{ "model": "/media/m2teamgroup/models/UserRepGen-4B-GGUF/UserRepGen-4B-bf16.gguf", "imatrix": "/media/m2teamgroup/models/UserRepGen-4B-GGUF/UserRepGen-4B-imatrix.gguf", "ftype": "Q2_K", "base_type": "q2_k", "family": "k", "recipe": "ident", "variant": "shr0.70", "auto_crush": false, "rung_mode": "share", "tier": "M", "rung_share": 0.7, "crush_pass_bytes": null, "embd_shares": { "token_embd.weight": { "share": 0.2541, "type": "q4_k" } }, "arch": "hybrid", "tied": true, "n_layer": 32, "body_rule": true, "pins": { "^blk\\.0\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.0\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.1\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.1\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.2\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.2\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.4\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.4\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.5\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.5\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.6\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.6\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.8\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.8\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.9\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.9\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.10\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.10\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.12\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.12\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.13\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.13\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.14\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.14\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.16\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.16\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.17\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.17\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.18\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.18\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.20\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.20\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.21\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.21\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.22\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.22\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.24\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.24\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.25\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.25\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.26\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.26\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.28\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.28\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.29\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.29\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.30\\.ssm_alpha\\.weight$": "tiny: 81,920 params, kept at f32", "^blk\\.30\\.ssm_beta\\.weight$": "tiny: 81,920 params, kept at f32" }, "shape_pins": {}, "fixed_pins": { "blk.0.ssm_alpha.weight": "f32", "blk.0.ssm_beta.weight": "f32", "blk.1.ssm_alpha.weight": "f32", "blk.1.ssm_beta.weight": "f32", "blk.2.ssm_alpha.weight": "f32", "blk.2.ssm_beta.weight": "f32", "blk.4.ssm_alpha.weight": "f32", "blk.4.ssm_beta.weight": "f32", "blk.5.ssm_alpha.weight": "f32", "blk.5.ssm_beta.weight": "f32", "blk.6.ssm_alpha.weight": "f32", "blk.6.ssm_beta.weight": "f32", "blk.8.ssm_alpha.weight": "f32", "blk.8.ssm_beta.weight": "f32", "blk.9.ssm_alpha.weight": "f32", "blk.9.ssm_beta.weight": "f32", "blk.10.ssm_alpha.weight": "f32", "blk.10.ssm_beta.weight": "f32", "blk.12.ssm_alpha.weight": "f32", "blk.12.ssm_beta.weight": "f32", "blk.13.ssm_alpha.weight": "f32", "blk.13.ssm_beta.weight": "f32", "blk.14.ssm_alpha.weight": "f32", "blk.14.ssm_beta.weight": "f32", "blk.16.ssm_alpha.weight": "f32", "blk.16.ssm_beta.weight": "f32", "blk.17.ssm_alpha.weight": "f32", "blk.17.ssm_beta.weight": "f32", "blk.18.ssm_alpha.weight": "f32", "blk.18.ssm_beta.weight": "f32", "blk.20.ssm_alpha.weight": "f32", "blk.20.ssm_beta.weight": "f32", "blk.21.ssm_alpha.weight": "f32", "blk.21.ssm_beta.weight": "f32", "blk.22.ssm_alpha.weight": "f32", "blk.22.ssm_beta.weight": "f32", "blk.24.ssm_alpha.weight": "f32", "blk.24.ssm_beta.weight": "f32", "blk.25.ssm_alpha.weight": "f32", "blk.25.ssm_beta.weight": "f32", "blk.26.ssm_alpha.weight": "f32", "blk.26.ssm_beta.weight": "f32", "blk.28.ssm_alpha.weight": "f32", "blk.28.ssm_beta.weight": "f32", "blk.29.ssm_alpha.weight": "f32", "blk.29.ssm_beta.weight": "f32", "blk.30.ssm_alpha.weight": "f32", "blk.30.ssm_beta.weight": "f32" }, "embeddings": { "token_embd.weight": "q4_k" }, "bytes": { "heuristic_body+embd": 2033059840, "map_body+embd": 1699266560, "ratio": 0.8358, "note": "quantizable, unpinned tensors only; pinned/unquantized tensors are identical in both" }, "body_base_share": 0.7, "body_bpw": 3.011, "body_bpw_heuristic": 3.392, "total_params": 4205751296, "file_bytes_pred": 1718841344, "file_bpw_pred": 3.27, "histogram": { "attn_gate": { "q2_k": 22, "q5_k": 1, "q4_k": 1 }, "attn_k": { "q4_k": 6, "q5_k": 2 }, "attn_output": { "q4_k": 7, "q5_k": 1 }, "attn_q": { "q2_k": 8 }, "attn_qkv": { "q2_k": 23, "q4_k": 1 }, "attn_v": { "q5_k": 8 }, "ffn_down": { "q2_k": 30, "q4_k": 2 }, "ffn_gate": { "q2_k": 31, "q4_k": 1 }, "ffn_up": { "q2_k": 23, "q4_k": 9 }, "ssm_out": { "q4_k": 23, "q5_k": 1 } }, "prior": "layout/prior.json", "pin_rule": "floor", "embd_cap": "heur", "generator": "auto_quant_v2.layout", "generator_key": "3bf8b43e20a68f0b", "quant_type": "Q2_K", "quantize_ftype": "Q2_K", "llama_cpp_version": "b11627", "unknown_kinds": {}, "commit": "2d948bec8623bf6a14e732adb3400ec09ebb5e20" }