---
license: mit
datasets:
- databricks/databricks-dolly-15k
language:
- en
pipeline_tag: text-generation
tags:
- dolly
- dolly-v2
- instruct
- sharded
- 8bit
- quantized
inference: false
---

# dolly-v2-12b: sharded **8bit** checkpoint 


This is a sharded checkpoint (with ~4GB shards) of the `databricks/dolly-v2-12b` model **in `8bit` precision** using `bitsandbytes`.

Refer to the [original model](https://huggingface.co/databricks/dolly-v2-12b) for all details w.r.t. to the model. For more info on loading 8bit models, refer to the [example repo](https://huggingface.co/ybelkada/bloom-1b7-8bit) and/or the `4.28.0` [release info](https://github.com/huggingface/transformers/releases/tag/v4.28.0).

- total model size is only ~12.5 GB!
- this enables low-RAM loading, i.e. Colab :)

## Basic Usage


install/upgrade `transformers`, `accelerate`, and `bitsandbytes`. For this to work **you must have** `transformers>=4.28.0` and `bitsandbytes>0.37.2`.

```bash
pip install -U -q transformers bitsandbytes accelerate
```

Load the model. As it is serialized in 8bit you don't need to do anything special:

```python
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "ethzanalytics/dolly-v2-12b-sharded-8bit"
tokenizer = AutoTokenizer.from_pretrained(model_name)

model = AutoModelForCausalLM.from_pretrained(model_name)
```