初始化项目，由ModelHub XC社区提供模型
Model: lomahony/pythia-70m-helpful-sft Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
82
README.md
Normal file
82
README.md
Normal file
@@ -0,0 +1,82 @@
|
||||
---
|
||||
language:
|
||||
- en
|
||||
tags:
|
||||
- pytorch
|
||||
- causal-lm
|
||||
- pythia
|
||||
license: apache-2.0
|
||||
datasets:
|
||||
- Anthropic/hh-rlhf
|
||||
---
|
||||
|
||||
[Pythia-70m](https://huggingface.co/EleutherAI/pythia-70m) supervised finetuned using TRLx library with the helpful subset of [Anthropic-hh-rlhf dataset](https://huggingface.co/datasets/Anthropic/hh-rlhf) for 1 epoch.
|
||||
|
||||
Checkpoints are also uploaded.
|
||||
|
||||
Fully reproducible finetuning code is available on [GitHub](https://github.com/lauraaisling/trlx-pythia/tree/main)
|
||||
|
||||
[wandb log](https://wandb.ai/lauraomahony999/pythia-sft/runs/3w7e3zmd)
|
||||
|
||||
See [Pythia-70m](https://huggingface.co/EleutherAI/pythia-70m) for model details [(paper)](https://arxiv.org/abs/2101.00027).
|
||||
|
||||
See further details of these models in the paper [Attributing Mode Collapse in the Fine-Tuning of Large Language Models](https://openreview.net/pdf?id=3pDMYjpOxk).
|
||||
|
||||
You can cite these models if they are helpful as follows:
|
||||
|
||||
<pre>
|
||||
@inproceedings{o2024attributing,
|
||||
title={Attributing Mode Collapse in the Fine-Tuning of Large Language Models},
|
||||
author={O’Mahony, Laura and Grinsztajn, Leo and Schoelkopf, Hailey and Biderman, Stella},
|
||||
booktitle={ICLR 2024, Mathematical and Empirical Understanding of Foundation Models (ME-FoMo) workshop},
|
||||
year={2024}
|
||||
}
|
||||
</pre>
|
||||
|
||||
hf (pretrained=lomahony/pythia-70m-helpful-sft), gen_kwargs: (None), limit: None, num_fewshot: 0, batch_size: 16
|
||||
| Tasks |Version|Filter|n-shot| Metric | Value | | Stderr |
|
||||
|--------------|------:|------|-----:|---------------|--------:|---|--------|
|
||||
|arc_challenge | 1|none | 0|acc | 0.1715|± | 0.0110|
|
||||
| | |none | 0|acc_norm | 0.2082|± | 0.0119|
|
||||
|arc_easy | 1|none | 0|acc | 0.3384|± | 0.0097|
|
||||
| | |none | 0|acc_norm | 0.3262|± | 0.0096|
|
||||
|boolq | 2|none | 0|acc | 0.4239|± | 0.0086|
|
||||
|hellaswag | 1|none | 0|acc | 0.2629|± | 0.0044|
|
||||
| | |none | 0|acc_norm | 0.2691|± | 0.0044|
|
||||
|lambada_openai| 1|none | 0|perplexity |5937.7964|± |424.7555|
|
||||
| | |none | 0|acc | 0.0328|± | 0.0025|
|
||||
|openbookqa | 1|none | 0|acc | 0.1580|± | 0.0163|
|
||||
| | |none | 0|acc_norm | 0.2520|± | 0.0194|
|
||||
|piqa | 1|none | 0|acc | 0.5593|± | 0.0116|
|
||||
| | |none | 0|acc_norm | 0.5392|± | 0.0116|
|
||||
|sciq | 1|none | 0|acc | 0.3710|± | 0.0153|
|
||||
| | |none | 0|acc_norm | 0.4990|± | 0.0158|
|
||||
|wikitext | 2|none | 0|word_perplexity| 550.5954|± |N/A |
|
||||
| | |none | 0|byte_perplexity| 3.2550|± |N/A |
|
||||
| | |none | 0|bits_per_byte | 1.7027|± |N/A |
|
||||
|winogrande | 1|none | 0|acc | 0.4878|± | 0.0140|
|
||||
|
||||
hf (pretrained=lomahony/pythia-70m-helpful-sft), gen_kwargs: (None), limit: None, num_fewshot: 5, batch_size: 16
|
||||
| Tasks |Version|Filter|n-shot| Metric | Value | | Stderr |
|
||||
|--------------|------:|------|-----:|---------------|---------:|---|---------|
|
||||
|arc_challenge | 1|none | 5|acc | 0.1869|± | 0.0114|
|
||||
| | |none | 5|acc_norm | 0.2210|± | 0.0121|
|
||||
|arc_easy | 1|none | 5|acc | 0.3207|± | 0.0096|
|
||||
| | |none | 5|acc_norm | 0.3245|± | 0.0096|
|
||||
|boolq | 2|none | 5|acc | 0.4159|± | 0.0086|
|
||||
|hellaswag | 1|none | 5|acc | 0.2633|± | 0.0044|
|
||||
| | |none | 5|acc_norm | 0.2596|± | 0.0044|
|
||||
|lambada_openai| 1|none | 5|perplexity |19968.0749|± |1423.3001|
|
||||
| | |none | 5|acc | 0.0202|± | 0.0020|
|
||||
|openbookqa | 1|none | 5|acc | 0.1440|± | 0.0157|
|
||||
| | |none | 5|acc_norm | 0.2420|± | 0.0192|
|
||||
|piqa | 1|none | 5|acc | 0.5359|± | 0.0116|
|
||||
| | |none | 5|acc_norm | 0.5229|± | 0.0117|
|
||||
|sciq | 1|none | 5|acc | 0.3240|± | 0.0148|
|
||||
| | |none | 5|acc_norm | 0.4310|± | 0.0157|
|
||||
|wikitext | 2|none | 5|word_perplexity| 550.5954|± |N/A |
|
||||
| | |none | 5|byte_perplexity| 3.2550|± |N/A |
|
||||
| | |none | 5|bits_per_byte | 1.7027|± |N/A |
|
||||
|winogrande | 1|none | 5|acc | 0.5154|± | 0.0140|
|
||||
|
||||
|
||||
29
config.json
Normal file
29
config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"_name_or_path": "EleutherAI/pythia-70m",
|
||||
"architectures": [
|
||||
"GPTNeoXForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 0,
|
||||
"classifier_dropout": 0.1,
|
||||
"eos_token_id": 0,
|
||||
"hidden_act": "gelu",
|
||||
"hidden_dropout": 0.0,
|
||||
"hidden_size": 512,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 2048,
|
||||
"layer_norm_eps": 1e-05,
|
||||
"max_position_embeddings": 2048,
|
||||
"model_type": "gpt_neox",
|
||||
"num_attention_heads": 8,
|
||||
"num_hidden_layers": 6,
|
||||
"rope_scaling": null,
|
||||
"rotary_emb_base": 10000,
|
||||
"rotary_pct": 0.25,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.34.1",
|
||||
"use_cache": true,
|
||||
"use_parallel_residual": true,
|
||||
"vocab_size": 50304
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 0,
|
||||
"eos_token_id": 0,
|
||||
"transformers_version": "4.34.1"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f1dd1955b390f7913ffd6da8ef3064c84cbcaeae84566994897ac3fc29377319
|
||||
size 140862792
|
||||
3
pytorch_model.bin
Normal file
3
pytorch_model.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2af77a9179e3857ccda535f1204f50fbc3bd1e583d1716df34aa7b6ce716b7c3
|
||||
size 140879908
|
||||
7
special_tokens_map.json
Normal file
7
special_tokens_map.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"bos_token": "<|endoftext|>",
|
||||
"eos_token": "<|endoftext|>",
|
||||
"pad_token": "<|padding|>",
|
||||
"sep_token": "<sep>",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
100534
tokenizer.json
Normal file
100534
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
213
tokenizer_config.json
Normal file
213
tokenizer_config.json
Normal file
@@ -0,0 +1,213 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<|padding|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"50254": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50255": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50256": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50257": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50258": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50259": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50260": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50261": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50262": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50263": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50264": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50265": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50266": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50267": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50268": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50269": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50270": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50271": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50272": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50273": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50274": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50275": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50276": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"bos_token": "<|endoftext|>",
|
||||
"clean_up_tokenization_spaces": true,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": "<|padding|>",
|
||||
"sep_token": "<sep>",
|
||||
"tokenizer_class": "GPTNeoXTokenizer",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
Reference in New Issue
Block a user