|
{ |
|
"_name_or_path": "data/starcoderplus-ift-v4.1", |
|
"activation_function": "gelu", |
|
"architectures": [ |
|
"GPTBigCodeForCausalLM" |
|
], |
|
"attention_softmax_in_fp32": true, |
|
"attn_pdrop": 0.1, |
|
"bos_token_id": 0, |
|
"embd_pdrop": 0.1, |
|
"eos_token_id": 0, |
|
"inference_runner": 0, |
|
"initializer_range": 0.02, |
|
"layer_norm_epsilon": 1e-05, |
|
"max_batch_size": null, |
|
"max_sequence_length": null, |
|
"model_type": "gpt_bigcode", |
|
"multi_query": true, |
|
"n_embd": 6144, |
|
"n_head": 48, |
|
"n_inner": 24576, |
|
"n_layer": 40, |
|
"n_positions": 8192, |
|
"pad_key_length": true, |
|
"pre_allocate_kv_cache": false, |
|
"resid_pdrop": 0.1, |
|
"scale_attention_softmax_in_fp32": true, |
|
"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, |
|
"torch_dtype": "bfloat16", |
|
"transformers_version": "4.28.1", |
|
"use_cache": true, |
|
"validate_runner_input": true, |
|
"vocab_size": 49156, |
|
"quantization_config": { |
|
"bits": 4, |
|
"group_size": -1, |
|
"damp_percent": 0.01, |
|
"desc_act": true, |
|
"sym": true, |
|
"true_sequential": true, |
|
"model_name_or_path": null, |
|
"model_file_base_name": "model", |
|
"quant_method": "gptq" |
|
} |
|
} |