sharpenb's picture
Upload folder using huggingface_hub (#1)
2839f12 verified
{
"_attn_implementation_autoset": true,
"_name_or_path": "/tmp/models/tmpnvyvihp2/tmpunxu8odp",
"architectures": [
"OlmoeForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"clip_qkv": null,
"eos_token_id": 50279,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 1024,
"max_position_embeddings": 4096,
"model_type": "olmoe",
"norm_topk_prob": false,
"num_attention_heads": 16,
"num_experts": 64,
"num_experts_per_tok": 8,
"num_hidden_layers": 16,
"num_key_value_heads": 16,
"output_router_logits": false,
"pad_token_id": 1,
"quantization_config": {
"quant_config": {
"offload_meta": false,
"scale_quant_params": null,
"weight_quant_params": {
"axis": 1,
"channel_wise": true,
"group_size": 64,
"nbits": 8,
"optimize": true,
"round_zero": false,
"view_as_float": false
},
"zero_quant_params": null
},
"quant_method": "hqq",
"skip_modules": [
"lm_head"
]
},
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"router_aux_loss_coef": 0.01,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.48.2",
"use_cache": true,
"vocab_size": 50304
}