Upload folder using huggingface_hub

checkpoints/llamastack/config.json

@@ -1,25 +1,26 @@
 {
-  "_name_or_path": "/content/tmp-output/checkpoint-100",
+  "_name_or_path": "bert-base-cased",
   "architectures": [
-    "GPTNeoXForCausalLM"
+    "BertModel"
   ],
-  "bos_token_id": 0,
-  "eos_token_id": 0,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
-  "hidden_size": 1024,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 2048,
-  "model_type": "gpt_neox",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
-  "rotary_emb_base": 10000,
-  "rotary_pct": 0.25,
-  "tie_word_embeddings": false,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.28.1",
+  "transformers_version": "4.29.2",
+  "type_vocab_size": 2,
   "use_cache": true,
-  "use_parallel_residual": true,
-  "vocab_size": 50304
+  "vocab_size": 28996
 }

checkpoints/llamastack/pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49a78274352d78140a0815f4d9223109be52486e9e634f0d7cf7773909580283
+size 194646579

checkpoints/llamastack/pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c69b3f1cd4e70ddbeac3609e2c175c3c207df3f79b5d2436532a4ffd354c8f95
+size 198498043

checkpoints/llamastack/pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:492c90340fe8439dcd723b70fc995d1998ebe83075117a66235b8cc846ff74f7
+size 40167707

checkpoints/llamastack/pytorch_model.bin.index.json

@@ -0,0 +1,207 @@
+{
+  "metadata": {
+    "total_size": 433245184
+  },
+  "weight_map": {
+    "embeddings.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "embeddings.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "embeddings.position_embeddings.weight": "pytorch_model-00001-of-00003.bin",
+    "embeddings.position_ids": "pytorch_model-00001-of-00003.bin",
+    "embeddings.token_type_embeddings.weight": "pytorch_model-00001-of-00003.bin",
+    "embeddings.word_embeddings.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.0.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.0.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.0.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.0.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.0.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.0.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.0.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.0.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.0.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.0.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.0.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.0.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.0.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.0.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.0.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.0.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.1.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.1.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.1.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.1.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.1.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.1.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.1.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.1.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.1.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.1.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.1.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.1.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.1.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.1.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.1.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.1.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.10.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.10.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.10.attention.output.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.10.attention.output.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.10.attention.self.key.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.10.attention.self.key.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.10.attention.self.query.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.10.attention.self.query.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.10.attention.self.value.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.10.attention.self.value.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.10.intermediate.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.10.intermediate.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.10.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.10.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.10.output.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.10.output.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.11.attention.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.11.attention.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.11.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.11.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.11.attention.self.key.bias": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.11.attention.self.key.weight": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.11.attention.self.query.bias": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.11.attention.self.query.weight": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.11.attention.self.value.bias": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.11.attention.self.value.weight": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.11.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.11.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.11.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.11.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.11.output.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.11.output.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "encoder.layer.2.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.2.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.2.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.2.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.2.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.2.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.2.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.2.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.2.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.2.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.2.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.2.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.2.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.2.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.2.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.2.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.3.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.3.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.3.attention.output.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.3.attention.output.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.3.attention.self.key.bias": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.3.attention.self.key.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.3.attention.self.query.bias": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.3.attention.self.query.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.3.attention.self.value.bias": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.3.attention.self.value.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.3.intermediate.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.3.intermediate.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "encoder.layer.3.output.LayerNorm.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.3.output.LayerNorm.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.3.output.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.3.output.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.4.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.4.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.4.attention.output.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.4.attention.output.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.4.attention.self.key.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.4.attention.self.key.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.4.attention.self.query.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.4.attention.self.query.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.4.attention.self.value.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.4.attention.self.value.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.4.intermediate.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.4.intermediate.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.4.output.LayerNorm.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.4.output.LayerNorm.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.4.output.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.4.output.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.5.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.5.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.5.attention.output.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.5.attention.output.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.5.attention.self.key.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.5.attention.self.key.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.5.attention.self.query.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.5.attention.self.query.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.5.attention.self.value.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.5.attention.self.value.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.5.intermediate.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.5.intermediate.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.5.output.LayerNorm.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.5.output.LayerNorm.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.5.output.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.5.output.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.6.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.6.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.6.attention.output.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.6.attention.output.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.6.attention.self.key.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.6.attention.self.key.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.6.attention.self.query.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.6.attention.self.query.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.6.attention.self.value.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.6.attention.self.value.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.6.intermediate.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.6.intermediate.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.6.output.LayerNorm.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.6.output.LayerNorm.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.6.output.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.6.output.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.7.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.7.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.7.attention.output.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.7.attention.output.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.7.attention.self.key.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.7.attention.self.key.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.7.attention.self.query.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.7.attention.self.query.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.7.attention.self.value.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.7.attention.self.value.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.7.intermediate.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.7.intermediate.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.7.output.LayerNorm.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.7.output.LayerNorm.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.7.output.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.7.output.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.8.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.8.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.8.attention.output.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.8.attention.output.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.8.attention.self.key.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.8.attention.self.key.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.8.attention.self.query.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.8.attention.self.query.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.8.attention.self.value.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.8.attention.self.value.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.8.intermediate.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.8.intermediate.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.8.output.LayerNorm.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.8.output.LayerNorm.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.8.output.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.8.output.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.9.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.9.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.9.attention.output.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.9.attention.output.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.9.attention.self.key.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.9.attention.self.key.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.9.attention.self.query.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.9.attention.self.query.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.9.attention.self.value.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.9.attention.self.value.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.9.intermediate.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.9.intermediate.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.9.output.LayerNorm.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.9.output.LayerNorm.weight": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.9.output.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "encoder.layer.9.output.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "pooler.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "pooler.dense.weight": "pytorch_model-00003-of-00003.bin"
+  }
+}