maisonmargela/granite-8b-code-small-stackoverflow
024
1{2 "_name_or_path": "ibm-granite/granite-8b-code-base",3 "architectures": [4 "LlamaForCausalLM"5 ],6 "attention_bias": true,7 "attention_dropout": 0.1,8 "bos_token_id": 0,9 "eos_token_id": 0,10 "hidden_act": "silu",11 "hidden_size": 4096,12 "initializer_range": 0.02,13 "intermediate_size": 14336,14 "max_position_embeddings": 4096,15 "mlp_bias": true,16 "model_type": "llama",17 "num_attention_heads": 32,18 "num_hidden_layers": 36,19 "num_key_value_heads": 8,20 "pad_token_id": 0,21 "pretraining_tp": 1,22 "rms_norm_eps": 1e-05,23 "rope_scaling": null,24 "rope_theta": 10000,25 "tie_word_embeddings": true,26 "torch_dtype": "float16",27 "transformers_version": "4.40.2",28 "use_cache": true,29 "vocab_size": 4915230}31 