|
--- |
|
language: |
|
- en |
|
tags: |
|
- llm-rs |
|
- ggml |
|
pipeline_tag: text-generation |
|
datasets: |
|
- the_pile |
|
--- |
|
|
|
# GGML covnerted Models of [EleutherAI](https://huggingface.co/EleutherAI)'s GPT-J model |
|
|
|
## Description |
|
|
|
GPT-J 6B is a transformer model trained using Ben Wang's [Mesh Transformer JAX](https://github.com/kingoflolz/mesh-transformer-jax/). "GPT-J" refers to the class of model, while "6B" represents the number of trainable parameters. |
|
|
|
<figure> |
|
|
|
| Hyperparameter | Value | |
|
|----------------------|------------| |
|
| \\(n_{parameters}\\) | 6053381344 | |
|
| \\(n_{layers}\\) | 28* | |
|
| \\(d_{model}\\) | 4096 | |
|
| \\(d_{ff}\\) | 16384 | |
|
| \\(n_{heads}\\) | 16 | |
|
| \\(d_{head}\\) | 256 | |
|
| \\(n_{ctx}\\) | 2048 | |
|
| \\(n_{vocab}\\) | 50257/50400† (same tokenizer as GPT-2/3) | |
|
| Positional Encoding | [Rotary Position Embedding (RoPE)](https://arxiv.org/abs/2104.09864) | |
|
| RoPE Dimensions | [64](https://github.com/kingoflolz/mesh-transformer-jax/blob/f2aa66e0925de6593dcbb70e72399b97b4130482/mesh_transformer/layers.py#L223) | |
|
<figcaption><p><strong>*</strong> Each layer consists of one feedforward block and one self attention block.</p> |
|
<p><strong>†</strong> Although the embedding matrix has a size of 50400, only 50257 entries are used by the GPT-2 tokenizer.</p></figcaption></figure> |
|
|
|
The model consists of 28 layers with a model dimension of 4096, and a feedforward dimension of 16384. The model |
|
dimension is split into 16 heads, each with a dimension of 256. Rotary Position Embedding (RoPE) is applied to 64 |
|
dimensions of each head. The model is trained with a tokenization vocabulary of 50257, using the same set of BPEs as |
|
GPT-2/GPT-3. |
|
|
|
|
|
## Converted Models |
|
| Name | Based on | Type | Container | GGML Version | |
|
|:---------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------|:-------|:------------|:---------------| |
|
| [gpt-j-6b-f16.bin](https://huggingface.co/rustformers/gpt-j-ggml/blob/main/gpt-j-6b-f16.bin) | [EleutherAI/gpt-j-6b](https://huggingface.co/EleutherAI/gpt-j-6b) | F16 | GGML | V3 | |
|
| [gpt-j-6b-q4_0.bin](https://huggingface.co/rustformers/gpt-j-ggml/blob/main/gpt-j-6b-q4_0.bin) | [EleutherAI/gpt-j-6b](https://huggingface.co/EleutherAI/gpt-j-6b) | Q4_0 | GGML | V3 | |
|
| [gpt-j-6b-q4_0-ggjt.bin](https://huggingface.co/rustformers/gpt-j-ggml/blob/main/gpt-j-6b-q4_0-ggjt.bin) | [EleutherAI/gpt-j-6b](https://huggingface.co/EleutherAI/gpt-j-6b) | Q4_0 | GGJT | V3 | |
|
| [gpt-j-6b-q5_1-ggjt.bin](https://huggingface.co/rustformers/gpt-j-ggml/blob/main/gpt-j-6b-q5_1-ggjt.bin) | [EleutherAI/gpt-j-6b](https://huggingface.co/EleutherAI/gpt-j-6b) | Q5_1 | GGJT | V3 | |
|
|
|
## 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/gpt-j-ggml",model_file="gpt-j-6b-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 -- gptj infer -m path/to/model.bin -p "Tell me how cool the Rust programming language is:" |
|
``` |
