| { | |
| "_name_or_path": "aisquared/dlite-v2-355m", | |
| "activation_function": "gelu_new", | |
| "architectures": [ | |
| "GPT2LMHeadModel" | |
| ], | |
| "attn_pdrop": 0.1, | |
| "bos_token_id": 50256, | |
| "custom_pipelines": { | |
| "text-generation": { | |
| "impl": "instruct_pipeline.InstructionTextGenerationPipeline", | |
| "pt": "AutoModelForCausalLM", | |
| "tf": "TFAutoModelForCausalLM" | |
| } | |
| }, | |
| "embd_pdrop": 0.1, | |
| "eos_token_id": 50256, | |
| "initializer_range": 0.02, | |
| "layer_norm_epsilon": 1e-05, | |
| "model_type": "gpt2", | |
| "n_ctx": 1024, | |
| "n_embd": 1024, | |
| "n_head": 16, | |
| "n_inner": null, | |
| "n_layer": 24, | |
| "n_positions": 1024, | |
| "n_special": 0, | |
| "predict_special_tokens": true, | |
| "quantization_config": { | |
| "batch_size": 1, | |
| "bits": 4, | |
| "block_name_to_quantize": "transformer.h", | |
| "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": 1024, | |
| "module_name_preceding_first_block": [ | |
| "transformer.wte", | |
| "transformer.wpe", | |
| "transformer.drop" | |
| ], | |
| "pad_token_id": null, | |
| "quant_method": "gptq", | |
| "sym": true, | |
| "tokenizer": null, | |
| "true_sequential": true, | |
| "use_cuda_fp16": true, | |
| "use_exllama": true | |
| }, | |
| "reorder_and_upcast_attn": false, | |
| "resid_pdrop": 0.1, | |
| "scale_attn_by_inverse_layer_idx": false, | |
| "scale_attn_weights": true, | |
| "summary_activation": null, | |
| "summary_first_dropout": 0.1, | |
| "summary_proj_to_labels": true, | |
| "summary_type": "cls_index", | |
| "summary_use_proj": true, | |
| "task_specific_params": { | |
| "text-generation": { | |
| "do_sample": true, | |
| "max_length": 50 | |
| } | |
| }, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.35.2", | |
| "use_cache": false, | |
| "vocab_size": 50260 | |
| } | |