| { |
| "_name_or_path": "baseten/smol_llama-101M-GQA", |
| "architectures": [ |
| "LlamaForSequenceClassification" |
| ], |
| "id2label": { |
| "0": "dummy_0", |
| "1": "dummy_1" |
| }, |
| "label2id": { |
| "dummy_0": 0, |
| "dummy_1": 1 |
| }, |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 1, |
| "eos_token_id": 2, |
| "head_dim": 32, |
| "hidden_act": "silu", |
| "hidden_size": 768, |
| "initializer_range": 0.02, |
| "intermediate_size": 3072, |
| "max_position_embeddings": 1024, |
| "mlp_bias": false, |
| "model_type": "llama", |
| "num_attention_heads": 24, |
| "num_hidden_layers": 6, |
| "num_key_value_heads": 8, |
| "pretraining_tp": 1, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 10000.0, |
| "tie_word_embeddings": false, |
| "torch_dtype": "float32", |
| "transformers_version": "4.45.1", |
| "use_cache": true, |
| "vocab_size": 32128 |
| } |
|
|
