---
tags:
- ctranslate2
- int8
- float16

license: cc
datasets:
- VMware/open-instruct-v1-oasst-dolly-hhrlhf
language:
- en
library_name: transformers
pipeline_tag: text-generation
---
# # Fast-Inference with Ctranslate2
Speedup inference while reducing memory by 2x-4x using int8 inference in C++ on CPU or GPU.

quantized version of [VMware/open-llama-13b-open-instruct](https://huggingface.co/VMware/open-llama-13b-open-instruct)
```bash
pip install hf-hub-ctranslate2>=2.12.0 ctranslate2>=3.16.0
```

```python
# from transformers import AutoTokenizer
model_name = "michaelfeil/ct2fast-open-llama-13b-open-instruct"


from hf_hub_ctranslate2 import GeneratorCT2fromHfHub
model = GeneratorCT2fromHfHub(
        # load in int8 on CUDA
        model_name_or_path=model_name,
        device="cuda",
        compute_type="int8_float16",
        # tokenizer=AutoTokenizer.from_pretrained("{ORG}/{NAME}")
)
outputs = model.generate(
    text=["def fibonnaci(", "User: How are you doing? Bot:"],
    max_length=64,
    include_prompt_in_result=False
)
print(outputs)
```

Checkpoint compatible to [ctranslate2>=3.16.0](https://github.com/OpenNMT/CTranslate2)
and [hf-hub-ctranslate2>=2.12.0](https://github.com/michaelfeil/hf-hub-ctranslate2)
- `compute_type=int8_float16` for `device="cuda"`
- `compute_type=int8`  for `device="cpu"`

Converted on 2023-06-27 using
```
ct2-transformers-converter --model VMware/open-llama-13b-open-instruct --output_dir ~/tmp-ct2fast-open-llama-13b-open-instruct --force --copy_files README.md tokenizer_config.json generation_config.json special_tokens_map.json .gitattributes --quantization int8_float16 --trust_remote_code
```

# Licence and other remarks:
This is just a quantized version. Licence conditions are intended to be idential to original huggingface repo.

# Original description
    

# VMware/open-llama-13B-open-instruct
Instruction-tuned version of the fully trained Open LLama 13B model. The model is open for <b>COMMERCIAL USE</b>. <br>

<b> NOTE </b> : The model was trained using the Alpaca prompt template \
<b> NOTE </b> : Fast tokenizer results in incorrect encoding, set the ```use_fast = False``` parameter, when instantiating the tokenizer\
<b> NOTE </b> : The model might struggle with code as the tokenizer merges multiple spaces

## License
- <b>Commercially Viable </b>
- Instruction dataset, [VMware/open-instruct-v1-oasst-dolly-hhrlhf](https://huggingface.co/datasets/VMware/open-instruct-v1-oasst-dolly-hhrlhf) is under cc-by-sa-3.0
- Language Model, ([openlm-research/open_llama_13b](https://huggingface.co/openlm-research/open_llama_13b)) is under apache-2.0


## Nomenclature 

- Model : Open-llama
- Model Size: 13B parameters
- Dataset: Open-instruct-v1 (oasst,dolly, hhrlhf)

## Use in Transformers

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

model_name = 'VMware/open-llama-13b-open-instruct'


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

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 = '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=512)
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>