| { | |
| "schema_version": 1, | |
| "model": { | |
| "name": "nv-embedcode-7b", | |
| "family": "embedding", | |
| "dsp_arch": "v81", | |
| "tokenizer_pre": "default" | |
| }, | |
| "params": { | |
| "hidden": 4096, | |
| "vocab": 32000, | |
| "n_layers": 32, | |
| "head_dim": 128, | |
| "max_ctx": 128, | |
| "eos_token_id": 2 | |
| }, | |
| "artifacts": { | |
| "contexts": { | |
| "enc_p0": { | |
| "bin": "nvembedcode7b_enc_p0_w8.bin" | |
| }, | |
| "enc_p1": { | |
| "bin": "nvembedcode7b_enc_p1_w8.bin" | |
| }, | |
| "enc_p2": { | |
| "bin": "nvembedcode7b_enc_p2_w8.bin" | |
| }, | |
| "enc_p3": { | |
| "bin": "nvembedcode7b_enc_p3_w8.bin" | |
| } | |
| }, | |
| "embed": "nvembedcode7b_embed_f16.bin", | |
| "tokenizer": "tokenizer.json" | |
| }, | |
| "plan": { | |
| "steps": [ | |
| { | |
| "host": "llama_embed_sharded", | |
| "params": { | |
| "encoder_parts": "nvembedcode7b_enc_p0_w8,nvembedcode7b_enc_p1_w8,nvembedcode7b_enc_p2_w8,nvembedcode7b_enc_p3_w8", | |
| "rope_factor": 1.0, | |
| "rope_theta": 10000.0, | |
| "neg": -50000 | |
| } | |
| } | |
| ] | |
| } | |
| } | |