| Small dummy LLama2-type Model useable for Unit/Integration tests. | |
| ```python | |
| from transformers import AutoConfig, AutoTokenizer, AutoModelForCausalLM | |
| repo_name = "MaxJeblick/llama2-0b-unit-test" | |
| model_name = "h2oai/h2ogpt-4096-llama2-7b-chat" | |
| config = AutoConfig.from_pretrained(model_name) | |
| config.hidden_size = 12 | |
| config.max_position_embeddings = 32 | |
| config.intermediate_size = 24 | |
| config.num_attention_heads = 2 | |
| config.num_hidden_layers = 2 | |
| config.num_key_value_heads = 2 | |
| tokenizer = AutoTokenizer.from_pretrained(model_name) | |
| model = AutoModelForCausalLM.from_config(config) | |
| print(model.num_parameters()) # 770_940 | |
| model.push_to_hub(repo_name, private=False) | |
| tokenizer.push_to_hub(repo_name, private=False) | |
| config.push_to_hub(repo_name, private=False) | |
| ``` |