| { |
| "_name_or_path": "TheTravellingEngineer/llama2-7b-hf-guanaco", |
| "architectures": [ |
| "LlamaForSequenceClassification" |
| ], |
| "attention_bias": false, |
| "bos_token_id": 1, |
| "eos_token_id": 2, |
| "hidden_act": "silu", |
| "hidden_size": 4096, |
| "id2label": { |
| "0": "LABEL_0" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 11008, |
| "label2id": { |
| "LABEL_0": 0 |
| }, |
| "max_position_embeddings": 4096, |
| "model_type": "llama", |
| "num_attention_heads": 32, |
| "num_hidden_layers": 32, |
| "num_key_value_heads": 32, |
| "pad_token_id": 0, |
| "pretraining_tp": 1, |
| "problem_type": "regression", |
| "quantization_config": { |
| "bnb_4bit_compute_dtype": "float32", |
| "bnb_4bit_quant_type": "fp4", |
| "bnb_4bit_use_double_quant": false, |
| "llm_int8_enable_fp32_cpu_offload": false, |
| "llm_int8_has_fp16_weight": false, |
| "llm_int8_skip_modules": null, |
| "llm_int8_threshold": 6.0, |
| "load_in_4bit": false, |
| "load_in_8bit": true, |
| "quant_method": "bitsandbytes" |
| }, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 10000.0, |
| "tie_word_embeddings": false, |
| "torch_dtype": "float16", |
| "transformers_version": "4.35.0", |
| "use_cache": true, |
| "vocab_size": 32000 |
| } |
|
|
