Pinkstack/Superthoughts-lite-v1-Q8-mlx
133
1{2 "architectures": [3 "LlamaForCausalLM"4 ],5 "attention_bias": false,6 "attention_dropout": 0.0,7 "bos_token_id": 1,8 "eos_token_id": 2,9 "head_dim": 64,10 "hidden_act": "silu",11 "hidden_size": 2048,12 "initializer_range": 0.02,13 "intermediate_size": 8192,14 "max_position_embeddings": 8192,15 "mlp_bias": false,16 "model_type": "llama",17 "num_attention_heads": 32,18 "num_hidden_layers": 24,19 "num_key_value_heads": 32,20 "pad_token_id": 49152,21 "pretraining_tp": 1,22 "quantization": {23 "group_size": 64,24 "bits": 825 },26 "quantization_config": {27 "group_size": 64,28 "bits": 829 },30 "rms_norm_eps": 1e-05,31 "rope_scaling": null,32 "rope_theta": 130000,33 "tie_word_embeddings": true,34 "torch_dtype": "float16",35 "transformers.js_config": {36 "kv_cache_dtype": {37 "fp16": "float16",38 "q4f16": "float16"39 }40 },41 "transformers_version": "4.48.3",42 "unsloth_fixed": true,43 "unsloth_version": "2025.2.5",44 "use_cache": true,45 "vocab_size": 4915346}