GPT2-EXperiment-2

Kukedlc/GPT2-EXperiment-2

GPT2-EXperiment-2 is a machine learning model from Kukedlc. Use it for the machine learning task on the model card, and read the license before you ship it in a product.

GPT2-EXperiment-2 is a merge of the following models using LazyMergekit: openai-community/gpt2 openai-community/gpt2 openai-community/gpt2

Downloads · 30 days

22% of all-time downloads

All-time downloads

Public

Parameters

1.2B

2.3 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors2.3 GB · 100%

At a glance

Model type: gpt2
Access: Public
Created: Sep 4, 2024
Updated: Sep 4, 2024
SHA: c9cbd0c1

Base models

openai-community/gpt2

Model card

From the Hugging Face model README

GPT2-EXperiment-2

GPT2-EXperiment-2 is a merge of the following models using LazyMergekit:

🧩 Configuration

slices:
- sources:
  - layer_range: [0, 3]
    model: openai-community/gpt2
- sources:
  - layer_range: [0, 11]
    model: openai-community/gpt2
- sources:
  - layer_range: [0, 11]
    model: openai-community/gpt2
- sources:
  - layer_range: [0, 11]
    model: openai-community/gpt2
- sources:
  - layer_range: [0, 11]
    model: openai-community/gpt2
- sources:
  - layer_range: [0, 11]
    model: openai-community/gpt2
- sources:
  - layer_range: [0, 11]
    model: openai-community/gpt2
- sources:
  - layer_range: [0, 11]
    model: openai-community/gpt2
- sources:
  - layer_range: [0, 11]
    model: openai-community/gpt2
- sources:
  - layer_range: [0, 11]
    model: openai-community/gpt2
- sources:
  - layer_range: [0, 11]
    model: openai-community/gpt2
- sources:
  - layer_range: [0, 11]
    model: openai-community/gpt2
- sources:
  - layer_range: [0, 11]
    model: openai-community/gpt2
- sources:
  - layer_range: [0, 11]
    model: openai-community/gpt2
- sources:
  - layer_range: [0, 11]
    model: openai-community/gpt2
- sources:
  - layer_range: [8, 11]
    model: openai-community/gpt2
merge_method: passthrough
dtype: float16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Kukedlc/GPT2-EXperiment-2"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

Type: gpt2
Created: Sep 4, 2024
Updated: Sep 4, 2024