| { | |
| "_name_or_path": "UnfilteredAI/NSFW-3B", | |
| "architectures": [ | |
| "CohereForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_HelpingAI.HelpingAIConfig", | |
| "AutoModelForCausalLM": "UnfilteredAI/NSFW-3B--modeling_HelpingAI.HelpingAIForCausalLM" | |
| }, | |
| "bos_token_id": 50278, | |
| "classifier_dropout": 0.1, | |
| "eos_token_id": 50279, | |
| "head_dim": 256, | |
| "hidden_act": "silu", | |
| "hidden_activation": null, | |
| "hidden_dropout": 0.0, | |
| "hidden_size": 2560, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 6912, | |
| "layer_norm_eps": 1e-05, | |
| "max_position_embeddings": 4096, | |
| "model_type": "HelpingAI", | |
| "norm_eps": 1e-05, | |
| "num_attention_heads": 32, | |
| "num_experts_per_tok": 2, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 32, | |
| "num_local_experts": 8, | |
| "output_router_logits": false, | |
| "partial_rotary_factor": 0.25, | |
| "quantization_config": { | |
| "_load_in_4bit": true, | |
| "_load_in_8bit": false, | |
| "bnb_4bit_compute_dtype": "bfloat16", | |
| "bnb_4bit_quant_storage": "bfloat16", | |
| "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": null, | |
| "llm_int8_threshold": 6.0, | |
| "load_in_4bit": true, | |
| "load_in_8bit": false, | |
| "quant_method": "bitsandbytes" | |
| }, | |
| "rms_norm_eps": 1e-06, | |
| "rope_pct": 0.25, | |
| "rope_scaling": null, | |
| "rope_theta": 10000, | |
| "router_aux_loss_coef": 0.02, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.42.3", | |
| "use_cache": false, | |
| "use_qkv_bias": false, | |
| "vocab_size": 50281 | |
| } | |