---
license: apache-2.0
datasets:
- mosaicml/dolly_hhrlhf
language:
- en
library_name: transformers
pipeline_tag: text-generation
---

# VMware/open-llama-0.3T-7B-instruct-dolly-hhrlhf

Fully Open Source, Commerically viable.

The instruction dataset, [mosaicml/dolly_hhrlhf](https://huggingface.co/datasets/mosaicml/dolly_hhrlhf) is under cc-by-sa-3.0, and the Language Model ([openlm-research/open_llama_7b_preview_300bt](https://huggingface.co/openlm-research/open_llama_7b_preview_300bt/tree/main/open_llama_7b_preview_300bt_transformers_weights)) is under apache-2.0 License. 

## Use in Transformers

Please load the tokenizer with 'add_bos_token = True' parameter as the underlying OpenLLaMa model and this model were trained with a BOS token. 

```
import os
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = 'VMware/open-llama-0.3T-7B-instruct-dolly-hhrlhf'


tokenizer = AutoTokenizer.from_pretrained(model_name, add_bos_token = True)

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype= torch.float16, device_map = 'sequential')

prompt_template = "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{instruction}\n\n### Response:"

prompt=  'how do I bake a cake?'


inputt = prompt_template.format(instruction= prompt)
input_ids = tokenizer(inputt, return_tensors="pt").input_ids.to("cuda")

output1 = model.generate(input_ids, max_length=512)
input_length = input_ids.shape[1]
output1 = output1[:, input_length:]
output= tokenizer.decode(output1[0])

print(output)

'''
Baking a cake is a simple process. You will need to prepare a cake mixture, then bake it in the oven. You can add various ingredients to the cake mixture, such as fruit, nuts, or spices, to make it flavorful. Baking a cake can be fun, as it creates a delicious dessert!</s>

'''
```



## Drawbacks
<ul>
<li>The model was trained on a partially trained Open-LLaMA checkpoint. (300B tokens).
</ul>

## Evaluation

<B>TODO</B>