CoolFace
Modelpublic

masakhane/zephyr-7b-gemma-sft-african-alpaca

sourceHugging Facegemmaupdated 2y agoView on Hugging Face
1likes34downloads
Model Card

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

zephyr-7b-gemma-sft-alpaca

This model is a fine-tuned version of google/gemma-7b on the masakhane/african-translated-alpaca dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.2737

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • —learning_rate: 1e-05
  • —trainbatchsize: 1
  • —evalbatchsize: 1
  • —seed: 42
  • —distributed_type: multi-GPU
  • —num_devices: 8
  • —gradientaccumulationsteps: 2
  • —totaltrainbatch_size: 16
  • —totalevalbatch_size: 8
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: cosine
  • —lrschedulerwarmup_ratio: 0.1
  • —num_epochs: 3

Training results

Training LossEpochStepValidation Loss
0.86711.058820.7445
0.52352.0117640.3905
0.33093.0176460.2737

Framework versions

  • —Transformers 4.39.0.dev0
  • —Pytorch 2.2.1+cu121
  • —Datasets 2.14.6
  • —Tokenizers 0.15.2

Usage

python

# Install transformers from source - only needed for versions <= v4.34
# pip install git+https://github.com/huggingface/transformers.git
# pip install accelerate

import torch
from transformers import pipeline

pipe = pipeline("text-generation", model="masakhane/zephyr-7b-gemma-sft-african-alpaca", torch_dtype=torch.bfloat16, device_map="auto")

# We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
messages = [
    {
        "role": "system",
        "content": "You are a friendly chatbot who answewrs question in given language",
    },
    {"role": "user", "content": "what is the 3 biggest countrys in Africa?"},
]
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
# <|system|>
# You are a friendly chatbot who always responds in the style of a pirate<eos>
# <|user|>
# what is the 3 biggest countrys in Africa?<eos>
# <|assistant|>
# The 3 biggest countries in Africa are Nigeria, Ethiopia and South Africa.

Quantized Versions through bitsandbytes

python

import torch
from transformers import pipeline
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig


quantization_config = BitsAndBytesConfig(load_in_4bit=True)

tokenizer = AutoTokenizer.from_pretrained("masakhane/zephyr-7b-gemma-sft-african-alpaca")
model = AutoModelForCausalLM.from_pretrained("masakhane/zephyr-7b-gemma-sft-african-alpaca", quantization_config=quantization_config)


pipe = pipeline("text-generation", model=model,tokenizer=tokenizer, torch_dtype=torch.bfloat16, device_map="auto")

messages = [
    {
        "role": "system",
        "content": "You are a friendly chatbot who answewrs question in given language",
    },
    {"role": "user", "content": "list languages in Africa?"},
]
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])