push-o-matic

config.json

@@ -1,5 +1,8 @@
 {
   "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomModel"
+  ],
   "attention_dropout": 0.0,
   "attention_softmax_in_fp32": true,
   "bias_dropout_fusion": true,
@@ -7,14 +10,14 @@
   "dht_prefix": "bigscience/test-bloomd-6b3",
   "eos_token_id": 2,
   "hidden_dropout": 0.0,
+  "hidden_size": 4096,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "masked_softmax_fusion": true,
   "model_type": "bloom",
-  "n_embed": 4096,
+  "n_head": 32,
   "n_inner": null,
   "n_layer": 30,
-  "num_attention_heads": 32,
   "offset_alibi": 100,
   "pad_token_id": 3,
   "pretraining_tp": 4,
@@ -24,6 +27,6 @@
   "slow_but_exact": false,
   "transformers_version": "4.21.0.dev0",
   "unk_token_id": 0,
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 250880
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a16a76ab0ef60497ad99fe7c5f6e76f455b1dae5d08fadeaebc849d14d1f5093
+oid sha256:50f206263e7636fc72a42747e86c39d576f3b6790f209132bdb8b03fa0660fb7
 size 2055243291

tokenizer_config.json

@@ -2,9 +2,9 @@
   "add_prefix_space": false,
   "bos_token": "<s>",
   "eos_token": "</s>",
-  "model_max_length": 1024,
   "name_or_path": "bigscience/bloom-6b3",
   "pad_token": "<pad>",
+  "padding_side": "left",
   "special_tokens_map_file": null,
   "tokenizer_class": "BloomTokenizer",
   "unk_token": "<unk>"