Hugging Face's logo

michaelfeil
/
ct2fast-RedPajama-INCITE-Instruct-3B-v1

Transformers
English ctranslate2 int8 float16 Inference Endpoints
Model card Files Community
Edit model card

# Fast-Inference with Ctranslate2

Speedup inference while reducing memory by 2x-4x using int8 inference in C++ on CPU or GPU.

quantized version of togethercomputer/RedPajama-INCITE-Instruct-3B-v1

pip install hf-hub-ctranslate2>=2.0.6

Converted on 2023-05-19 using

ct2-transformers-converter --model togethercomputer/RedPajama-INCITE-Instruct-3B-v1 --output_dir /home/michael/tmp-ct2fast-RedPajama-INCITE-Instruct-3B-v1 --force --copy_files tokenizer.json README.md tokenizer_config.json generation_config.json special_tokens_map.json .gitattributes --quantization float16

Checkpoint compatible to ctranslate2>=3.13.0 and hf-hub-ctranslate2>=2.0.6

  • compute_type=int8_float16 for device="cuda"
  • compute_type=int8 for device="cpu"
from hf_hub_ctranslate2 import TranslatorCT2fromHfHub, GeneratorCT2fromHfHub
from transformers import AutoTokenizer

model_name = "michaelfeil/ct2fast-RedPajama-INCITE-Instruct-3B-v1"
# use either TranslatorCT2fromHfHub or GeneratorCT2fromHfHub here, depending on model.
model = GeneratorCT2fromHfHub(
        # load in int8 on CUDA
        model_name_or_path=model_name, 
        device="cuda",
        compute_type="int8_float16",
        tokenizer=AutoTokenizer.from_pretrained("togethercomputer/RedPajama-INCITE-Instruct-3B-v1")
)
outputs = model.generate(
    text=["How do you call a fast Flan-ingo?", "User: How are you doing? Bot:"],
)
print(outputs)

Licence and other remarks:

This is just a quantized version. Licence conditions are intended to be idential to original huggingface repo.

Original description

tags:

  • ctranslate2
  • int8
  • float16

RedPajama-INCITE-Instruct-3B-v1

RedPajama-INCITE-Instruct-3B-v1 was developed by Together and leaders from the open-source AI community including Ontocord.ai, ETH DS3Lab, AAI CERC, Université de Montréal, MILA - Québec AI Institute, Stanford Center for Research on Foundation Models (CRFM), Stanford Hazy Research research group and LAION.

The model was fine-tuned for few-shot applications on the data of GPT-JT, with exclusion of tasks that overlap with the HELM core scenarios.

Model Details

  • Developed by: Together Computer.
  • Model type: Language Model
  • Language(s): English
  • License: Apache 2.0
  • Model Description: A 2.8B parameter pretrained language model.

Quick Start

Please note that the model requires transformers version >= 4.25.1.

GPU Inference

This requires a GPU with 8GB memory.

import torch
import transformers
from transformers import AutoTokenizer, AutoModelForCausalLM

MIN_TRANSFORMERS_VERSION = '4.25.1'

# check transformers version
assert transformers.__version__ >= MIN_TRANSFORMERS_VERSION, f'Please upgrade transformers to version {MIN_TRANSFORMERS_VERSION} or higher.'

# init
tokenizer = AutoTokenizer.from_pretrained("togethercomputer/RedPajama-INCITE-Instruct-3B-v1")
model = AutoModelForCausalLM.from_pretrained("togethercomputer/RedPajama-INCITE-Instruct-3B-v1", torch_dtype=torch.float16)
model = model.to('cuda:0')
# infer
prompt = "Q: The capital of France is?\nA:"
inputs = tokenizer(prompt, return_tensors='pt').to(model.device)
input_length = inputs.input_ids.shape[1]
outputs = model.generate(
    **inputs, max_new_tokens=128, do_sample=True, temperature=0.7, top_p=0.7, top_k=50, return_dict_in_generate=True
)
token = outputs.sequences[0, input_length:]
output_str = tokenizer.decode(token)
print(output_str)
"""
Paris
"""

GPU Inference in Int8

This requires a GPU with 6GB memory.

To run inference with int8, please ensure you have installed accelerate and bitandbytes. You can install them with the following command:

pip install accelerate
pip install bitsandbytes

Then you can run inference with int8 as follows:

import torch
import transformers
from transformers import AutoTokenizer, AutoModelForCausalLM

MIN_TRANSFORMERS_VERSION = '4.25.1'

# check transformers version
assert transformers.__version__ >= MIN_TRANSFORMERS_VERSION, f'Please upgrade transformers to version {MIN_TRANSFORMERS_VERSION} or higher.'

# init
tokenizer = AutoTokenizer.from_pretrained("togethercomputer/RedPajama-INCITE-Instruct-3B-v1")
model = AutoModelForCausalLM.from_pretrained("togethercomputer/RedPajama-INCITE-Instruct-3B-v1", device_map='auto', torch_dtype=torch.float16, load_in_8bit=True)

# infer
prompt = "Q: The capital of France is?\nA:"
inputs = tokenizer(prompt, return_tensors='pt').to(model.device)
input_length = inputs.input_ids.shape[1]
outputs = model.generate(
    **inputs, max_new_tokens=128, do_sample=True, temperature=0.7, top_p=0.7, top_k=50, return_dict_in_generate=True
)
token = outputs.sequences[0, input_length:]
output_str = tokenizer.decode(token)
print(output_str)
"""
Paris
"""

CPU Inference 

import torch
import transformers
from transformers import AutoTokenizer, AutoModelForCausalLM

MIN_TRANSFORMERS_VERSION = '4.25.1'

# check transformers version
assert transformers.__version__ >= MIN_TRANSFORMERS_VERSION, f'Please upgrade transformers to version {MIN_TRANSFORMERS_VERSION} or higher.'

# init
tokenizer = AutoTokenizer.from_pretrained("togethercomputer/RedPajama-INCITE-Instruct-3B-v1")
model = AutoModelForCausalLM.from_pretrained("togethercomputer/RedPajama-INCITE-Instruct-3B-v1", torch_dtype=torch.bfloat16)
# infer
prompt = "Q: The capital of France is?\nA:"
inputs = tokenizer(prompt, return_tensors='pt').to(model.device)
input_length = inputs.input_ids.shape[1]
outputs = model.generate(
    **inputs, max_new_tokens=128, do_sample=True, temperature=0.7, top_p=0.7, top_k=50, return_dict_in_generate=True
)
token = outputs.sequences[0, input_length:]
output_str = tokenizer.decode(token)
print(output_str)
"""
Paris
"""

Please note that since LayerNormKernelImpl is not implemented in fp16 for CPU, we use bfloat16 for CPU inference.

Uses

Direct Use

Excluded uses are described below.

Misuse, Malicious Use, and Out-of-Scope Use

It is the responsibility of the end user to ensure that the model is used in a responsible and ethical manner.

Out-of-Scope Use

RedPajama-INCITE-Instruct-3B-v1 is a language model and may not perform well for other use cases outside of its intended scope. For example, it may not be suitable for use in safety-critical applications or for making decisions that have a significant impact on individuals or society. It is important to consider the limitations of the model and to only use it for its intended purpose.

Misuse and Malicious Use

RedPajama-INCITE-Instruct-3B-v1 is designed for language modeling. Misuse of the model, such as using it to engage in illegal or unethical activities, is strictly prohibited and goes against the principles of the project.

Using the model to generate content that is cruel to individuals is a misuse of this model. This includes, but is not limited to:

  • Generating fake news, misinformation, or propaganda
  • Promoting hate speech, discrimination, or violence against individuals or groups
  • Impersonating individuals or organizations without their consent
  • Engaging in cyberbullying or harassment
  • Defamatory content
  • Spamming or scamming
  • Sharing confidential or sensitive information without proper authorization
  • Violating the terms of use of the model or the data used to train it
  • Creating automated bots for malicious purposes such as spreading malware, phishing scams, or spamming

Limitations

RedPajama-INCITE-Instruct-3B-v1, like other language models, has limitations that should be taken into consideration. For example, the model may not always provide accurate or relevant answers, particularly for questions that are complex, ambiguous, or outside of its training data. We therefore welcome contributions from individuals and organizations, and encourage collaboration towards creating a more robust and inclusive chatbot.

Training

Training Data

Please refer to togethercomputer/RedPajama-Data-1T

Training Procedure

  • Hardware: 8 A100
  • Optimizer: Adam
  • Gradient Accumulations: 1
  • Num of Tokens: 131M tokens
  • Learning rate: 1e-5

Community

Join us on Together Discord

Downloads last month
6
Unable to determine this model’s pipeline type. Check the docs .

Datasets used to train michaelfeil/ct2fast-RedPajama-INCITE-Instruct-3B-v1