Upload DeciCoderForCausalLM

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "Deci/DeciCoder-1b",
+  "architectures": [
+    "DeciCoderForCausalLM"
+  ],
+  "attention_bias": false,
+  "auto_map": {
+    "AutoConfig": "Deci/DeciCoder-1b--configuration_decicoder.DeciCoderConfig",
+    "AutoModelForCausalLM": "Deci/DeciCoder-1b--modeling_decicoder.DeciCoderForCausalLM"
+  },
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5888,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "naive_attention_decode_batched": true,
+  "naive_attention_decode_single": false,
+  "naive_attention_prefill": false,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 20,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.34.0",
+  "use_bfloat16": true,
+  "use_cache": true,
+  "vocab_size": 49152
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.34.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:440e1e08a6c7c2219c0d5dac364e17567a10221d08030e7064f6b09c718ccd17
+size 2227404713