Upload model

config.json

@@ -1,30 +1,32 @@
 {
-  "_name_or_path": "cti_report_summarizer",
+  "_name_or_path": "cerebras/Cerebras-GPT-590M",
+  "activation_function": "gelu",
   "architectures": [
-    "GPTNeoXForCausalLM"
+    "GPT2LMHeadModel"
   ],
-  "attention_bias": true,
-  "attention_dropout": 0.0,
-  "bos_token_id": 0,
-  "classifier_dropout": 0.1,
-  "eos_token_id": 0,
-  "hidden_act": "gelu",
-  "hidden_dropout": 0.0,
-  "hidden_size": 1024,
+  "attn_pdrop": 0.0,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 2048,
-  "model_type": "gpt_neox",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
-  "rope_scaling": null,
-  "rotary_emb_base": 10000,
-  "rotary_pct": 0.25,
-  "tie_word_embeddings": false,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_embd": 1536,
+  "n_head": 12,
+  "n_inner": 6144,
+  "n_layer": 18,
+  "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": "4.40.1",
   "use_cache": true,
-  "use_parallel_residual": true,
-  "vocab_size": 50304
+  "vocab_size": 50257
 }

generation_config.json

@@ -1,6 +1,6 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 0,
-  "eos_token_id": 0,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
   "transformers_version": "4.40.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:937c99e8c5e21341dbe8572558d275315366d3572238500fd6274fb82a690d4e
-size 1621370224
+oid sha256:60d9553bda53fdf7343d22c0a868f95094c59e7455c5a87d232c72622e17bb66
+size 2361266536