Add files

.gitattributes

@@ -9,14 +9,10 @@
 *.lfs.* 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
@@ -29,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,11 @@
+---
+language: 
+  - eng
+tags:
+- integration
+pipeline_tag: text-generation
+---
+
+# BigScience - testing model
+
+This model aims to test the conversion between Megatron-LM and transformers. It is a small ```GPT-2```-like model that has been used to debug the script. Use it only for integration tests

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "hf-internal-testing/tiny-random-bloom",
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomModel"
+  ],
+  "attention_dropout": 0.1,
+  "bias_dropout_fusion": true,
+  "bos_token_id": 0,
+  "dtype": "bfloat16",
+  "eos_token_id": 0,
+  "hidden_dropout": 0.1,
+  "hidden_size": 64,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "masked_softmax_fusion": true,
+  "model_type": "bloom",
+  "n_head": 8,
+  "n_inner": null,
+  "n_layer": 2,
+  "pretraining_tp": 2,
+  "seq_length": 20,
+  "skip_bias_add": true,
+  "slow_but_exact": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.21.0.dev0",
+  "use_cache": false,
+  "vocab_size": 250880
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e22bceb559a5fcdc3dbb0f9ea622210cbe6b2a56d459ad7693284a1e99569c8
+size 32322126

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fa39cd4b1500feb205bcce3b9703a4373414cafe4970e0657b413f7ddd2a9d3
+size 14500438

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "eos_token": "</s>", "bos_token": "<s>", "pad_token": "<pad>", "name_or_path": "bigscience/tokenizer", "special_tokens_map_file": null, "tokenizer_class": "BloomTokenizerFast"}