0x8badbeef's picture
Upload folder using huggingface_hub
8b4ca17 verified
{
"architectures": [
"Olmo3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 100257,
"dtype": "bfloat16",
"eos_token_id": 100257,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 11008,
"layer_types": [
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention"
],
"max_position_embeddings": 65536,
"model_type": "olmo3",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"pad_token_id": 100277,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"attention_factor": 1.2079441541679836,
"beta_fast": 32,
"beta_slow": 1,
"factor": 8.0,
"original_max_position_embeddings": 8192,
"rope_theta": 500000,
"rope_type": "yarn"
},
"sliding_window": 4096,
"tie_word_embeddings": false,
"transformers_version": "5.2.0",
"unsloth_fixed": true,
"unsloth_version": "2026.1.4",
"use_cache": false,
"vocab_size": 100278,
"quantization_config": {
"config_groups": {
"group_0": {
"input_activations": {
"dynamic": false,
"num_bits": 4,
"type": "float",
"group_size": 16
},
"weights": {
"dynamic": false,
"num_bits": 4,
"type": "float",
"group_size": 16
},
"targets": [
"Linear"
]
}
},
"ignore": [
"lm_head"
],
"quant_algo": "NVFP4",
"kv_cache_scheme": {
"dynamic": false,
"num_bits": 8,
"type": "float"
},
"producer": {
"name": "modelopt",
"version": "0.0.1.dev1+g5cc2a5451.d20260228"
},
"quant_method": "modelopt"
}
}