Upload 12 files

This is Ghazal Small Pretrained LLM with 124 M Params trained on 1.5B Tokens

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": null,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 64000,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 768,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 768,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "use_cache": true,
+  "vocab_size": 64002
+}

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 64000,
+  "transformers_version": "4.26.1"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97931ddea8c30d77b7811b2c971760d064ea29a0e9b4b4ed3a88d3297eecabcf
+size 1078481861

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e56b94b4242a617239256e00722f0f56924dd2eafa0c0007b93f178623b7ca06
+size 546331197

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84290731c7ca60bd4ac2da53d4ef86e0612c7fad522f3966b7fe0bf8ded9924c
+size 15597

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d011f2ad242133664d5c210e4430195460701c9035092826b29ba59ca03962aa
+size 557

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4caf1d864fcff137a7c1c21f3b039dd6bb72190348ec6c92fc6584595b6fa57
+size 627

special_tokens_map.json

@@ -0,0 +1,4 @@
+{
+  "eos_token": "<EOS>",
+  "pad_token": "<EOS>"
+}

tokenizer_config.json

@@ -0,0 +1,4 @@
+{
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f44d489779f957d1098d4de5722bf51c6a086f0f6e57f842819279422d6d5405
+size 3451