Upload model

config.json

@@ -1,89 +1,39 @@
 {
-  "_name_or_path": "apple/OpenELM-270M-Instruct",
-  "activation_fn_name": "swish",
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
   "architectures": [
-    "OpenELMForCausalLM"
+    "GPT2LMHeadModel"
   ],
-  "auto_map": {
-    "AutoConfig": "apple/OpenELM-270M-Instruct--configuration_openelm.OpenELMConfig",
-    "AutoModelForCausalLM": "apple/OpenELM-270M-Instruct--modeling_openelm.OpenELMForCausalLM"
-  },
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "ffn_dim_divisor": 256,
-  "ffn_multipliers": [
-    0.5,
-    0.73,
-    0.97,
-    1.2,
-    1.43,
-    1.67,
-    1.9,
-    2.13,
-    2.37,
-    2.6,
-    2.83,
-    3.07,
-    3.3,
-    3.53,
-    3.77,
-    4.0
-  ],
-  "ffn_with_glu": true,
-  "head_dim": 64,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "max_context_length": 2048,
-  "model_dim": 1280,
-  "model_type": "openelm",
-  "normalization_layer_name": "rms_norm",
-  "normalize_qk_projections": true,
-  "num_gqa_groups": 4,
-  "num_kv_heads": [
-    3,
-    3,
-    3,
-    3,
-    3,
-    4,
-    4,
-    4,
-    4,
-    4,
-    4,
-    4,
-    5,
-    5,
-    5,
-    5
-  ],
-  "num_query_heads": [
-    12,
-    12,
-    12,
-    12,
-    12,
-    16,
-    16,
-    16,
-    16,
-    16,
-    16,
-    16,
-    20,
-    20,
-    20,
-    20
-  ],
-  "num_transformer_layers": 16,
-  "qkv_multipliers": [
-    0.5,
-    1.0
-  ],
-  "rope_freq_constant": 10000,
-  "rope_max_length": 4096,
-  "share_input_output_layers": true,
+  "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,
+  "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": "float32",
   "transformers_version": "4.46.3",
   "use_cache": true,
-  "vocab_size": 32000
+  "vocab_size": 50257
 }

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": "4.46.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3533b6637933eac2477a105ca5c63885c1f36b97efb0013c28d04ea5efdfd1c4
-size 1086123184
+oid sha256:f64ee0f8e61086240eed3b6ca93a879de041976727e4f919df57df28d66e2a01
+size 497774208