ahmedzk11/tiny-random-minicpm-o-2_6

Tiny Random MiniCPM-o-2.6

Tiny random initialization of MiniCPM-o-2.6 for Optimum-Intel validation testing.

Model Details

• Architecture: MiniCPM-o-2.6
• Size: 37.70MB
• Purpose: Testing and validation only (not trained)
• Created for: Optimum-Intel integration tests

Configuration

hidden_size: 128
num_hidden_layers: 2
num_attention_heads: 2
intermediate_size: 256
vocab_size: 1000
max_position_embeddings: 512
torch_dtype: bfloat16

Usage

from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained(
    "ahmedzk11/tiny-random-minicpm-o-2_6",
    trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained(
    "ahmedzk11/tiny-random-minicpm-o-2_6",
    trust_remote_code=True
)

Testing

This model is used in Optimum-Intel validation tests for MiniCPM-o-2.6 architecture.

Note: This model has random weights and is NOT suitable for actual inference tasks.