theprint/phi-3-mini-4k-python
12k
1{2 "_name_or_path": "unsloth/Phi-3-mini-4k-instruct-bnb-4bit",3 "architectures": [4 "MistralForCausalLM"5 ],6 "attention_dropout": 0.0,7 "bos_token_id": 1,8 "eos_token_id": 32000,9 "hidden_act": "silu",10 "hidden_size": 3072,11 "initializer_range": 0.02,12 "intermediate_size": 8192,13 "max_position_embeddings": 4096,14 "model_type": "mistral",15 "num_attention_heads": 32,16 "num_hidden_layers": 32,17 "num_key_value_heads": 32,18 "pad_token_id": 32000,19 "rms_norm_eps": 1e-05,20 "rope_theta": 10000.0,21 "sliding_window": 2048,22 "tie_word_embeddings": false,23 "torch_dtype": "float16",24 "transformers_version": "4.41.2",25 "unsloth_version": "2024.5",26 "use_cache": true,27 "vocab_size": 3206428}