zephyr-7b-gemma-sft-african-ultrachat

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

  • Loss: 1.0802

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

masakhane/african-ultrachat

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 1e-05
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • total_eval_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss
1.1942 1.0 2089 1.1757
0.952 2.0 4178 1.0642
0.7033 3.0 6267 1.0802

Framework versions

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

How to use

import torch
from transformers import pipeline

pipe = pipeline("text-generation", model="masakhane/zephyr-7b-gemma-sft-african-ultrachat", 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 always responds in the style of a pirate",
    },
    {"role": "user", "content": "αˆ°αˆ‹αˆ αŠ₯αŠ•α‹΄α‰΅ αŠαˆ…?"},
]
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|>
# αˆ°αˆ‹αˆ αŠ₯αŠ•α‹΄α‰΅ αŠαˆ…?<eos>
# <|assistant|>
# αˆ°αˆ‹αˆ αŠ₯αŠ•α‹΄α‰΅ αŠαˆ…/ነሽ? αŠ₯αŠ”αˆ α‰ αŒ€αŠ“ ነኝፒ αŠ₯αŠ•α‹°αˆαŠ• αŠαˆ…/ነሽ αŠ₯αŠ“ α‹¨αˆα‰΅αˆαˆαŒˆα‹ αŠ₯αŠ•α‹΄α‰΅ αŠα‹?
Downloads last month
42
Safetensors
Model size
8.54B params
Tensor type
BF16
Β·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for masakhane/zephyr-7b-gemma-sft-african-ultrachat

Base model

google/gemma-7b
Finetuned
(97)
this model

Dataset used to train masakhane/zephyr-7b-gemma-sft-african-ultrachat