Upload folder using huggingface_hub

config.json

@@ -1,29 +1,39 @@
 {
-  "_name_or_path": "EleutherAI/pythia-160m",
+  "_name_or_path": "bigcode/tiny_starcoder_py",
+  "activation_function": "gelu_pytorch_tanh",
   "architectures": [
-    "GPTNeoXForCausalLM"
+    "GPTBigCodeForCausalLM"
   ],
-  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "attn_pdrop": 0.1,
   "bos_token_id": 0,
-  "classifier_dropout": 0.1,
+  "embd_pdrop": 0.1,
   "eos_token_id": 0,
-  "hidden_act": "gelu",
-  "hidden_dropout": 0.0,
-  "hidden_size": 768,
+  "inference_runner": 0,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 2048,
-  "model_type": "gpt_neox",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "rope_scaling": null,
-  "rotary_emb_base": 10000,
-  "rotary_pct": 0.25,
-  "tie_word_embeddings": false,
+  "layer_norm_epsilon": 1e-05,
+  "max_batch_size": null,
+  "max_sequence_length": null,
+  "model_type": "gpt_bigcode",
+  "multi_query": true,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": 3072,
+  "n_layer": 20,
+  "n_positions": 8192,
+  "pad_key_length": true,
+  "pre_allocate_kv_cache": false,
+  "resid_pdrop": 0.1,
+  "scale_attention_softmax_in_fp32": true,
+  "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": "4.35.2",
   "use_cache": true,
-  "use_parallel_residual": true,
-  "vocab_size": 50304
+  "validate_runner_input": true,
+  "vocab_size": 49152
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c5986f47218d8f11757fc45a301bcdbfef9f457132ca78a54f60aec0ab2fefb
-size 649308728
+oid sha256:2511febb239ddea42bb00cce01ba561ffec5cd6f53554ec54ae0fd416fe93f30
+size 656601304