初始化项目,由ModelHub XC社区提供模型
Model: TehVenom/DiffMerge-DollyGPT-Pygmalion Source: Original Platform
This commit is contained in:
42
config.json
Normal file
42
config.json
Normal file
@@ -0,0 +1,42 @@
|
||||
{
|
||||
"_name_or_path": "TehVenom_DiffMerge-DollyGPT-Pygmalion",
|
||||
"activation_function": "gelu_new",
|
||||
"architectures": [
|
||||
"GPTJForCausalLM"
|
||||
],
|
||||
"attn_pdrop": 0.0,
|
||||
"bos_token_id": 50256,
|
||||
"embd_pdrop": 0.0,
|
||||
"eos_token_id": 50256,
|
||||
"gradient_checkpointing": false,
|
||||
"initializer_range": 0.02,
|
||||
"layer_norm_epsilon": 1e-05,
|
||||
"model_type": "gptj",
|
||||
"n_embd": 4096,
|
||||
"n_head": 16,
|
||||
"n_inner": null,
|
||||
"n_layer": 28,
|
||||
"n_positions": 2048,
|
||||
"resid_pdrop": 0.0,
|
||||
"rotary_dim": 64,
|
||||
"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,
|
||||
"temperature": 1.0
|
||||
}
|
||||
},
|
||||
"tie_word_embeddings": false,
|
||||
"tokenizer_class": "GPT2Tokenizer",
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.28.0.dev0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 50400,
|
||||
"welcome": "You are currently running a diff merge of ((GPT-J-Dolly - GPT-J-6b)*0.7 + Pygmalion-6b*0.9), \n"
|
||||
}
|
||||
Reference in New Issue
Block a user