Upload model

config.json

@@ -5,18 +5,19 @@
   ],
   "attn_pdrop": 0.1,
   "bos_token_id": 50256,
-  "dtype": "bfloat16",
+  "dtype": "float32",
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
+  "intermediate_size": 32,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
-  "n_ctx": 1024,
   "n_embd": 8,
   "n_head": 4,
   "n_inner": null,
   "n_layer": 2,
   "n_positions": 1024,
+  "num_key_value_heads": 2,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,
@@ -26,12 +27,6 @@
   "summary_proj_to_labels": true,
   "summary_type": "cls_index",
   "summary_use_proj": true,
-  "task_specific_params": {
-    "text-generation": {
-      "do_sample": true,
-      "max_length": 50
-    }
-  },
   "transformers_version": "4.57.0.dev0",
   "use_cache": true,
   "vocab_size": 50257

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07b862c46681bcbf918b437645266488f0de4c38eba6b7417116b384ff0c38a9
-size 826536
+oid sha256:7be33b67605f25d79fc603526434e8ca451c0a4dd743ddda54a90c9804aa2e72
+size 1650536