Upload model

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "/data/llmjp0/model_cache_dir/outputs/checkpoint_HF/1.3B/ds_gpt_v101_fattn_nfs_0825_refined-data-gpt_1.3B_refined_gpu96_node12_lr0.0001708_gbs1536_mbs4_nwk2_zero1_pp1/global_step96173",
+  "activation_function": "gelu",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 7,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 7,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 2048,
+  "n_head": 16,
+  "n_inner": 8192,
+  "n_layer": 24,
+  "n_positions": 2048,
+  "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,
+  "torch_dtype": "float16",
+  "transformers_version": "4.34.0",
+  "use_cache": true,
+  "vocab_size": 50688
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 7,
+  "eos_token_id": 7,
+  "transformers_version": "4.34.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ed5e7d03afb86318ccf73475a3151192a0f25994ab05c8d2396cce9e74953e9
+size 2633307101