remove tokenizer_name field (#735)

mosaicml · Nov 14, 2023 · 45113eb · 45113eb
1 parent 753feff
commit 45113eb
Show file tree

Hide file tree

Showing 6 changed files with 0 additions and 10 deletions.
diff --git 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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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