---
license: cc
datasets:
- VMware/open-instruct-v1-oasst-dolly-hhrlhf
language:
- en
library_name: transformers
pipeline_tag: text-generation
---

# VMware/open-llama-7B-open-instruct
Instruction-tuned version of SalesForce/Xgen-7b-8k-base. The model is open for <b>COMMERCIAL USE</b>. <br>

We expanded Open-instruct with additional commercially viable zero-shot COT datasets from Flan v2 (~70k). (TODO: List out the datasets) <br>

The model supports up to <b>8192 tokens </b>

<b> NOTE </b> : The model was trained using the Alpaca prompt template


## License
- <b>Commercially Viable </b>
- The instruction datasets used for instruction tuning are open for commercial usage. (TODO LIST OUT THE DATASETS)
- Language Model, ([Salesforce/xgen-7b-8k-base](https://huggingface.co/Salesforce/xgen-7b-8k-base)) is under apache-2.0



## Use in Transformers

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

model_name = 'VMware/xgen-7b-8k-open-instruct'


tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=False, trust_remote_code = True)

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, 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 = 'Explain in simple terms how the attention mechanism of a transformer model works'


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

output1 = model.generate(input_ids, max_length=8192)
input_length = input_ids.shape[1]
output1 = output1[:, input_length:]
output = tokenizer.decode(output1[0])

print(output)

```
  
## Finetuning details
The finetuning scripts will be available in our [RAIL Github Repository](https://github.com/vmware-labs/research-and-development-artificial-intelligence-lab/tree/main/instruction-tuning)
## Evaluation

<B>TODO</B>