| { |
| "_name_or_path": "merged_model", |
| "architectures": [ |
| "PhiForCausalLM" |
| ], |
| "attention_dropout": 0.0, |
| "auto_map": { |
| "AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig", |
| "AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM" |
| }, |
| "bos_token_id": null, |
| "embd_pdrop": 0.0, |
| "eos_token_id": null, |
| "hidden_act": "gelu_new", |
| "hidden_size": 2560, |
| "initializer_range": 0.02, |
| "intermediate_size": 10240, |
| "layer_norm_eps": 1e-05, |
| "max_position_embeddings": 2048, |
| "model_type": "phi", |
| "num_attention_heads": 32, |
| "num_hidden_layers": 32, |
| "num_key_value_heads": 32, |
| "partial_rotary_factor": 0.4, |
| "qk_layernorm": false, |
| "quantization_config": { |
| "batch_size": 1, |
| "bits": 4, |
| "block_name_to_quantize": null, |
| "cache_block_outputs": true, |
| "damp_percent": 0.1, |
| "dataset": [ |
| "c4" |
| ], |
| "desc_act": false, |
| "exllama_config": { |
| "version": 1 |
| }, |
| "group_size": 128, |
| "max_input_length": null, |
| "model_seqlen": null, |
| "module_name_preceding_first_block": null, |
| "pad_token_id": null, |
| "quant_method": "gptq", |
| "sym": true, |
| "tokenizer": null, |
| "true_sequential": true, |
| "use_cuda_fp16": false, |
| "use_exllama": true |
| }, |
| "resid_pdrop": 0.1, |
| "rope_scaling": null, |
| "rope_theta": 10000.0, |
| "tie_word_embeddings": false, |
| "torch_dtype": "float16", |
| "transformers_version": "4.36.2", |
| "use_cache": true, |
| "vocab_size": 51200 |
| } |
|
|
