From 45113ebf4ef2ad3714c1a9b51d9cca79bcafb921 Mon Sep 17 00:00:00 2001
From: Daniel King <43149077+dakinggg@users.noreply.github.com>
Date: Tue, 14 Nov 2023 10:48:56 -0800
Subject: [PATCH] remove tokenizer_name field (#735)

---
 scripts/inference/benchmarking/yamls/1b.yaml        | 1 -
 scripts/inference/benchmarking/yamls/7b.yaml        | 1 -
 scripts/train/yamls/pretrain/gpt-neo-125m.yaml      | 2 --
 scripts/train/yamls/pretrain/gpt-neo-125m_eval.yaml | 2 --
 scripts/train/yamls/pretrain/gpt2-small.yaml        | 2 --
 scripts/train/yamls/pretrain/opt-3b.yaml            | 2 --
 6 files changed, 10 deletions(-)

diff --git a/scripts/inference/benchmarking/yamls/1b.yaml b/scripts/inference/benchmarking/yamls/1b.yaml
index f94aa3d806..d1cfb3c913 100644
--- a/scripts/inference/benchmarking/yamls/1b.yaml
+++ b/scripts/inference/benchmarking/yamls/1b.yaml
@@ -12,7 +12,6 @@ tokenizer:
 model:
   name: mpt_causal_lm
   init_device: cpu
-  tokenizer_name: ${tokenizer_name}
   d_model: 2048
   n_heads: 16 # Modified 24->16 so that d_head == 128 to statisfy FlashAttention
   n_layers: 24
diff --git a/scripts/inference/benchmarking/yamls/7b.yaml b/scripts/inference/benchmarking/yamls/7b.yaml
index 55e9ae8413..f57ed2657f 100644
--- a/scripts/inference/benchmarking/yamls/7b.yaml
+++ b/scripts/inference/benchmarking/yamls/7b.yaml
@@ -12,7 +12,6 @@ tokenizer:
 model:
   name: mpt_causal_lm
   init_device: cpu
-  tokenizer_name: ${tokenizer_name}
   d_model: 4096
   n_heads: 32
   n_layers: 32
diff --git a/scripts/train/yamls/pretrain/gpt-neo-125m.yaml b/scripts/train/yamls/pretrain/gpt-neo-125m.yaml
index cfb447e2e4..12914e14bc 100644
--- a/scripts/train/yamls/pretrain/gpt-neo-125m.yaml
+++ b/scripts/train/yamls/pretrain/gpt-neo-125m.yaml
@@ -34,7 +34,6 @@ train_loader:
     remote: ${data_remote}
     split: train
     shuffle: true
-    tokenizer_name: ${tokenizer_name}
     max_seq_len: ${max_seq_len}
     shuffle_seed: ${global_seed}
   drop_last: true
@@ -47,7 +46,6 @@ eval_loader:
     remote: ${data_remote}
     split: val
     shuffle: false
-    tokenizer_name: ${tokenizer_name}
     max_seq_len: ${max_seq_len}
     shuffle_seed: ${global_seed}
   drop_last: false
diff --git a/scripts/train/yamls/pretrain/gpt-neo-125m_eval.yaml b/scripts/train/yamls/pretrain/gpt-neo-125m_eval.yaml
index fc1e3b0b7f..3da239c717 100644
--- a/scripts/train/yamls/pretrain/gpt-neo-125m_eval.yaml
+++ b/scripts/train/yamls/pretrain/gpt-neo-125m_eval.yaml
@@ -34,7 +34,6 @@ train_loader:
     remote: ${data_remote}
     split: train
     shuffle: true
-    tokenizer_name: ${tokenizer_name}
     max_seq_len: ${max_seq_len}
     shuffle_seed: ${global_seed}
   drop_last: true
@@ -47,7 +46,6 @@ eval_loader:
     remote: ${data_remote}
     split: val
     shuffle: false
-    tokenizer_name: ${tokenizer_name}
     max_seq_len: ${max_seq_len}
     shuffle_seed: ${global_seed}
   drop_last: false
diff --git a/scripts/train/yamls/pretrain/gpt2-small.yaml b/scripts/train/yamls/pretrain/gpt2-small.yaml
index dde59d55b1..d40cff6e9e 100644
--- a/scripts/train/yamls/pretrain/gpt2-small.yaml
+++ b/scripts/train/yamls/pretrain/gpt2-small.yaml
@@ -34,7 +34,6 @@ train_loader:
     remote: ${data_remote}
     split: train
     shuffle: true
-    tokenizer_name: ${tokenizer_name}
     max_seq_len: ${max_seq_len}
     shuffle_seed: ${global_seed}
   drop_last: true
@@ -47,7 +46,6 @@ eval_loader:
     remote: ${data_remote}
     split: val
     shuffle: false
-    tokenizer_name: ${tokenizer_name}
     max_seq_len: ${max_seq_len}
     shuffle_seed: ${global_seed}
   drop_last: false
diff --git a/scripts/train/yamls/pretrain/opt-3b.yaml b/scripts/train/yamls/pretrain/opt-3b.yaml
index 3ac281f0ea..4423784b54 100644
--- a/scripts/train/yamls/pretrain/opt-3b.yaml
+++ b/scripts/train/yamls/pretrain/opt-3b.yaml
@@ -27,7 +27,6 @@ train_loader:
     remote: ${data_remote}
     split: train
     shuffle: true
-    tokenizer_name: ${tokenizer_name}
     max_seq_len: ${max_seq_len}
     shuffle_seed: ${global_seed}
   drop_last: true
@@ -40,7 +39,6 @@ eval_loader:
     remote: ${data_remote}
     split: val
     shuffle: false
-    tokenizer_name: ${tokenizer_name}
     max_seq_len: ${max_seq_len}
     shuffle_seed: ${global_seed}
   drop_last: false