|
--- |
|
base_model: meta-llama/Meta-Llama-3-8B |
|
inference: false |
|
model_creator: astronomer-io |
|
model_name: Meta-Llama-3-8B |
|
model_type: llama |
|
pipeline_tag: text-generation |
|
quantized_by: davidxmle |
|
license: other |
|
license_name: llama-3 |
|
license_link: https://huggingface.co./meta-llama/Meta-Llama-3-8B/blob/main/LICENSE |
|
tags: |
|
- llama |
|
- llama-3 |
|
- facebook |
|
- meta |
|
- astronomer |
|
- gptq |
|
- pretrained |
|
- quantized |
|
- finetuned |
|
- autotrain_compatible |
|
- endpoints_compatible |
|
datasets: |
|
- wikitext |
|
--- |
|
<!-- header start --> |
|
<!-- 200823 --> |
|
<div style="width: auto; margin-left: auto; margin-right: auto"> |
|
<img src="https://www.astronomer.io/logo/astronomer-logo-RGB-standard-1200px.png" alt="Astronomer" style="width: 60%; min-width: 400px; display: block; margin: auto;"> |
|
</div> |
|
<div style="margin-top: 1.0em; margin-bottom: 1.0em;"></div> |
|
|
|
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">This model is generously created and made open source by <a href="https://astronomer.io">Astronomer</a>.</p></div> |
|
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">Astronomer is the de facto company for <a href="https://airflow.apache.org/">Apache Airflow</a>, the most trusted open-source framework for data orchestration and MLOps.</p></div> |
|
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;"> |
|
<!-- header end --> |
|
|
|
# Llama-3-8B-GPTQ-8-Bit |
|
- Original Model creator: [Meta Llama from Meta](https://huggingface.co./meta-llama) |
|
- Original model: [meta-llama/Meta-Llama-3-8B](https://huggingface.co./meta-llama/Meta-Llama-3-8B) |
|
- Built with Meta Llama 3 |
|
- Quantized by [David Xue](https://www.linkedin.com/in/david-xue-uva/) from [Astronomer](https://astronomer.io) |
|
|
|
## MUST READ: Very Important!! Note About Untrained Special Tokens in Llama 3 Base (Non-instruct) Models & Fine-tuning Llama 3 Base |
|
- **If you intend to fine-tune this model with any added tokens, or fine-tune for instruction following, please use the [untrained-special-tokens-fixed](https://huggingface.co./astronomer-io/Llama-3-8B-GPTQ-4-Bit/tree/untrained-special-tokens-fixed) branch/revision.** |
|
- Special tokens such as the ones used for instruct are undertrained in Llama 3 base models. |
|
- Credits: discovered by Daniel Han https://twitter.com/danielhanchen/status/1781395882925343058 |
|
- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/655ad0f8727df37c77a09cb9/1U2rRrx60p1pNeeAZw8Rd.png) |
|
|
|
## Important Note About Serving with vLLM & oobabooga/text-generation-webui |
|
- For loading this model onto vLLM, make sure all requests have `"stop_token_ids":[128001, 128009]` to temporarily address the non-stop generation issue. |
|
- vLLM does not yet respect `generation_config.json`. |
|
- vLLM team is working on a a fix for this https://github.com/vllm-project/vllm/issues/4180 |
|
- For oobabooga/text-generation-webui |
|
- Load the model via AutoGPTQ, with `no_inject_fused_attention` enabled. This is a bug with AutoGPTQ library. |
|
- Under `Parameters` -> `Generation` -> `Skip special tokens`: turn this off (deselect) |
|
- Under `Parameters` -> `Generation` -> `Custom stopping strings`: add `"<|end_of_text|>","<|eot_id|>"` to the field |
|
|
|
<!-- description start --> |
|
## Description |
|
|
|
This repo contains 4 Bit quantized GPTQ model files for [meta-llama/Meta-Llama-3-8B](https://huggingface.co./meta-llama/Meta-Llama-3-8B). |
|
|
|
This model can be loaded with less than 6 GB of VRAM (huge reduction from the original 16.07GB model) and can be served lightning fast with the cheapest Nvidia GPUs possible (Nvidia T4, Nvidia K80, RTX 4070, etc). |
|
|
|
The 4 bit GPTQ quant has small quality degradation from the original `bfloat16` model but can be served on much smaller GPUs with maximum improvement in latency and throughput. |
|
|
|
The `untrained-special-tokens-fixed` branch is the same model as the main branch but has special tokens and tokens untrained (by finding the tokens where max embedding value of each token in input_embeddings and output_embeddings is 0) and setting them to the average of all trained tokens for each feature. Using this branch is recommended if you plan to do any fine-tuning with your own tokens added or with instruction following. |
|
|
|
<!-- description end --> |
|
|
|
## GPTQ Quantization Method |
|
- This model is quantized by utilizing the AutoGPTQ library, following best practices noted by [GPTQ paper](https://arxiv.org/abs/2210.17323) |
|
- Quantization is calibrated and aligned with random samples from the specified dataset (wikitext for now) for minimum accuracy loss. |
|
|
|
| Branch | Bits | Group Size | Act Order | Damp % | GPTQ Dataset | Sequence Length | VRAM Size | ExLlama | Special Tokens Fixed | Description | |
|
| ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ------- | ---- | |
|
| [main](https://huggingface.co./astronomer-io/Llama-3-8B-GPTQ-4-Bit/tree/main) | 4 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co./datasets/wikitext/viewer/wikitext-2-v1/test) | 8192 | 5.74 GB | Yes | No | 4-bit, with Act Order and group size 128g. Smallest model possible with small accuracy loss | |
|
| [untrained-special-tokens-fixed](https://huggingface.co./astronomer-io/Llama-3-8B-GPTQ-4-Bit/tree/untrained-special-tokens-fixed) | 4 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co./datasets/wikitext/viewer/wikitext-2-v1/test) | 8192 | 5.74 GB | Yes | Yes | Same as the main branch. The special tokens that were untrained causing exploding gradients/NaN gradients have had their embedding values set to the average of trained tokens for each feature | |
|
| More variants to come | TBD | TBD | TBD | TBD | TBD | TBD | TBD | TBD | TBD | May upload additional variants of GPTQ 4 bit models in the future using different parameters such as 128g group size and etc. | |
|
|
|
## Serving this GPTQ model using vLLM |
|
Tested serving this model via vLLM using an Nvidia T4 (16GB VRAM). |
|
|
|
Tested with the below command |
|
```bash |
|
python -m vllm.entrypoints.openai.api_server --model astronomer-io/Llama-3-8B-GPTQ-4-Bit --max-model-len 8192 --dtype float16 |
|
``` |
|
For the non-stop token generation bug, make sure to send requests with `stop_token_ids":[128001, 128009]` to vLLM endpoint |
|
### Contributors |
|
- Quantized by [David Xue, Machine Learning Engineer from Astronomer](https://www.linkedin.com/in/david-xue-uva/) |
|
|