molmo-7B-D-bnb-4bit / config.json
cyan2k's picture
Update config.json
917f180 verified
{
"_name_or_path": "cyan2k/molmo-7B-D-bnb-4bit",
"architectures": [
"MolmoForCausalLM"
],
"attention_layer_norm": false,
"auto_map": {
"AutoConfig": "config_molmo.MolmoConfig",
"AutoModelForCausalLM": "modeling_molmo.MolmoForCausalLM"
},
"clip_qkv": null,
"embedding_size": 152064,
"hidden_size": 3584,
"initializer_range": 0.02,
"intermediate_size": 37888,
"layer_norm_eps": 1e-06,
"layer_norm_type": "rms",
"max_position_embeddings": 4096,
"model_type": "molmo",
"norm_after": false,
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"qkv_bias": true,
"quantization_config": {
"_load_in_4bit": true,
"_load_in_8bit": false,
"bnb_4bit_compute_dtype": "float32",
"bnb_4bit_quant_storage": "uint8",
"bnb_4bit_quant_type": "fp4",
"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"
},
"rope_theta": 1000000.0,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.44.0",
"use_cache": true,
"use_position_ids": true,
"vocab_size": 152064,
"weight_tying": false
}