| { |
| "architectures": [ |
| "ApertusForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 1, |
| "torch_dtype": "bfloat16", |
| "eos_token_id": 68, |
| "hidden_act": "xielu", |
| "hidden_dropout": 0.0, |
| "hidden_size": 4096, |
| "initializer_range": 0.02, |
| "intermediate_size": 21504, |
| "max_position_embeddings": 65536, |
| "mlp_bias": false, |
| "model_type": "apertus", |
| "num_attention_heads": 32, |
| "num_hidden_layers": 32, |
| "num_key_value_heads": 8, |
| "pad_token_id": 3, |
| "post_norm": false, |
| "qk_norm": true, |
| "quantization_config": { |
| "_load_in_4bit": true, |
| "_load_in_8bit": false, |
| "bnb_4bit_compute_dtype": "bfloat16", |
| "bnb_4bit_quant_storage": "uint8", |
| "bnb_4bit_quant_type": "nf4", |
| "bnb_4bit_use_double_quant": true, |
| "llm_int8_enable_fp32_cpu_offload": false, |
| "llm_int8_has_fp16_weight": false, |
| "llm_int8_skip_modules": [ |
| "embed_tokens", |
| "embedding", |
| "lm_head", |
| "multi_modal_projector", |
| "merger", |
| "modality_projection", |
| "router", |
| "visual", |
| "vision_tower", |
| "model.layers.7.mlp", |
| "model.layers.6.mlp", |
| "model.layers.9.self_attn", |
| "model.layers.12.self_attn", |
| "model.layers.28.mlp", |
| "model.layers.2.mlp", |
| "model.layers.0.self_attn.o_proj", |
| "model.layers.0.mlp.down_proj", |
| "model.layers.1.self_attn.o_proj", |
| "model.layers.2.self_attn.o_proj", |
| "model.layers.3.self_attn.o_proj", |
| "model.layers.4.self_attn.o_proj", |
| "model.layers.5.self_attn.o_proj", |
| "model.layers.6.self_attn.o_proj", |
| "model.layers.7.self_attn.o_proj", |
| "model.layers.9.self_attn.o_proj", |
| "model.layers.10.self_attn.o_proj", |
| "model.layers.11.self_attn.o_proj", |
| "model.layers.12.self_attn.o_proj", |
| "model.layers.13.self_attn.o_proj", |
| "model.layers.14.self_attn.o_proj", |
| "model.layers.15.self_attn.o_proj", |
| "model.layers.16.self_attn.o_proj", |
| "model.layers.18.self_attn.o_proj", |
| "model.layers.19.self_attn.o_proj", |
| "model.layers.24.self_attn.o_proj", |
| "model.layers.28.self_attn.o_proj", |
| "model.layers.30.self_attn.o_proj" |
| ], |
| "llm_int8_threshold": 6.0, |
| "load_in_4bit": true, |
| "load_in_8bit": false, |
| "quant_method": "bitsandbytes" |
| }, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": { |
| "factor": 8.0, |
| "high_freq_factor": 4.0, |
| "low_freq_factor": 1.0, |
| "original_max_position_embeddings": 8192, |
| "rope_type": "llama3", |
| "type": "llama3" |
| }, |
| "rope_theta": 12000000, |
| "tie_word_embeddings": false, |
| "transformers_version": "4.56.2", |
| "unsloth_fixed": true, |
| "use_cache": false, |
| "vocab_size": 131072 |
| } |
|
|