3b647129fcd3325575085a1f640aa33407c0f0a263e44e8f03473ef921824d6e

config.json

@@ -1,21 +1,22 @@
 {
-    "_name_or_path": "/covalent/.cache/models/tmp4xz2tdfviscktn9o",
+    "_name_or_path": "/covalent/.cache/models/tmpysopg_w8vy94jgc8",
+    "activation_function": "gelu_new",
     "architectures": [
-        "MistralForCausalLM"
+        "GPT2LMHeadModel"
     ],
-    "attention_dropout": 0.0,
-    "bos_token_id": 1,
-    "eos_token_id": 2,
-    "head_dim": 128,
-    "hidden_act": "silu",
-    "hidden_size": 4096,
+    "attn_pdrop": 0.1,
+    "bos_token_id": 50256,
+    "embd_pdrop": 0.1,
+    "eos_token_id": 50256,
     "initializer_range": 0.02,
-    "intermediate_size": 14336,
-    "max_position_embeddings": 32768,
-    "model_type": "mistral",
-    "num_attention_heads": 32,
-    "num_hidden_layers": 32,
-    "num_key_value_heads": 8,
+    "layer_norm_epsilon": 1e-05,
+    "model_type": "gpt2",
+    "n_ctx": 1024,
+    "n_embd": 768,
+    "n_head": 12,
+    "n_inner": null,
+    "n_layer": 12,
+    "n_positions": 1024,
     "quantization_config": {
         "_load_in_4bit": false,
         "_load_in_8bit": true,
@@ -33,13 +34,24 @@
         "load_in_8bit": true,
         "quant_method": "bitsandbytes"
     },
-    "rms_norm_eps": 1e-05,
-    "rope_theta": 1000000.0,
-    "sliding_window": null,
-    "tie_word_embeddings": false,
+    "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": "float16",
     "transformers_version": "4.46.2",
     "use_cache": true,
-    "vocab_size": 32768,
+    "vocab_size": 50257,
     "api_key": null
 }

generation_config.json

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

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:825fa12a420e39b0dbb728ae43723b4dc9d16060926ab92fc272eb7a88d40f14
+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/tmp4xz2tdfv",
+    "cache_dir": "/covalent/.cache/models/tmpysopg_w8",
     "task": "",
     "save_load_fn": "bitsandbytes",
     "save_load_fn_args": {}