cf7e1418fc7b5cb0c81900b108b8f3fd2b5f6484d3a398c1a2b45b8179c49f7b

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/covalent/.cache/models/tmpk1t5rgu6v17wvlsb",
+  "_name_or_path": "/covalent/.cache/models/tmp40i0g00bxd3z4zcp",
   "activation_function": "gelu_new",
   "architectures": [
     "GPTOptim"

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a9316cb534bf66e7e13d432916c9d943119734ba5ed1df39a00f821c9fa3380
+oid sha256:6fe716862891eb09b200da6d0eb2214796809985c13fcbe14d2c3c27f542762f
 size 1207575528

models--distributed--optimized-gpt2-1b/refs/main

@@ -1 +1 @@
-fba79423a8549ee57e7ae92c54c57628e4a3b012
+0f5f2c85309718087017f97adaabc63a05d6a493

models--distributed--optimized-gpt2-1b/snapshots/0f5f2c85309718087017f97adaabc63a05d6a493/config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "distributed/optimized-gpt2-1b",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPTOptim"
+  ],
+  "attn_pdrop": 0.1,
+  "auto_map": {
+    "AutoConfig": "distributed/optimized-gpt2-500m--configuration_gpt_optimized.GPTOptimConfig",
+    "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
+  },
+  "block_size": 1024,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt_optimized",
+  "n_embd": 1280,
+  "n_head": 32,
+  "n_inner": null,
+  "n_layer": 48,
+  "n_positions": 1024,
+  "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": "float32",
+  "transformers_version": "4.39.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

smash_config.json

@@ -28,7 +28,7 @@
     "quant_llm-int8_weight_bits": 8,
     "max_batch_size": 1,
     "device": "cuda",
-    "cache_dir": "/covalent/.cache/models/tmpk1t5rgu6",
+    "cache_dir": "/covalent/.cache/models/tmp40i0g00b",
     "task": "",
     "save_load_fn": "bitsandbytes",
     "save_load_fn_args": {