yi-6B-GGUF / README.md
Jezzarax's picture
Update README.md with license information (#1)
87b2a8e verified
---
base_model: 01-ai/Yi-6B
inference: false
model_creator: 01-ai
model_name: Yi 6B
model_type: yi
prompt_template: 'Human: {prompt} Assistant:
'
quantized_by: jezzarax
license: apache-2.0
---
<!-- markdownlint-disable MD041 -->
# Yi 6B - GGUF
- Model creator: [01-ai](https://huggingface.co/01-ai)
- Original model: [Yi 34B](https://huggingface.co/01-ai/Yi-6B)
- Readme and repo format by [TheBloke](https://huggingface.co/TheBloke/) and his [Yi-34B-GGUF repo](https://huggingface.co/TheBloke/Yi-34B-GGUF)
<!-- description start -->
## Description
This repo contains GGUF format model files for [01-ai's Yi 6B](https://huggingface.co/01-ai/Yi-6B).
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
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/jezzarax/yi-6b-GGUF)
* [01-ai's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/01-ai/Yi-6B)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Yi
```
Human: {prompt} 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 | Use case |
| ---- | ---- | ---- | ---- | ----- |
| [yi-6b.Q2_K.gguf](https://huggingface.co/jezzarax/yi-6b-GGUF/blob/main/yi-6b.Q2_K.gguf) | Q2_K | 2 | 2.5 GB| smallest, significant quality loss - not recommended for most purposes |
| [yi-6b.Q3_K_S.gguf](https://huggingface.co/jezzarax/yi-6b-GGUF/blob/main/yi-6b.Q3_K_S.gguf) | Q3_K_S | 3 | 2.6 GB| very small, high quality loss |
| [yi-6b.Q3_K.gguf](https://huggingface.co/jezzarax/yi-6b-GGUF/blob/main/yi-6b.Q3_K.gguf) | Q3_K_M | 3 | 2.8 GB| very small, high quality loss |
| [yi-6b.Q3_K_L.gguf](https://huggingface.co/jezzarax/yi-6b-GGUF/blob/main/yi-6b.Q3_K_L.gguf) | Q3_K_L | 3 | 3.1 GB| small, substantial quality loss |
| [yi-6b.Q4_K_S.gguf](https://huggingface.co/jezzarax/yi-6b-GGUF/blob/main/yi-6b.Q4_K_S.gguf) | Q4_K_S | 4 | 3.3 GB | small, greater quality loss |
| [yi-6b.Q4_K.gguf](https://huggingface.co/jezzarax/yi-6b-GGUF/blob/main/yi-6b.Q4_K.gguf) | Q4_K | 4 | 3.5 GB GB | medium, balanced quality - recommended |
| [yi-6b.Q5_K_S.gguf](https://huggingface.co/jezzarax/yi-6b-GGUF/blob/main/yi-6b.Q5_K_S.gguf) | Q5_K_S | 5 | 4.0 GB | large, low quality loss - recommended |
| [yi-6b.Q5_K.gguf](https://huggingface.co/jezzarax/yi-6b-GGUF/blob/main/yi-6b.Q5_K.gguf) | Q5_K | 5 | 4.1 GB | large, very low quality loss - recommended |
| [yi-6b.Q6_K.gguf](https://huggingface.co/jezzarax/yi-6b-GGUF/blob/main/yi-6b.Q6_K.gguf) | Q6_K | 6 | 4.7 GB | very large, extremely low quality loss |
| [yi-6b.f16.gguf](https://huggingface.co/jezzarax/yi-6b-GGUF/blob/main/yi-6b.f16.gguf) | f16 | 16 | 12 GB| very large, no 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: jezzarax/yi-6b-GGUF and below it, a specific filename to download, such as: yi-6b.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 jezzarax/yi-6b-GGUF yi-6b.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 jezzarax/yi-6b-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 jezzarax/yi-6b-GGUF yi-6b.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 yi-6b.Q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Human: {prompt} 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 here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md).
## 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
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("jezzarax/yi-6b-GGUF", model_file="yi-6b.Q4_K_M.gguf", model_type="yi", gpu_layers=50)
print(llm("AI is going to"))
```
## 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 -->
<!-- original-model-card start -->
# Original model card: 01-ai's Yi 6B
<div align="center">
<img src="./Yi.svg" width="200px">
</div>
## Introduction
The **Yi** series models are large language models trained from scratch by
developers at [01.AI](https://01.ai/). The first public release contains two
bilingual(English/Chinese) base models with the parameter sizes of 6B([`Yi-6B`](https://huggingface.co/01-ai/Yi-6B))
and 34B([`Yi-34B`](https://huggingface.co/01-ai/Yi-34B)). Both of them are trained
with 4K sequence length and can be extended to 32K during inference time.
The [`Yi-6B-200K`](https://huggingface.co/01-ai/Yi-6B-200K)
and [`Yi-34B-200K`](https://huggingface.co/01-ai/Yi-34B-200K) are base model with
200K context length.
## News
- 🎯 **2023/11/06**: The base model of [`Yi-6B-200K`](https://huggingface.co/01-ai/Yi-6B-200K)
and [`Yi-34B-200K`](https://huggingface.co/01-ai/Yi-34B-200K) with 200K context length.
- 🎯 **2023/11/02**: The base model of [`Yi-6B`](https://huggingface.co/01-ai/Yi-6B) and
[`Yi-34B`](https://huggingface.co/01-ai/Yi-34B).
## Model Performance
| Model | MMLU | CMMLU | C-Eval | GAOKAO | BBH | Common-sense Reasoning | Reading Comprehension | Math & Code |
| :------------ | :------: | :------: | :------: | :------: | :------: | :--------------------: | :-------------------: | :---------: |
| | 5-shot | 5-shot | 5-shot | 0-shot | 3-shot@1 | - | - | - |
| LLaMA2-34B | 62.6 | - | - | - | 44.1 | 69.9 | 68.0 | 26.0 |
| LLaMA2-70B | 68.9 | 53.3 | - | 49.8 | 51.2 | 71.9 | 69.4 | 36.8 |
| Baichuan2-13B | 59.2 | 62.0 | 58.1 | 54.3 | 48.8 | 64.3 | 62.4 | 23.0 |
| Qwen-14B | 66.3 | 71.0 | 72.1 | 62.5 | 53.4 | 73.3 | 72.5 | **39.8** |
| Skywork-13B | 62.1 | 61.8 | 60.6 | 68.1 | 41.7 | 72.4 | 61.4 | 24.9 |
| InternLM-20B | 62.1 | 59.0 | 58.8 | 45.5 | 52.5 | 78.3 | - | 30.4 |
| Aquila-34B | 67.8 | 71.4 | 63.1 | - | - | - | - | - |
| Falcon-180B | 70.4 | 58.0 | 57.8 | 59.0 | 54.0 | 77.3 | 68.8 | 34.0 |
| Yi-6B | 63.2 | 75.5 | 72.0 | 72.2 | 42.8 | 72.3 | 68.7 | 19.8 |
| Yi-6B-200K | 64.0 | 75.3 | 73.5 | 73.9 | 42.0 | 72.0 | 69.1 | 19.0 |
| **Yi-34B** | **76.3** | **83.7** | 81.4 | 82.8 | **54.3** | **80.1** | 76.4 | 37.1 |
| Yi-34B-200K | 76.1 | 83.6 | **81.9** | **83.4** | 52.7 | 79.7 | **76.6** | 36.3 |
While benchmarking open-source models, we have observed a disparity between the
results generated by our pipeline and those reported in public sources (e.g.
OpenCompass). Upon conducting a more in-depth investigation of this difference,
we have discovered that various models may employ different prompts,
post-processing strategies, and sampling techniques, potentially resulting in
significant variations in the outcomes. Our prompt and post-processing strategy
remains consistent with the original benchmark, and greedy decoding is employed
during evaluation without any post-processing for the generated content. For
scores that were not reported by the original authors (including scores reported
with different settings), we try to get results with our pipeline.
To evaluate the model's capability extensively, we adopted the methodology
outlined in Llama2. Specifically, we included PIQA, SIQA, HellaSwag, WinoGrande,
ARC, OBQA, and CSQA to assess common sense reasoning. SquAD, QuAC, and BoolQ
were incorporated to evaluate reading comprehension. CSQA was exclusively tested
using a 7-shot setup, while all other tests were conducted with a 0-shot
configuration. Additionally, we introduced GSM8K (8-shot@1), MATH (4-shot@1),
HumanEval (0-shot@1), and MBPP (3-shot@1) under the category "Math & Code". Due
to technical constraints, we did not test Falcon-180 on QuAC and OBQA; the score
is derived by averaging the scores on the remaining tasks. Since the scores for
these two tasks are generally lower than the average, we believe that
Falcon-180B's performance was not underestimated.
## Usage
Please visit our [github repository](https://github.com/01-ai/Yi) for general
guidance on how to use this model.
## Disclaimer
Although we use data compliance checking algorithms during the training process
to ensure the compliance of the trained model to the best of our ability, due to
the complexity of the data and the diversity of language model usage scenarios,
we cannot guarantee that the model will generate correct and reasonable output
in all scenarios. Please be aware that there is still a risk of the model
producing problematic outputs. We will not be responsible for any risks and
issues resulting from misuse, misguidance, illegal usage, and related
misinformation, as well as any associated data security concerns.
## License
The Yi series models are fully open for academic research and free commercial
usage with permission via applications. All usage must adhere to the [Model
License Agreement 2.0](https://huggingface.co/01-ai/Yi-34B/blob/main/LICENSE). To
apply for the official commercial license, please contact us
([yi@01.ai](mailto:yi@01.ai)).
<!-- original-model-card end -->