[feature] ColossalEval: Evaluation Pipeline for LLMs (#4786)

* Add ColossalEval

* Delete evaluate in Chat

---------

Co-authored-by: Xu Yuanchen <yuanchen.xu00@gmail.com>
Co-authored-by: Tong Li <tong.li352711588@gmail.com>
This commit is contained in:
Yuanchen
2023-09-24 23:14:11 +08:00
committed by GitHub
parent 74aa7d964a
commit ce777853ae
60 changed files with 5314 additions and 2497 deletions

View File

@@ -0,0 +1,44 @@
{
"language": "en",
"category": {
"brainstorming": {
"GPT": [
"language organization",
"relevance",
"creativity",
"practicality",
"reasonableness"
]
},
"chat": {
"GPT": [
"language organization",
"naturalness",
"engagingness",
"fidelity"
]
},
"generation": {
"GPT": [
"language organization",
"relevance",
"diversity"
]
},
"open_qa": {
"GPT": [
"language organization",
"relevance",
"correctness"
]
},
"roleplay": {
"GPT": [
"language organization",
"relevance",
"fidelity",
"creativity"
]
}
}
}

View File

@@ -0,0 +1,33 @@
{
"model": [
{
"name": "model name",
"model_class": "HuggingFaceCausalLM",
"parameters": {
"path": "path to model",
"model_max_length": 4096,
"tokenizer_path": "",
"tokenizer_kwargs": {
"trust_remote_code": true
},
"peft_path": null,
"model_kwargs": {
"torch_dtype": "torch.float32",
"trust_remote_code": true
},
"prompt_template": "plain",
"batch_size": 4
}
}
],
"dataset": [
{
"name": "colossal",
"dataset_class": "ColossalDataset",
"debug": false,
"few_shot": false,
"path": "../../configs/gpt_evaluation/data/eval_en_examples.json",
"save_path": "path to save converted dataset (inference_data/colossal.json)"
}
]
}