_L.gguf](https://huggingface.co/TheBloke/juanako-7B-v1-GGUF/blob/main/juanako-7b-v1.Q3_K_L.gguf) | Q3_K_L | 3 | 3.82 GB| 6.32 GB | small, substantial quality loss |
| [juanako-7b-v1.Q4_0.gguf](https://huggingface.co/TheBloke/juanako-7B-v1-GGUF/blob/main/juanako-7b-v1.Q4_0.gguf) | Q4_0 | 4 | 4.11 GB| 6.61 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [juanako-7b-v1.Q4_K_S.gguf](https://huggingface.co/TheBloke/juanako-7B-v1-GGUF/blob/main/juanako-7b-v1.Q4_K_S.gguf) | Q4_K_S | 4 | 4.14 GB| 6.64 GB | small, greater quality loss |
| [juanako-7b-v1.Q4_K_M.gguf](https://huggingface.co/TheBloke/juanako-7B-v1-GGUF/blob/main/juanako-7b-v1.Q4_K_M.gguf) | Q4_K_M | 4 | 4.37 GB| 6.87 GB | medium, balanced quality - recommended |
| [juanako-7b-v1.Q5_0.gguf](https://huggingface.co/TheBloke/juanako-7B-v1-GGUF/blob/main/juanako-7b-v1.Q5_0.gguf) | Q5_0 | 5 | 5.00 GB| 7.50 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [juanako-7b-v1.Q5_K_S.gguf](https://huggingface.co/TheBloke/juanako-7B-v1-GGUF/blob/main/juanako-7b-v1.Q5_K_S.gguf) | Q5_K_S | 5 | 5.00 GB| 7.50 GB | large, low quality loss - recommended |
| [juanako-7b-v1.Q5_K_M.gguf](https://huggingface.co/TheBloke/juanako-7B-v1-GGUF/blob/main/juanako-7b-v1.Q5_K_M.gguf) | Q5_K_M | 5 | 5.13 GB| 7.63 GB | large, very low quality loss - recommended |
| [juanako-7b-v1.Q6_K.gguf](https://huggingface.co/TheBloke/juanako-7B-v1-GGUF/blob/main/juanako-7b-v1.Q6_K.gguf) | Q6_K | 6 | 5.94 GB| 8.44 GB | very large, extremely low quality loss |
| [juanako-7b-v1.Q8_0.gguf](https://huggingface.co/TheBloke/juanako-7B-v1-GGUF/blob/main/juanako-7b-v1.Q8_0.gguf) | Q8_0 | 8 | 7.70 GB| 10.20 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/juanako-7B-v1-GGUF and below it, a specific filename to download, such as: juanako-7b-v1.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/juanako-7B-v1-GGUF juanako-7b-v1.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/juanako-7B-v1-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/juanako-7B-v1-GGUF juanako-7b-v1.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 32 -m juanako-7b-v1.Q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 2048` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries.
### How to load this model in Python code, using ctransformers
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install ctransformers
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]
# Or with AMD ROCm GPU acceleration (Linux only)
CT_HIPBLAS=1 pip install ctransformers --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems only
CT_METAL=1 pip install ctransformers --no-binary ctransformers
```
#### Simple ctransformers example code
```python
#SDK模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('TheBloke/juanako-7B-v1-GGUF')
```
Git下载
```
#Git模型下载
git clone https://www.modelscope.cn/TheBloke/juanako-7B-v1-GGUF.git
from ctransformers import AutoModelForCausalLM
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = AutoModelForCausalLM.from_pretrained("TheBloke/juanako-7B-v1-GGUF", model_file="juanako-7b-v1.Q4_K_M.gguf", model_type="mistral", gpu_layers=50)
print(llm("AI is going to"))
```
<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Brandon Frisco, LangChain4j, Spiking Neurons AB, transmissions 11, Joseph William Delisle, Nitin Borwankar, Willem Michiel, Michael Dempsey, vamX, Jeffrey Morgan, zynix, jjj, Omer Bin Jawed, Sean Connelly, jinyuan sun, Jeromy Smith, Shadi, Pawan Osman, Chadd, Elijah Stavena, Illia Dulskyi, Sebastain Graf, Stephen Murray, terasurfer, Edmond Seymore, Celu Ramasamy, Mandus, Alex, biorpg, Ajan Kanaga, Clay Pascal, Raven Klaugh, 阿明, K, ya boyyy, usrbinkat, Alicia Loh, John Villwock, ReadyPlayerEmma, Chris Smitley, Cap'n Zoog, fincy, GodLy, S_X, sidney chen, Cory Kujawski, OG, Mano Prime, AzureBlack, Pieter, Kalila, Spencer Kim, Tom X Nguyen, Stanislav Ovsiannikov, Michael Levine, Andrey, Trailburnt, Vadim, Enrico Ros, Talal Aujan, Brandon Phillips, Jack West, Eugene Pentland, Michael Davis, Will Dee, webtim, Jonathan Leane, Alps Aficionado, Rooh Singh, Tiffany J. Kim, theTransient, Luke @flexchar, Elle, Caitlyn Gatomon, Ari Malik, subjectnull, Johann-Peter Hartmann, Trenton Dambrowitz, Imad Khwaja, Asp the Wyvern, Emad Mostaque, Rainer Wilmers, Alexandros Triantafyllidis, Nicholas, Pedro Madruga, SuperWojo, Harry Royden McLaughlin, James Bentley, Olakabola, David Ziegler, Ai Maven, Jeff Scroggin, Nikolai Manek, Deo Leter, Matthew Berman, Fen Risland, Ken Nordquist, Manuel Alberto Morcote, Luke Pendergrass, TL, Fred von Graf, Randy H, Dan Guido, NimbleBox.ai, Vitor Caleffi, Gabriel Tamborski, knownsqashed, Lone Striker, Erik Bjäreholt, John Detwiler, Leonard Tan, Iucharbius
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: FBL's Juanako 7B V1
# juanako-7b-v1
This model is a fine-tuned version of [fblgit/zephyr-lora-dpo-b1](https://huggingface.co/fblgit/zephyr-lora-dpo-b1) on the HuggingFaceH4/ultrafeedback_binarized dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4594
- Rewards/chosen: -1.1095
- Rewards/rejected: -2.3132
- Rewards/accuracies: 0.7964
- Rewards/margins: 1.2037
- Logps/rejected: -220.0052
- Logps/chosen: -217.5506
- Logits/rejected: -2.5535
- Logits/chosen: -2.7973
** Please feel free to run more tests and commit the results. Also if you are interested to participate in [UNA's paper research or GPU sponsorship](mailto:info@fblnet.net) **
## Model description
**It seems to outperforms the original Zephyr in most of the tasks.**
I trained Juanako with the same datasets and trainer from [alignment-handbook/zephyr-7b-sft-lora](https://huggingface.co/alignment-handbook/zephyr-7b-sft-lora)
* 1 epoch on DPO with transformers-UNA, the result is [fblgit/zephyr-lora-dpo-b1](https://huggingface.co/fblgit/zephyr-lora-dpo-b1) after merge using FastChat converter.
* finally 1 epoch on DPO with transformers-UNA to [fblgit/zephyr-lora-dpo-b1](https://huggingface.co/fblgit/zephyr-lora-dpo-b1).
Some other experiments were performed as well to test transformers-UNA capabilities on diverse scenarios and models.
**This is a complete version of the model, the result of converting LoRa's**
## Intended uses & limitations
Research purposes.
## Training and evaluation data
alignment-handbook DPO with UNA on top of the SFT lora.
### Evaluation lm-evaluation-harness
#### GSM8K
```
hf (pretrained=/root/juanako-7b-v1-beta,load_in_4bit=False,dtype=float16), limit: None, num_fewshot: 3, batch_size: 4
```
|Tasks|Version| Filter | Metric |Value | |Stderr|
|-----|-------|----------|-----------|-----:|---|-----:|
|gsm8k|Yaml |get-answer|exact_match|0.4556|± |0.0137|
#### 0-Shot
```
hf (pretrained=fblgit/juanako-7b-v1,load_in_4bit=False,dtype=float16), limit: None, num_fewshot: 0, batch_size: 8
```
| Tasks |Version|Filter| Metric | Value | |Stderr|
|-------------------|-------|------|-----------|------:|---|-----:|
|arc_challenge |Yaml |none |acc | 0.5691|± |0.0145|
| | |none |acc_norm | 0.6041|± |0.0143|
|arc_easy |Yaml |none |acc | 0.8363|± |0.0076|
| | |none |acc_norm | 0.8161|± |0.0079|
|hellaswag |Yaml |none |acc | 0.6554|± |0.0047|
| | |none |acc_norm | 0.8411|± |0.0036|
|boolq |Yaml |none |acc | 0.8355|± |0.0065|
|lambada |N/A |none |perplexity | 3.3607|± |0.1398|
| | |none |acc | 0.7309|± |0.0137|
|piqa |Yaml |none |acc | 0.8194|± |0.0090|
| | |none |acc_norm | 0.8335|± |0.0087|
|sciq |Yaml |none |acc | 0.9480|± |0.0070|
| | |none |acc_norm | 0.8960|± |0.0097|
|truthfulqa |N/A |none |bleu_max |26.0803|± |0.6528|
| - truthfulqa_mc1 |Yaml |none |acc | 0.4198|± |0.0173|
| - truthfulqa_mc2 |Yaml |none |acc | 0.5847|± |0.0153|
|winogrande |Yaml |none |acc | 0.7609|± |0.0120|
#### 1-Shot
```
hf (pretrained=fblgit/juanako-7b-v1,load_in_4bit=False,dtype=float16), limit: None, num_fewshot: 1, batch_size: 8
```
| Tasks |Version|Filter| Metric | Value | |Stderr|
|-------------------|-------|------|-----------|------:|---|-----:|
|arc_challenge |Yaml |none |acc | 0.6084|± |0.0143|
| | |none |acc_norm | 0.6357|± |0.0141|
|arc_easy |Yaml |none |acc | 0.8645|± |0.0070|
| | |none |acc_norm | 0.8645|± |0.0070|
|hellaswag |Yaml |none |acc | 0.6475|± |0.0048|
| | |none |acc_norm | 0.8372|± |0.0037|
|boolq |Yaml |none |acc | 0.8609|± |0.0061|
|lambada |N/A |none |perplexity | 3.5484|± |0.1034|
| | |none |acc | 0.7207|± |0.0107|
|piqa |Yaml |none |acc | 0.8259|± |0.0088|
| | |none |acc_norm | 0.8384|± |0.0086|
|sciq |Yaml |none |acc | 0.9730|± |0.0051|
| | |none |acc_norm | 0.9740|± |0.0050|
|truthfulqa |N/A |none |bleu_max |18.9814|± |0.4805|
| | |none |acc | 0.4856|± |0.0521|
| - truthfulqa_mc1 |Yaml |none |acc | 0.4333|± |0.0173|
| - truthfulqa_mc2 |Yaml |none |acc | 0.5903|± |0.0153|
|winogrande |Yaml |none |acc | 0.7609|± |0.0120|
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 12
- gradient_accumulation_steps: 16
- total_train_batch_size: 192
- total_eval_batch_size: 12
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.01
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
| 0.4966 | 0.15 | 50 | 0.4893 | -1.1759 | -2.2914 | 0.7485 | 1.1155 | -219.7872 | -218.2148 | -2.5450 | -2.7884 |
| 0.4522 | 0.31 | 100 | 0.4808 | -0.8099 | -1.8893 | 0.7784 | 1.0794 | -215.7659 | -214.5544 | -2.5644 | -2.8095 |
| 0.5048 | 0.46 | 150 | 0.4706 | -1.0526 | -2.1412 | 0.7725 | 1.0887 | -218.2852 | -216.9814 | -2.5638 | -2.8089 |
| 0.4853 | 0.62 | 200 | 0.4640 | -1.0787 | -2.2821 | 0.7725 | 1.2034 | -219.6941 | -217.2426 | -2.5460 | -2.7891 |
| 0.4639 | 0.77 | 250 | 0.4636 | -1.2348 | -2.4583 | 0.8084 | 1.2235 | -221.4559 | -218.8034 | -2.5533 | -2.7970 |
| 0.4634 | 0.93 | 300 | 0.4601 | -1.1370 | -2.3243 | 0.7964 | 1.1873 | -220.1163 | -217.8257 | -2.5540 | -2.7977 |
| - | 1.00 | 300 | 0.4594 | -1.1095 | -2.3132 | 0.7964 | 1.2037 | -220.0052 | -217.5506 | -2.5535 | -2.7973 |
### Framework versions
- Transformers 4.35.0-UNA
- Pytorch 2.1.0
- Datasets 2.14.6
- Tokenizers 0.14.1
## MMLU Results
#### 1-Shot
```
hf (pretrained=fblgit/juanako-7b-v1,load_in_4bit=False,dtype=float16), limit: None, num_fewshot: 1, batch_size: 1
```
| Tasks |Version|Filter|Metric|Value | |Stderr|
|---------------------------------------|-------|------|------|-----:|---|-----:|
|mmlu |N/A |none |acc |0.6085|± |0.1321|
| - humanities |N/A |none |acc |0.5405|± |0.1478|
| - formal_logic |Yaml |none |acc |0.4206|± |0.0442|
| - high_school_european_history |Yaml |none |acc |0.7576|± |0.0335|
| - high_school_us_history |Yaml |none |acc |0.8186|± |0.0270|
| - high_school_world_history |Yaml |none |acc |0.7890|± |0.0266|
| - international_law |Yaml |none |acc |0.7438|± |0.0398|
| - jurisprudence |Yaml |none |acc |0.8056|± |0.0383|
| - logical_fallacies |Yaml |none |acc |0.7791|± |0.0326|
| - moral_disputes |Yaml |none |acc |0.7023|± |0.0246|
| - moral_scenarios |Yaml |none |acc |0.2145|± |0.0137|
| - philosophy |Yaml |none |acc |0.7074|± |0.0258|
| - prehistory |Yaml |none |acc |0.7377|± |0.0245|
| - professional_law |Yaml |none |acc |0.4361|± |0.0127|
| - world_religions |Yaml |none |acc |0.8421|± |0.0280|
| - other |N/A |none |acc |0.6894|± |0.1091|
| - business_ethics |Yaml |none |acc |0.5600|± |0.0499|
| - clinical_knowledge |Yaml |none |acc |0.6981|± |0.0283|
| - college_medicine |Yaml |none |acc |0.6185|± |0.0370|
| - global_facts |Yaml |none |acc |0.3300|± |0.0473|
| - human_aging |Yaml |none |acc |0.6726|± |0.0315|
| - management |Yaml |none |acc |0.8058|± |0.0392|
| - marketing |Yaml |none |acc |0.8419|± |0.0239|
| - medical_genetics |Yaml |none |acc |0.7200|± |0.0451|
| - miscellaneous |Yaml |none |acc |0.8033|± |0.0142|
| - nutrition |Yaml |none |acc |0.7288|± |0.0255|
| - professional_accounting |Yaml |none |acc |0.4929|± |0.0298|
| - professional_medicine |Yaml |none |acc |0.6801|± |0.0283|
| - virology |Yaml |none |acc |0.5000|± |0.0389|
| - social_sciences |N/A |none |acc |0.7195|± |0.0676|
| - econometrics |Yaml |none |acc |0.5000|± |0.0470|
| - high_school_geography |Yaml |none |acc |0.7879|± |0.0291|
| - high_school_government_and_politics|Yaml |none |acc |0.8601|± |0.0250|
| - high_school_macroeconomics |Yaml |none |acc |0.6231|± |0.0246|
| - high_school_microeconomics |Yaml |none |acc |0.6471|± |0.0310|
| - high_school_psychology |Yaml |none |acc |0.8000|± |0.0171|
| - human_sexuality |Yaml |none |acc |0.7557|± |0.0377|
| - professional_psychology |Yaml |none |acc |0.6552|± |0.0192|
| - public_relations |Yaml |none |acc |0.6636|± |0.0453|
| - security_studies |Yaml |none |acc |0.7184|± |0.0288|
| - sociology |Yaml |none |acc |0.8358|± |0.0262|
| - us_foreign_policy |Yaml |none |acc |0.8500|± |0.0359|
| - stem |N/A |none |acc |0.5217|± |0.1149|
| - abstract_algebra |Yaml |none |acc |0.3000|± |0.0461|
| - anatomy |Yaml |none |acc |0.6222|± |0.0419|
| - astronomy |Yaml |none |acc |0.6711|± |0.0382|
| - college_biology |Yaml |none |acc |0.7361|± |0.0369|
| - college_chemistry |Yaml |none |acc |0.4400|± |0.0499|
| - college_computer_science |Yaml |none |acc |0.5000|± |0.0503|
| - college_mathematics |Yaml |none |acc |0.3100|± |0.0465|
| - college_physics |Yaml |none |acc |0.4902|± |0.0497|
| - computer_security |Yaml |none |acc |0.7100|± |0.0456|
| - conceptual_physics |Yaml |none |acc |0.5362|± |0.0326|
| - electrical_engineering |Yaml |none |acc |0.5862|± |0.0410|
| - elementary_mathematics |Yaml |none |acc |0.4365|± |0.0255|
| - high_school_biology |Yaml |none |acc |0.7129|± |0.0257|
| - high_school_chemistry |Yaml |none |acc |0.5074|± |0.0352|
| - high_school_computer_science |Yaml |none |acc |0.6500|± |0.0479|
| - high_school_mathematics |Yaml |none |acc |0.3259|± |0.0286|
| - high_school_physics |Yaml |none |acc |0.3709|± |0.0394|
| - high_school_statistics |Yaml |none |acc |0.5139|± |0.0341|
| - machine_learning |Yaml |none |acc |0.5089|± |0.0475|
| Groups |Version|Filter|Metric|Value | |Stderr|
|------------------|-------|------|------|-----:|---|-----:|
|mmlu |N/A |none |acc |0.6085|± |0.1321|
| - humanities |N/A |none |acc |0.5405|± |0.1478|
| - other |N/A |none |acc |0.6894|± |0.1091|
| - social_sciences|N/A |none |acc |0.7195|± |0.0676|
| - stem |N/A |none |acc |0.5217|± |0.1149|
<!-- original-model-card end -->

3
config.json Normal file
View File

@@ -0,0 +1,3 @@
{
"model_type": "mistral"
}

1
configuration.json Normal file
View File

@@ -0,0 +1 @@
{"framework": "pytorch", "task": "others", "allow_remote": true}

3
juanako-7b-v1.Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:825e2329c0186c60f77f744475a66e1f2baf2d7763a6d7dbde147e65f16681ea
size 3083097824

3
juanako-7b-v1.Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:aed753c0d2da4a9e9ba58c005158d51747c0147df7bb2ad18ba0699b7dfc7971
size 3822024416

3
juanako-7b-v1.Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2f289eb2ca75315a7a64e5ba94e4360b307648b6fc6025c16704ede8af749ed9
size 3518985952

3
juanako-7b-v1.Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ddc0f9a8303c3509eff1d2777654b9cc732ef469e0127c732729496c8013620c
size 3164567264

3
juanako-7b-v1.Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f1e45b37f05fe8447ae973aeeffc2a81fc9364a35644f166e2de01e0db302f8d
size 4108916448

3
juanako-7b-v1.Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9ae880215a95ab2397167a9a89127e84ce6d306cdb93d18cee2dc4324746804a
size 4368439008

3
juanako-7b-v1.Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f9e559189ae988f52e05c250b777ddd7009b3489ed8ac7e579f2269c89fb620a
size 4140373728

3
juanako-7b-v1.Q5_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2f851f5f2e260811e34c3c570a2b46aad9817972057f743eb8e036423c42fba1
size 4997715680

3
juanako-7b-v1.Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2373f17fac98de6ffc72f57b48740c8ba94fb18b76bfffbe3dea4fb6ab693495
size 5131409120

3
juanako-7b-v1.Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:091966a6a1283ba4bd710912de86acd0b01553ac40182fa3ddd634281e753231
size 4997715680

3
juanako-7b-v1.Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2589198cb173bcfe0c7a76bb4930d839c0a678fb4eea08ca338d50ec1b254977
size 5942064864

3
juanako-7b-v1.Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a522b45fa7296b6f925cc94aead788dd9d11975b27f7a72b002c79ee4b2126b0
size 7695857376