| { |
| "architectures": [ |
| "LlamaForSequenceClassification" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 1, |
| "eos_token_id": 2, |
| "head_dim": 64, |
| "hidden_act": "silu", |
| "hidden_size": 2048, |
| "id2label": { |
| "0": "negative", |
| "1": "neutral", |
| "2": "positive" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 8192, |
| "label2id": { |
| "negative": 0, |
| "neutral": 1, |
| "positive": 2 |
| }, |
| "max_position_embeddings": 8192, |
| "mlp_bias": false, |
| "model_type": "llama", |
| "num_attention_heads": 32, |
| "num_hidden_layers": 24, |
| "num_key_value_heads": 32, |
| "pad_token_id": 2, |
| "pretraining_tp": 1, |
| "problem_type": "single_label_classification", |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 130000, |
| "tie_word_embeddings": true, |
| "torch_dtype": "bfloat16", |
| "transformers.js_config": { |
| "dtype": "q4", |
| "kv_cache_dtype": { |
| "fp16": "float16", |
| "q4f16": "float16" |
| }, |
| "use_external_data_format": { |
| "model.onnx": true, |
| "model_fp16.onnx": true |
| } |
| }, |
| "transformers_version": "4.51.3", |
| "use_cache": false, |
| "vocab_size": 49152 |
| } |
|
|
