Upload folder using huggingface_hub (#11)

- b39087967277caacf2fd52df0e3f6b8d7094e50943fc558d6b93b04551d545a6 (5b0637d4d4fd214456166548741f14a81681ae0a)

config.json

@@ -1,30 +1,22 @@
 {
-    "_name_or_path": "/covalent/.cache/models/tmp2bzhzdeygdc1g4no",
+    "_name_or_path": "/covalent/.cache/models/tmpn6xfl4p6rr5vasf3",
     "activation_function": "gelu_new",
     "architectures": [
         "GPT2LMHeadModel"
     ],
     "attn_pdrop": 0.1,
-    "bos_token_id": 1,
+    "bos_token_id": 50256,
     "embd_pdrop": 0.1,
-    "eos_token_id": 2,
-    "gradient_checkpointing": false,
-    "id2label": {
-        "0": "LABEL_0"
-    },
+    "eos_token_id": 50256,
     "initializer_range": 0.02,
-    "label2id": {
-        "LABEL_0": 0
-    },
     "layer_norm_epsilon": 1e-05,
     "model_type": "gpt2",
-    "n_ctx": 2048,
+    "n_ctx": 1024,
     "n_embd": 768,
     "n_head": 12,
     "n_inner": null,
     "n_layer": 12,
-    "n_positions": 2048,
-    "pad_token_id": 0,
+    "n_positions": 1024,
     "quantization_config": {
         "_load_in_4bit": false,
         "_load_in_8bit": true,
@@ -51,9 +43,15 @@
     "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": "float16",
     "transformers_version": "4.46.2",
     "use_cache": true,
-    "vocab_size": 50264,
+    "vocab_size": 50257,
     "api_key": null
 }

generation_config.json

@@ -1,7 +1,6 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "pad_token_id": 0,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
   "transformers_version": "4.46.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62dc750aa6e44b6b42e62ac17669a7e2f64bd05f4cc6f03f028ad710f1192e5b
-size 165884440
+oid sha256:52d6664e6c842ad768891439d7fb68df99058ad6159633a3f3f2c000b4ba5385
+size 164300824

smash_config.json

@@ -28,7 +28,7 @@
     "quant_llm-int8_weight_bits": 8,
     "max_batch_size": 1,
     "device": "cuda",
-    "cache_dir": "/covalent/.cache/models/tmp2bzhzdey",
+    "cache_dir": "/covalent/.cache/models/tmpn6xfl4p6",
     "task": "",
     "save_load_fn": "bitsandbytes",
     "save_load_fn_args": {}