| { | |
| "_name_or_path": "/ceph/hdd/staff/charpent/.cache/modelss1topxxmln453_33", | |
| "architectures": [ | |
| "Gemma2ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attn_logit_softcapping": 50.0, | |
| "bos_token_id": 2, | |
| "cache_implementation": "hybrid", | |
| "dtype": "bfloat16", | |
| "eos_token_id": 1, | |
| "final_logit_softcapping": 30.0, | |
| "head_dim": 256, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_activation": "gelu_pytorch_tanh", | |
| "hidden_size": 2304, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 9216, | |
| "max_position_embeddings": 8192, | |
| "model_type": "gemma2", | |
| "num_attention_heads": 8, | |
| "num_hidden_layers": 26, | |
| "num_key_value_heads": 4, | |
| "pad_token_id": 0, | |
| "quantization_config": { | |
| "_load_in_4bit": true, | |
| "_load_in_8bit": false, | |
| "bnb_4bit_compute_dtype": "bfloat16", | |
| "bnb_4bit_quant_storage": "uint8", | |
| "bnb_4bit_quant_type": "fp4", | |
| "bnb_4bit_use_double_quant": false, | |
| "llm_int8_enable_fp32_cpu_offload": false, | |
| "llm_int8_has_fp16_weight": false, | |
| "llm_int8_skip_modules": [ | |
| "lm_head" | |
| ], | |
| "llm_int8_threshold": 6.0, | |
| "load_in_4bit": true, | |
| "load_in_8bit": false, | |
| "quant_method": "bitsandbytes" | |
| }, | |
| "query_pre_attn_scalar": 224, | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta": 10000.0, | |
| "sliding_window": 4096, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.42.4", | |
| "use_cache": true, | |
| "vocab_size": 256000 | |
| } | |