Update tiny models for GPTBigCodeForCausalLM

config.json

@@ -0,0 +1,36 @@
+{
+  "activation_function": "relu",
+  "add_cross_attention": false,
+  "architectures": [
+    "GPTBigCodeForCausalLM"
+  ],
+  "attention_softmax_in_fp32": false,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 49152,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 49152,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "is_decoder": true,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt_bigcode",
+  "multi_query": true,
+  "n_embd": 32,
+  "n_head": 4,
+  "n_inner": 37,
+  "n_layer": 2,
+  "n_positions": 512,
+  "num_key_value_heads": 1,
+  "pad_token_id": 49154,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attention_softmax_in_fp32": false,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.16.0.dev0",
+  "type_vocab_size": 16,
+  "use_cache": true,
+  "vocab_size": 49157
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 49152,
+  "eos_token_id": 49152,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 49154,
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:400e48d94833f118e4b9696e148571d2b5ca9f0fa25cc5990ba95c1d9fa31a49
+size 6402112

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|endoftext|>",
+    "<fim-prefix>",
+    "<fim-middle>",
+    "<fim-suffix>",
+    "<fim-pad>"
+  ],
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 512,
+  "tokenizer_class": "TokenizersBackend"
+}