Instructions to use shibatch/tinyllama4gpt2m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use shibatch/tinyllama4gpt2m with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("shibatch/tinyllama4gpt2m", dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "MixtralForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "dtype": "float32", | |
| "eos_token_id": 2, | |
| "head_dim": null, | |
| "hidden_act": "silu", | |
| "hidden_size": 96, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 192, | |
| "max_position_embeddings": 1024, | |
| "model_type": "mixtral", | |
| "num_attention_heads": 4, | |
| "num_experts_per_tok": 3, | |
| "num_hidden_layers": 2, | |
| "num_key_value_heads": 2, | |
| "num_local_experts": 5, | |
| "output_router_logits": false, | |
| "pad_token_id": 2, | |
| "rms_norm_eps": 1e-05, | |
| "rope_parameters": { | |
| "factor": 4.0, | |
| "high_freq_factor": 4.0, | |
| "low_freq_factor": 1.0, | |
| "original_max_position_embeddings": 256, | |
| "rope_theta": 1000000.0, | |
| "rope_type": "llama3", | |
| "type": "llama3" | |
| }, | |
| "router_aux_loss_coef": 0.001, | |
| "router_jitter_noise": 0.0, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.9.0", | |
| "use_cache": false, | |
| "vocab_size": 4000 | |
| } | |