ajibawa-2023/Python-Code-33B
9181
1{2 "_name_or_path": "/media/mla100eus1/Projects_1/Python-Code-33B",3 "architectures": [4 "LlamaForCausalLM"5 ],6 "bos_token_id": 1,7 "eos_token_id": 2,8 "hidden_act": "silu",9 "hidden_size": 6656,10 "initializer_range": 0.02,11 "intermediate_size": 17920,12 "max_position_embeddings": 2048,13 "max_sequence_length": 2048,14 "model_type": "llama",15 "num_attention_heads": 52,16 "num_hidden_layers": 60,17 "pad_token_id": 0,18 "rms_norm_eps": 1e-06,19 "tie_word_embeddings": false,20 "torch_dtype": "bfloat16",21 "transformers_version": "4.28.1",22 "use_cache": false,23 "vocab_size": 3200024}25 