adpretko/train-riscv-O2_epoch3_AMD
013
1{2 "architectures": [3 "Qwen2ForCausalLM"4 ],5 "attention_dropout": 0.0,6 "bos_token_id": 151643,7 "eos_token_id": 151645,8 "hidden_act": "silu",9 "hidden_size": 1536,10 "initializer_range": 0.02,11 "intermediate_size": 8960,12 "layer_types": [13 "full_attention",14 "full_attention",15 "full_attention",16 "full_attention",17 "full_attention",18 "full_attention",19 "full_attention",20 "full_attention",21 "full_attention",22 "full_attention",23 "full_attention",24 "full_attention",25 "full_attention",26 "full_attention",27 "full_attention",28 "full_attention",29 "full_attention",30 "full_attention",31 "full_attention",32 "full_attention",33 "full_attention",34 "full_attention",35 "full_attention",36 "full_attention",37 "full_attention",38 "full_attention",39 "full_attention",40 "full_attention"41 ],42 "max_position_embeddings": 32768,43 "max_window_layers": 21,44 "model_type": "qwen2",45 "num_attention_heads": 12,46 "num_hidden_layers": 28,47 "num_key_value_heads": 2,48 "rms_norm_eps": 1e-06,49 "rope_scaling": null,50 "rope_theta": 1000000.0,51 "sliding_window": null,52 "tie_word_embeddings": true,53 "torch_dtype": "bfloat16",54 "transformers_version": "4.55.0",55 "use_cache": false,56 "use_sliding_window": false,57 "vocab_size": 15193658}59 