{
  "schema_version": 1,
  "_comment": "LFM2.5-230M @ MAXCTX=512, W8 weight-only (int8 weights, fp16 activations) + GQA-native decode + batched prefill (PN=512) + NPU lm-head. 14-layer hybrid = 8 short-conv + 6 GQA-attention; per-layer schedule via attn_idx/conv_idx (the op defaults to the 16-layer 350M when absent).",
  "model": {
    "name": "lfm2-5-230m",
    "family": "llm",
    "dsp_arch": "v75"
  },
  "params": {
    "hidden": 1024,
    "vocab": 65536,
    "n_layers": 14,
    "max_ctx": 512,
    "kv_dim": 512,
    "head_dim": 64,
    "rope_theta": 1000000.0,
    "eos_token_id": 7
  },
  "artifacts": {
    "contexts": {
      "decode": {
        "bin": "lfm230_dec_512_w8.bin"
      },
      "prefill": {
        "bin": "lfm230_pf_512_w8.bin"
      },
      "lmhead": {
        "bin": "lfm230_lmh_w8.bin"
      }
    },
    "embed": "lfm_embed_f16.bin",
    "tokenizer": "tokenizer.json"
  },
  "plan": {
    "steps": [
      {
        "host": "lfm_generate",
        "params": {
          "prefill": "lfm230_pf_512_w8",
          "decode": "lfm230_dec_512_w8",
          "lmhead": "lfm230_lmh_w8",
          "attn_idx": "2,4,6,8,10,12",
          "conv_idx": "0,1,3,5,7,9,11,13"
        }
      },
      {
        "emit": "all"
      }
    ]
  },
  "chat": {
    "bos": [
      1
    ],
    "system": {
      "prefix": "<|im_start|>system\n",
      "suffix": "<|im_end|>\n"
    },
    "user": {
      "prefix": "<|im_start|>user\n",
      "suffix": "<|im_end|>\n"
    },
    "assistant": {
      "prefix": "<|im_start|>assistant\n",
      "suffix": "<|im_end|>\n"
    }
  }
}