初始化项目，由ModelHub XC社区提供模型
Model: digitous/GPT-R Source: Original Platform
This commit is contained in:
ModelHub XC
34
.gitattributes
vendored
Normal file
34
.gitattributes
vendored
Normal file
@@ -0,0 +1,34 @@
|
||||
*.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
|
||||
*.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
|
||||
80
README.md
Normal file
80
README.md
Normal file
@@ -0,0 +1,80 @@
|
||||
---
|
||||
license: bigscience-openrail-m
|
||||
language:
|
||||
- en
|
||||
---
|
||||
GPT-R [Ronin]
|
||||
|
||||
GPT-R is an experimental model containing a parameter-wise 60/40 blend (weighted average) of the weights of ppo_hh_gpt-j and GPT-JT-6B-v1.
|
||||
|
||||
-Intended Merge Value-
|
||||
|
||||
As with fine-tuning, merging weights does not add information but transforms it, therefore it is important to consider trade-offs.
|
||||
GPT-Ronin combines ppo_hh_gpt-j and GPT-JT; both technical
|
||||
achievements are blended with the intent to elevate the strengths of
|
||||
both. Datasets of both are linked below to assist in exploratory speculation on which datasets in what quantity and configuration have
|
||||
the largest impact on the usefulness of a model without the expense of
|
||||
fine-tuning. Blend was done in FP32 and output in FP16.
|
||||
|
||||
-Intended Use-
|
||||
|
||||
Research purposes only, intended for responsible use.
|
||||
Express a task in natural language, and GPT-R will do the thing.
|
||||
Try telling it "Write an article about X but put Y spin on it.",
|
||||
"Write a five step numbered guide on how to do X.", or any other
|
||||
basic instructions. It does its best.
|
||||
|
||||
Can also be used as a base to merge with conversational,
|
||||
story writing, or adventure themed models of the same class
|
||||
(GPT-J & 6b NeoX) and parameter size (6b) to experiment with
|
||||
the morphology of model weights based on the value added
|
||||
by instruct.
|
||||
|
||||
Merge tested using KoboldAI with Nucleus Sampling Top-P set to 0.7, Temperature at 0.5, and Repetition Penalty at 1.14; extra samplers
|
||||
disabled.
|
||||
|
||||
-Credits To-
|
||||
|
||||
Core Model:
|
||||
https://huggingface.co/EleutherAI/gpt-j-6B
|
||||
Author:
|
||||
https://www.eleuther.ai/
|
||||
|
||||
Model1; 60% ppo_hh_gpt-j:
|
||||
https://huggingface.co/reciprocate/ppo_hh_gpt-j
|
||||
|
||||
Author Repo:
|
||||
https://huggingface.co/reciprocate
|
||||
|
||||
Related; CarperAI:
|
||||
https://huggingface.co/CarperAI
|
||||
|
||||
Dataset is a variant of the Helpful Harmless assistant themed
|
||||
dataset and Proximal Policy Optimization, specific datasets
|
||||
used are unknown; listed repo datasets include:
|
||||
https://huggingface.co/datasets/reciprocate/summarize_eval_ilql
|
||||
https://huggingface.co/datasets/reciprocate/hh_eval_ilql
|
||||
|
||||
PPO explained:
|
||||
https://paperswithcode.com/method/ppo
|
||||
Potential HH-type datasets utilized:
|
||||
https://huggingface.co/HuggingFaceH4
|
||||
https://huggingface.co/datasets/Anthropic/hh-rlhf
|
||||
|
||||
Model2; 40% GPT-JT-6B-V1:
|
||||
https://huggingface.co/togethercomputer/GPT-JT-6B-v1
|
||||
|
||||
Author Repo:
|
||||
https://huggingface.co/togethercomputer
|
||||
|
||||
Related; BigScience:
|
||||
https://huggingface.co/bigscience
|
||||
|
||||
Datasets:
|
||||
https://huggingface.co/datasets/the_pile
|
||||
https://huggingface.co/datasets/bigscience/P3
|
||||
https://github.com/allenai/natural-instructions
|
||||
https://ai.googleblog.com/2022/05/language-models-perform-reasoning-via.html
|
||||
|
||||
Weight merge Script credit to Concedo:
|
||||
https://huggingface.co/concedo
|
||||
43
config.json
Normal file
43
config.json
Normal file
@@ -0,0 +1,43 @@
|
||||
{
|
||||
"_name_or_path": "digitous/GPT-R",
|
||||
"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": true,
|
||||
"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": "4.24.0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 50400,
|
||||
"welcome": "## GPT-R is an experimental merge of reciprocate/ppo_hh_gpt-j and togethercomputer/GPT-JT-6B-v1."
|
||||
}
|
||||
50001
merges.txt
Normal file
50001
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
pytorch_model-00001-of-00006.bin
Normal file
3
pytorch_model-00001-of-00006.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:afcbcdb9e4a5f2a1ae7d92e0efecc0faba2911fb3429a049b499810d08d0f027
|
||||
size 2078278875
|
||||
3
pytorch_model-00002-of-00006.bin
Normal file
3
pytorch_model-00002-of-00006.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2e3f4a63fd723bdf1816f9ff41f5b8dc83fb5d805ce54ab305947efe562cbace
|
||||
size 2068098521
|
||||
3
pytorch_model-00003-of-00006.bin
Normal file
3
pytorch_model-00003-of-00006.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1cf4b1efe0eb8106b4410f75786b57c6f35b4121bf11d73c128371f88dd48060
|
||||
size 2068098585
|
||||
3
pytorch_model-00004-of-00006.bin
Normal file
3
pytorch_model-00004-of-00006.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8bb1b11331e7fbd292ed1a116d79bafe37d98f73fc7fd9ac1083be089bd62649
|
||||
size 2068098585
|
||||
3
pytorch_model-00005-of-00006.bin
Normal file
3
pytorch_model-00005-of-00006.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:78eef26d93857bc8956ece900545197b272e9777c33f98fc8e273e566f64ea40
|
||||
size 2034543815
|
||||
3
pytorch_model-00006-of-00006.bin
Normal file
3
pytorch_model-00006-of-00006.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:28488fb3122922488d2d3c1200f42d81322aa6bb56b1ba971655637fc3f5e6ea
|
||||
size 1902199207
|
||||
348
pytorch_model.bin.index.json
Normal file
348
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,348 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 12219206136
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.bias": "pytorch_model-00006-of-00006.bin",
|
||||
"lm_head.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.0.attn.bias": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.0.attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.0.attn.masked_bias": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.0.attn.out_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.0.attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.0.attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.0.mlp.fc_in.bias": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.0.mlp.fc_in.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.0.mlp.fc_out.bias": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.0.mlp.fc_out.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.1.attn.bias": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.1.attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.1.attn.masked_bias": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.1.attn.out_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.1.attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.1.attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.1.mlp.fc_in.bias": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.1.mlp.fc_in.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.1.mlp.fc_out.bias": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.1.mlp.fc_out.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.10.attn.bias": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.10.attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.10.attn.masked_bias": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.10.attn.out_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.10.attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.10.attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.10.ln_1.bias": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.10.ln_1.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.10.mlp.fc_in.bias": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.10.mlp.fc_in.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.10.mlp.fc_out.bias": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.10.mlp.fc_out.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.11.attn.bias": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.11.attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.11.attn.masked_bias": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.11.attn.out_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.11.attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.11.attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.11.ln_1.bias": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.11.ln_1.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.11.mlp.fc_in.bias": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.11.mlp.fc_in.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.11.mlp.fc_out.bias": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.11.mlp.fc_out.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.12.attn.bias": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.12.attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.12.attn.masked_bias": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.12.attn.out_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.12.attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.12.attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.12.ln_1.bias": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.12.ln_1.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.12.mlp.fc_in.bias": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.12.mlp.fc_in.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.12.mlp.fc_out.bias": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.12.mlp.fc_out.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.13.attn.bias": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.13.attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.13.attn.masked_bias": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.13.attn.out_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.13.attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.13.attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.13.ln_1.bias": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.13.ln_1.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.13.mlp.fc_in.bias": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.13.mlp.fc_in.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.13.mlp.fc_out.bias": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.13.mlp.fc_out.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.14.attn.bias": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.14.attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.14.attn.masked_bias": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.14.attn.out_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.14.attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.14.attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.14.ln_1.bias": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.14.ln_1.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.14.mlp.fc_in.bias": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.14.mlp.fc_in.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.14.mlp.fc_out.bias": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.14.mlp.fc_out.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.15.attn.bias": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.15.attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.15.attn.masked_bias": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.15.attn.out_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.15.attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.15.attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.15.ln_1.bias": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.15.ln_1.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.15.mlp.fc_in.bias": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.15.mlp.fc_in.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.15.mlp.fc_out.bias": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.15.mlp.fc_out.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.16.attn.bias": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.16.attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.16.attn.masked_bias": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.16.attn.out_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.16.attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.16.attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.16.ln_1.bias": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.16.ln_1.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.16.mlp.fc_in.bias": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.16.mlp.fc_in.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.16.mlp.fc_out.bias": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.16.mlp.fc_out.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.17.attn.bias": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.17.attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.17.attn.masked_bias": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.17.attn.out_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.17.attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.17.attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.17.ln_1.bias": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.17.ln_1.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.17.mlp.fc_in.bias": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.17.mlp.fc_in.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.17.mlp.fc_out.bias": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.17.mlp.fc_out.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.18.attn.bias": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.18.attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.18.attn.masked_bias": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.18.attn.out_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.18.attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.18.attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.18.ln_1.bias": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.18.ln_1.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.18.mlp.fc_in.bias": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.18.mlp.fc_in.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.18.mlp.fc_out.bias": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.18.mlp.fc_out.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.19.attn.bias": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.19.attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.19.attn.masked_bias": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.19.attn.out_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.19.attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.19.attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.19.ln_1.bias": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.19.ln_1.weight": "pytorch_model-00004-of-00006.bin",
|
||||
"transformer.h.19.mlp.fc_in.bias": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.19.mlp.fc_in.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.19.mlp.fc_out.bias": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.19.mlp.fc_out.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.2.attn.bias": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.2.attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.2.attn.masked_bias": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.2.attn.out_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.2.attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.2.attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.2.mlp.fc_in.bias": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.2.mlp.fc_in.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.2.mlp.fc_out.bias": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.2.mlp.fc_out.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.20.attn.bias": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.20.attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.20.attn.masked_bias": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.20.attn.out_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.20.attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.20.attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.20.ln_1.bias": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.20.ln_1.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.20.mlp.fc_in.bias": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.20.mlp.fc_in.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.20.mlp.fc_out.bias": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.20.mlp.fc_out.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.21.attn.bias": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.21.attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.21.attn.masked_bias": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.21.attn.out_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.21.attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.21.attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.21.ln_1.bias": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.21.ln_1.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.21.mlp.fc_in.bias": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.21.mlp.fc_in.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.21.mlp.fc_out.bias": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.21.mlp.fc_out.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.22.attn.bias": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.22.attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.22.attn.masked_bias": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.22.attn.out_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.22.attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.22.attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.22.ln_1.bias": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.22.ln_1.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.22.mlp.fc_in.bias": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.22.mlp.fc_in.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.22.mlp.fc_out.bias": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.22.mlp.fc_out.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.23.attn.bias": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.23.attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.23.attn.masked_bias": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.23.attn.out_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.23.attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.23.attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.23.ln_1.bias": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.23.ln_1.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.23.mlp.fc_in.bias": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.23.mlp.fc_in.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.23.mlp.fc_out.bias": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.23.mlp.fc_out.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.24.attn.bias": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.24.attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.24.attn.masked_bias": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.24.attn.out_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.24.attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.24.attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.24.ln_1.bias": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.24.ln_1.weight": "pytorch_model-00005-of-00006.bin",
|
||||
"transformer.h.24.mlp.fc_in.bias": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.24.mlp.fc_in.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.24.mlp.fc_out.bias": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.24.mlp.fc_out.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.25.attn.bias": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.25.attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.25.attn.masked_bias": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.25.attn.out_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.25.attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.25.attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.25.ln_1.bias": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.25.ln_1.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.25.mlp.fc_in.bias": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.25.mlp.fc_in.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.25.mlp.fc_out.bias": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.25.mlp.fc_out.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.26.attn.bias": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.26.attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.26.attn.masked_bias": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.26.attn.out_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.26.attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.26.attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.26.ln_1.bias": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.26.ln_1.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.26.mlp.fc_in.bias": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.26.mlp.fc_in.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.26.mlp.fc_out.bias": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.26.mlp.fc_out.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.27.attn.bias": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.27.attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.27.attn.masked_bias": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.27.attn.out_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.27.attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.27.attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.27.ln_1.bias": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.27.ln_1.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.27.mlp.fc_in.bias": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.27.mlp.fc_in.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.27.mlp.fc_out.bias": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.27.mlp.fc_out.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.h.3.attn.bias": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.3.attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.3.attn.masked_bias": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.3.attn.out_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.3.attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.3.attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.3.ln_1.bias": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.3.mlp.fc_in.bias": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.3.mlp.fc_in.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.3.mlp.fc_out.bias": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.3.mlp.fc_out.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.4.attn.bias": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.4.attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.4.attn.masked_bias": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.4.attn.out_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.4.attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.4.attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.4.ln_1.bias": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00006.bin",
|
||||
"transformer.h.4.mlp.fc_in.bias": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.4.mlp.fc_in.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.4.mlp.fc_out.bias": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.4.mlp.fc_out.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.5.attn.bias": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.5.attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.5.attn.masked_bias": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.5.attn.out_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.5.attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.5.attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.5.ln_1.bias": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.5.ln_1.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.5.mlp.fc_in.bias": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.5.mlp.fc_in.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.5.mlp.fc_out.bias": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.5.mlp.fc_out.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.6.attn.bias": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.6.attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.6.attn.masked_bias": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.6.attn.out_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.6.attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.6.attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.6.ln_1.bias": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.6.ln_1.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.6.mlp.fc_in.bias": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.6.mlp.fc_in.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.6.mlp.fc_out.bias": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.6.mlp.fc_out.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.7.attn.bias": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.7.attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.7.attn.masked_bias": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.7.attn.out_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.7.attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.7.attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.7.ln_1.bias": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.7.ln_1.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.7.mlp.fc_in.bias": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.7.mlp.fc_in.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.7.mlp.fc_out.bias": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.7.mlp.fc_out.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.8.attn.bias": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.8.attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.8.attn.masked_bias": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.8.attn.out_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.8.attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.8.attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.8.ln_1.bias": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.8.ln_1.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.8.mlp.fc_in.bias": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.8.mlp.fc_in.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.8.mlp.fc_out.bias": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.8.mlp.fc_out.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.9.attn.bias": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.9.attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.9.attn.masked_bias": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.9.attn.out_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.9.attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.9.attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.9.ln_1.bias": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.9.ln_1.weight": "pytorch_model-00002-of-00006.bin",
|
||||
"transformer.h.9.mlp.fc_in.bias": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.9.mlp.fc_in.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.9.mlp.fc_out.bias": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.h.9.mlp.fc_out.weight": "pytorch_model-00003-of-00006.bin",
|
||||
"transformer.ln_f.bias": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.ln_f.weight": "pytorch_model-00006-of-00006.bin",
|
||||
"transformer.wte.weight": "pytorch_model-00001-of-00006.bin"
|
||||
}
|
||||
}
|
||||
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": "<|endoftext|>",
|
||||
"sep_token": "<sep>",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
100304
tokenizer.json
Normal file
100304
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
10
tokenizer_config.json
Normal file
10
tokenizer_config.json
Normal file
@@ -0,0 +1,10 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"bos_token": "<|endoftext|>",
|
||||
"eos_token": "<|endoftext|>",
|
||||
"model_max_length": 1024,
|
||||
"name_or_path": "gpt2",
|
||||
"special_tokens_map_file": null,
|
||||
"tokenizer_class": "GPT2Tokenizer",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user