| { | |
| "base_model_name_or_path": "tiiuae/falcon-7b-instruct", | |
| "peft_model_id": "steveglover/falcon-7b-instruct-telco-texttonest", | |
| "_name_or_path": "falcon-7b-instruct-telco-texttonest", | |
| "architectures": [ | |
| "RWForCausalLM" | |
| ], | |
| "bias": false, | |
| "bos_token_id": 11, | |
| "eos_token_id": 11, | |
| "hidden_dropout": 0.0, | |
| "hidden_size": 4544, | |
| "initializer_range": 0.02, | |
| "layer_norm_epsilon": 1e-05, | |
| "model_type": "RefinedWebModel", | |
| "multi_query": true, | |
| "n_head": 71, | |
| "n_layer": 32, | |
| "parallel_attn": true, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.27.4", | |
| "use_cache": true, | |
| "vocab_size": 65024, | |
| "tokenizer_class": "GPT2Tokenizer", | |
| "attention_probs_dropout_prob": 0.0, | |
| "attn_pdrop": 0.0, | |
| "embd_pdrop": 0.0, | |
| "pad_token_id": 1023, | |
| "fan_in_fan_out": false, | |
| "inference_mode": true, | |
| "init_lora_weights": true, | |
| "lora_alpha": 32, | |
| "lora_dropout": 0.05, | |
| "modules_to_save": null, | |
| "peft_type": "LORA", | |
| "r": 16, | |
| "target_modules": [ | |
| "q_proj", | |
| "v_proj" | |
| ], | |
| "task_type": "CAUSAL_LM" | |
| } |