29 lines
904 B
JSON
29 lines
904 B
JSON
|
{
|
||
|
|
"model_type": "rna_llm",
|
||
|
|
"text_model_name": "Qwen/Qwen3-1.7B",
|
||
|
|
"chat_template_family": "qwen",
|
||
|
|
"rna_embed_dim": 2048,
|
||
|
|
"max_rna_seq_len": 1,
|
||
|
|
"max_length_text": 4096,
|
||
|
|
"lora_rank": 32,
|
||
|
|
"lora_alpha": 64,
|
||
|
|
"lora_dropout": 0.05,
|
||
|
|
"source_checkpoint": "/n/holylfs06/LABS/mzitnik_lab/Lab/lfesser/evo_tfm/hf_upload_models/Qwen3-1.7B-RNA-SFT-paper-e5-val_loss-0.5394.ckpt",
|
||
|
|
"epoch": 2,
|
||
|
|
"global_step": 515,
|
||
|
|
"hyper_parameters": {
|
||
|
|
"text_model_name": "Qwen/Qwen3-1.7B",
|
||
|
|
"rna_embed_dim": 2048,
|
||
|
|
"lora_rank": 32,
|
||
|
|
"lora_alpha": 64,
|
||
|
|
"lora_dropout": 0.05,
|
||
|
|
"max_length_text": 4096,
|
||
|
|
"chat_template_family": "qwen"
|
||
|
|
},
|
||
|
|
"special_tokens": [
|
||
|
|
"<|rna_start|>",
|
||
|
|
"<|rna_pad|>",
|
||
|
|
"<|rna_end|>"
|
||
|
|
],
|
||
|
|
"notes": "RNA embeddings are precomputed offline (TranscriptFormer, 2048-d) and projected via rna_projection.pt. Use the evo_tfm/rna_models inference code to load."
|
||
|
|
}
|