Upload model

config.json

@@ -1,31 +1,32 @@
 {
-  "_name_or_path": "facebook/opt-350m",
-  "_remove_final_layer_norm": false,
-  "activation_dropout": 0.0,
-  "activation_function": "relu",
+  "_name_or_path": "cerebras/Cerebras-GPT-256M",
+  "activation_function": "gelu",
   "architectures": [
-    "OPTForCausalLM"
+    "GPT2LMHeadModel"
   ],
-  "attention_dropout": 0.0,
-  "bos_token_id": 2,
-  "do_layer_norm_before": false,
-  "dropout": 0.1,
-  "enable_bias": true,
-  "eos_token_id": 2,
-  "ffn_dim": 4096,
-  "hidden_size": 1024,
-  "init_std": 0.02,
-  "layer_norm_elementwise_affine": true,
-  "layerdrop": 0.0,
-  "max_position_embeddings": 2048,
-  "model_type": "opt",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
-  "pad_token_id": 1,
-  "prefix": "</s>",
+  "attn_pdrop": 0.0,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_embd": 1088,
+  "n_head": 17,
+  "n_inner": 4352,
+  "n_layer": 14,
+  "n_positions": 2048,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.0,
+  "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": 50272,
-  "word_embed_proj_dim": 512
+  "vocab_size": 50257
 }

generation_config.json

@@ -1,7 +1,6 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 2,
-  "eos_token_id": 2,
-  "pad_token_id": 1,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
   "transformers_version": "4.39.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7f330534a0774129ccefbcdcfb79303ab4f3ee88634b512f93eb4f87f59671e
-size 1324830880
+oid sha256:1e055c157c8de350edbd0a09f9b68de8bb6e7ba386d3921fe07682b89a80998f
+size 1023925760