Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-57000/trainer_state.json filter=lfs diff=lfs merge=lfs -text

checkpoint-57000/config.json

@@ -0,0 +1,34 @@
+{
+  "architectures": [
+    "PhiForCausalLM"
+  ],
+  "attention_dropout": 0.2,
+  "attn_pdrop": 0.2,
+  "bos_token_id": 126,
+  "embd_pdrop": 0.2,
+  "eos_token_id": 127,
+  "hidden_act": "gelu_new",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 256,
+  "model_type": "phi",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 12,
+  "partial_rotary_factor": 0.5,
+  "qk_layernorm": false,
+  "resid_pdrop": 0.2,
+  "rope_scaling": {
+    "factor": 2.0,
+    "rope_type": "linear",
+    "type": "linear"
+  },
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.0.dev0",
+  "use_cache": true,
+  "vocab_size": 128
+}

checkpoint-57000/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 126,
+  "eos_token_id": 127,
+  "transformers_version": "4.53.0.dev0"
+}

checkpoint-57000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e79c1a5b2220be3a22d24924ec7e4ddcdd76c1128cbab717f8346d33ed3c67a8
+size 170486872

checkpoint-57000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d28e8466866e77fb877900764a39fe6cd16a75f7076535399ba1fcd63f8af44
+size 341082635

checkpoint-57000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be3041a85aa8ec91a0a928965d70552f6e2e1660be5fdd39effc2fdc2aa17af3
+size 14645

checkpoint-57000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:439135c3b7434a00c95eed83ed5c1a5c23ff85e651c104fd0abca05e1074e994
+size 1465

checkpoint-57000/trainer_state.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8492b9b6fec4bbebb67610bba3c644c54d2a3a03aeb8ca279f450d13fb120a3
+size 12735786

checkpoint-57000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8244366125f5c8258f6d7ce3b674d8f1331a98bf56d1d6a9e8b5b001b440e20a
+size 5713

config.json

@@ -0,0 +1,34 @@
+{
+  "architectures": [
+    "PhiForCausalLM"
+  ],
+  "attention_dropout": 0.2,
+  "attn_pdrop": 0.2,
+  "bos_token_id": 126,
+  "embd_pdrop": 0.2,
+  "eos_token_id": 127,
+  "hidden_act": "gelu_new",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 256,
+  "model_type": "phi",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 12,
+  "partial_rotary_factor": 0.5,
+  "qk_layernorm": false,
+  "resid_pdrop": 0.2,
+  "rope_scaling": {
+    "factor": 2.0,
+    "rope_type": "linear",
+    "type": "linear"
+  },
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.0.dev0",
+  "use_cache": true,
+  "vocab_size": 128
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 126,
+  "eos_token_id": 127,
+  "transformers_version": "4.53.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e79c1a5b2220be3a22d24924ec7e4ddcdd76c1128cbab717f8346d33ed3c67a8
+size 170486872

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8244366125f5c8258f6d7ce3b674d8f1331a98bf56d1d6a9e8b5b001b440e20a
+size 5713