mpt-7b-ggml / README.md
LLukas22's picture
Generated README.md
af6801d
|
raw
history blame
6.38 kB
---
license: apache-2.0
language:
- en
pipeline_tag: text-generation
tags:
- llm-rs
- ggml
datasets:
- mc4
- c4
- togethercomputer/RedPajama-Data-1T
- bigcode/the-stack
- allenai/s2orc
inference: false
---
# GGML converted versions of [Mosaic's](https://huggingface.co/mosaicml) MPT Models
MPT-7B is a decoder-style transformer pretrained from scratch on 1T tokens of English text and code.
This model was trained by [MosaicML](https://www.mosaicml.com).
MPT-7B is part of the family of MosaicPretrainedTransformer (MPT) models, which use a modified transformer architecture optimized for efficient training and inference.
## Converted Models:
| Name | Based on | Type | Container | GGML Version |
|:------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:-------|:------------|:---------------|
| [mpt-7b-chat-f16.bin](https://huggingface.co/rustformers/mpt-7b-ggml/blob/main/mpt-7b-chat-f16.bin) | [mosaicml/mpt-7b-chat](https://huggingface.co/mosaicml/mpt-7b-chat) | F16 | GGML | V3 |
| [mpt-7b-chat-q4_0.bin](https://huggingface.co/rustformers/mpt-7b-ggml/blob/main/mpt-7b-chat-q4_0.bin) | [mosaicml/mpt-7b-chat](https://huggingface.co/mosaicml/mpt-7b-chat) | Q4_0 | GGML | V3 |
| [mpt-7b-chat-q4_0-ggjt.bin](https://huggingface.co/rustformers/mpt-7b-ggml/blob/main/mpt-7b-chat-q4_0-ggjt.bin) | [mosaicml/mpt-7b-chat](https://huggingface.co/mosaicml/mpt-7b-chat) | Q4_0 | GGJT | V3 |
| [mpt-7b-chat-q5_1-ggjt.bin](https://huggingface.co/rustformers/mpt-7b-ggml/blob/main/mpt-7b-chat-q5_1-ggjt.bin) | [mosaicml/mpt-7b-chat](https://huggingface.co/mosaicml/mpt-7b-chat) | Q5_1 | GGJT | V3 |
| [mpt-7b-f16.bin](https://huggingface.co/rustformers/mpt-7b-ggml/blob/main/mpt-7b-f16.bin) | [mosaicml/mpt-7b](https://huggingface.co/mosaicml/mpt-7b) | F16 | GGML | V3 |
| [mpt-7b-instruct-f16.bin](https://huggingface.co/rustformers/mpt-7b-ggml/blob/main/mpt-7b-instruct-f16.bin) | [mosaicml/mpt-7b-instruct](https://huggingface.co/mosaicml/mpt-7b-instruct) | F16 | GGML | V3 |
| [mpt-7b-instruct-q4_0.bin](https://huggingface.co/rustformers/mpt-7b-ggml/blob/main/mpt-7b-instruct-q4_0.bin) | [mosaicml/mpt-7b-instruct](https://huggingface.co/mosaicml/mpt-7b-instruct) | Q4_0 | GGML | V3 |
| [mpt-7b-instruct-q4_0-ggjt.bin](https://huggingface.co/rustformers/mpt-7b-ggml/blob/main/mpt-7b-instruct-q4_0-ggjt.bin) | [mosaicml/mpt-7b-instruct](https://huggingface.co/mosaicml/mpt-7b-instruct) | Q4_0 | GGJT | V3 |
| [mpt-7b-instruct-q5_1-ggjt.bin](https://huggingface.co/rustformers/mpt-7b-ggml/blob/main/mpt-7b-instruct-q5_1-ggjt.bin) | [mosaicml/mpt-7b-instruct](https://huggingface.co/mosaicml/mpt-7b-instruct) | Q5_1 | GGJT | V3 |
| [mpt-7b-q4_0.bin](https://huggingface.co/rustformers/mpt-7b-ggml/blob/main/mpt-7b-q4_0.bin) | [mosaicml/mpt-7b](https://huggingface.co/mosaicml/mpt-7b) | Q4_0 | GGML | V3 |
| [mpt-7b-q4_0-ggjt.bin](https://huggingface.co/rustformers/mpt-7b-ggml/blob/main/mpt-7b-q4_0-ggjt.bin) | [mosaicml/mpt-7b](https://huggingface.co/mosaicml/mpt-7b) | Q4_0 | GGJT | V3 |
| [mpt-7b-q5_1-ggjt.bin](https://huggingface.co/rustformers/mpt-7b-ggml/blob/main/mpt-7b-q5_1-ggjt.bin) | [mosaicml/mpt-7b](https://huggingface.co/mosaicml/mpt-7b) | Q5_1 | GGJT | V3 |
| [mpt-7b-storywriter-f16.bin](https://huggingface.co/rustformers/mpt-7b-ggml/blob/main/mpt-7b-storywriter-f16.bin) | [mosaicml/mpt-7b-storywriter](https://huggingface.co/mosaicml/mpt-7b-storywriter) | F16 | GGML | V3 |
| [mpt-7b-storywriter-q4_0.bin](https://huggingface.co/rustformers/mpt-7b-ggml/blob/main/mpt-7b-storywriter-q4_0.bin) | [mosaicml/mpt-7b-storywriter](https://huggingface.co/mosaicml/mpt-7b-storywriter) | Q4_0 | GGML | V3 |
| [mpt-7b-storywriter-q4_0-ggjt.bin](https://huggingface.co/rustformers/mpt-7b-ggml/blob/main/mpt-7b-storywriter-q4_0-ggjt.bin) | [mosaicml/mpt-7b-storywriter](https://huggingface.co/mosaicml/mpt-7b-storywriter) | Q4_0 | GGJT | V3 |
| [mpt-7b-storywriter-q5_1-ggjt.bin](https://huggingface.co/rustformers/mpt-7b-ggml/blob/main/mpt-7b-storywriter-q5_1-ggjt.bin) | [mosaicml/mpt-7b-storywriter](https://huggingface.co/mosaicml/mpt-7b-storywriter) | Q5_1 | GGJT | V3 |
⚠️Caution⚠️: mpt-7b-storywriter is still under development!
## Usage
### Python via [llm-rs](https://github.com/LLukas22/llm-rs-python):
#### Installation
Via pip: `pip install llm-rs`
#### Run inference
```python
from llm_rs import AutoModel
#Load the model, define any model you like from the list above as the `model_file`
model = AutoModel.from_pretrained("rustformers/mpt-7b-ggml",model_file="mpt-7b-q4_0-ggjt.bin")
#Generate
print(model.generate("The meaning of life is"))
```
### Rust via [rustformers/llm](https://github.com/rustformers/llm):
#### Installation
```
git clone --recurse-submodules https://github.com/rustformers/llm.git
cd llm
cargo build --release
```
#### Run inference
```
cargo run --release -- mpt infer -m path/to/model.bin -p "Tell me how cool the Rust programming language is:"
```
### C via [GGML](https://github.com/ggerganov/ggml)
The `GGML` example only supports the ggml container type!
#### Installation
```
git clone https://github.com/ggerganov/ggml
cd ggml
mkdir build && cd build
cmake ..
make -j4 mpt
```
#### Run inference
```
./bin/mpt -m path/to/model.bin -p "The meaning of life is"
```