rahuldshetty/tinyllama-python

1{2  "_name_or_path": "unsloth/tinyllama",3  "architectures": [4    "LlamaForCausalLM"5  ],6  "attention_bias": false,7  "attention_dropout": 0.0,8  "bos_token_id": 1,9  "eos_token_id": 2,10  "hidden_act": "silu",11  "hidden_size": 2048,12  "initializer_range": 0.02,13  "intermediate_size": 5632,14  "max_position_embeddings": 4096,15  "model_type": "llama",16  "num_attention_heads": 32,17  "num_hidden_layers": 22,18  "num_key_value_heads": 4,19  "pad_token_id": 0,20  "pretraining_tp": 1,21  "quantization_config": {22    "bnb_4bit_compute_dtype": "float16",23    "bnb_4bit_quant_type": "nf4",24    "bnb_4bit_use_double_quant": true,25    "llm_int8_enable_fp32_cpu_offload": false,26    "llm_int8_has_fp16_weight": false,27    "llm_int8_skip_modules": "null",28    "llm_int8_threshold": 6.0,29    "load_in_4bit": true,30    "load_in_8bit": false,31    "quant_method": "bitsandbytes"32  },33  "rms_norm_eps": 1e-05,34  "rope_scaling": {35    "factor": 2.0,36    "type": "linear"37  },38  "rope_theta": 10000.0,39  "tie_word_embeddings": false,40  "torch_dtype": "float16",41  "transformers_version": "4.37.0.dev0",42  "unsloth_version": "2024.1",43  "use_cache": true,44  "vocab_size": 3200045}46