{ "schema_version": 1, "model": { "name": "nv-embedqa-1b", "family": "embedding", "dsp_arch": "v81", "tokenizer_pre": "llama3" }, "params": { "hidden": 2048, "vocab": 128256, "n_layers": 16, "head_dim": 64, "max_ctx": 64, "eos_token_id": 128001 }, "artifacts": { "contexts": { "encoder": { "bin": "nvembedqa_enc.bin" } }, "embed": "nvembedqa_embed_f16.bin", "tokenizer": "tokenizer.json" }, "plan": { "steps": [ { "host": "llama_embed", "params": { "encoder": "nvembedqa_enc_f16", "rope_factor": 32.0, "neg": -50000 } } ] } }