reorg: remove superseded path svd-llm-13b/

svd-llm-13b/README.md

@@ -1,29 +0,0 @@
----
-license: llama2
-base_model: NousResearch/Llama-2-13b-chat-hf
-tags: [svd, low-rank, model-compression, llama2, knowledge-distillation]
----
-
-# SVD-LLM @ 7.74B (59.47% kept of LLaMA-2-13B-chat), KD-healed 60M tokens
-
-SVD-LLM (ICLR 2025): truncation-aware data whitening + closed-form parameter update, official code (@ 7538cca), uniform 41.58% removal across all 7 projection types of all 40 layers.
-
-- **HEALED checkpoint** (this dir). The matching **UNHEALED** pre-distillation weights are in
-  `svd-llm-13b-unhealed/` — do not mix them up: same `ranks.json`, different `state_dict_fp16.pt` (see
-  `provenance.json` SHA256 here vs the unhealed dir's record).
-- Healing: pure forward-KL distillation from frozen NousResearch/Llama-2-13b-chat-hf teacher,
-  60M tokens, held-out KL **2.0904 -> 0.3007**, probe MMLU (5-shot, limit 40) **24.56% -> 46.54%**.
-- Identical recipe/protocol to the TR-3 13B and the 7B SVD baselines (see their dirs).
-
-## Load
-
-```python
-import json
-from lowrank_linear import build, materialize_all
-model = build("NousResearch/Llama-2-13b-chat-hf", json.load(open("ranks.json")),
-              "state_dict_fp16.pt", device="cuda")
-materialize_all(model)   # inference-only fusion U@V
-```
-
-Full provenance (data mixture + revisions, decontamination, SHA256 of every input and
-checkpoint, 12 x 5M milestone trajectory) in `provenance.json`.

svd-llm-13b/config.json

@@ -1,26 +0,0 @@
-{
-  "_name_or_path": null,
-  "architectures": [
-    "LlamaForCausalLM"
-  ],
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "hidden_act": "silu",
-  "hidden_size": 5120,
-  "initializer_range": 0.02,
-  "intermediate_size": 13824,
-  "max_position_embeddings": 4096,
-  "model_type": "llama",
-  "num_attention_heads": 40,
-  "num_hidden_layers": 40,
-  "num_key_value_heads": 40,
-  "pad_token_id": 0,
-  "pretraining_tp": 1,
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": null,
-  "tie_word_embeddings": false,
-  "torch_dtype": "float16",
-  "transformers_version": "4.31.0.dev0",
-  "use_cache": true,
-  "vocab_size": 32000
-}

svd-llm-13b/lowrank_linear.py

@@ -1,83 +0,0 @@
-"""Minimal standalone loader for the SVD-baseline compressed LLaMA-2-7B checkpoints.
-
-No dependency beyond torch + transformers. The state_dict stores every compressed
-projection as two factors of a LowRankLinear (A: out x k, B: k x in); ranks.json
-holds the per-layer integer rank of each projection. Untouched parameters
-(embeddings, norms) keep their stock transformers names.
-
-Usage:
-    import json, torch
-    from lowrank_linear import build
-    model = build(
-        base_id="NousResearch/Llama-2-7b-chat-hf",
-        ranks=json.load(open("ranks.json")),
-        state_dict_path="state_dict_fp16.pt",
-        device="cuda", dtype=torch.float16,
-    )
-    tokenizer = AutoTokenizer.from_pretrained("NousResearch/Llama-2-7b-chat-hf")
-    out = model.generate(tokenizer("2+2=", return_tensors="pt").to("cuda").input_ids,
-                         max_new_tokens=16, do_sample=False)
-    print(tokenizer.decode(out[0]))
-"""
-
-from __future__ import annotations
-
-import torch
-import torch.nn as nn
-import torch.nn.functional as F
-
-
-class LowRankLinear(nn.Module):
-    """y = A (B x).  A: out x r, B: r x in.  (LLaMA projections carry no bias.)"""
-
-    def __init__(self, A: torch.Tensor, B: torch.Tensor):
-        super().__init__()
-        self.A = nn.Parameter(A)
-        self.B = nn.Parameter(B)
-
-    def forward(self, x):
-        return F.linear(F.linear(x, self.B), self.A)
-
-    @torch.no_grad()
-    def materialize_(self) -> nn.Linear:
-        """Replace this module with the dense W = A @ B (inference only; never call
-        while training -- it cuts the gradient path)."""
-        W = (self.A @ self.B).to(self.A.dtype)
-        dense = nn.Linear(self.B.shape[1], self.A.shape[0], bias=False,
-                          device=W.device, dtype=W.dtype)
-        dense.weight.data = W
-        return dense
-
-
-def build(base_id: str, ranks: dict, state_dict_path: str,
-          device: str = "cuda", dtype=torch.float16):
-    from transformers import AutoModelForCausalLM
-
-    model = AutoModelForCausalLM.from_pretrained(base_id, torch_dtype=dtype)
-    search = {}
-    for name, mod in model.named_modules():
-        if isinstance(mod, nn.Linear):
-            search[name] = mod
-    for path, k in ranks.items():
-        out_f, in_f = search[path].weight.shape
-        model_mod = model
-        for p in path.split(".")[:-1]:
-            model_mod = getattr(model_mod, p)
-        setattr(model_mod, path.split(".")[-1],
-                LowRankLinear(torch.zeros(out_f, int(k), dtype=dtype),
-                              torch.zeros(int(k), in_f, dtype=dtype)))
-    sd = torch.load(state_dict_path, map_location="cpu", weights_only=True)
-    model.load_state_dict(sd, strict=True)
-    del sd
-    return model.to(device)
-
-
-def materialize_all(model):
-    """Fuse every LowRankLinear back into a dense nn.Linear in place."""
-    for name, mod in list(model.named_modules()):
-        if isinstance(mod, LowRankLinear):
-            parent = model
-            for p in name.split(".")[:-1]:
-                parent = getattr(parent, p)
-            setattr(parent, name.split(".")[-1], mod.materialize_())
-    return model

svd-llm-13b/provenance.json

@@ -1,199 +0,0 @@
-{
-  "method": "KD healing: alpha*T^2*KL(teacher||student) + (1-alpha)*CE",
-  "student_init": "/data1/rkp00022/zixuan/projects/TR3_main/checkpoints/svdllm1_r04158_tr3fmt/state_dict_fp16.pt",
-  "teacher": "NousResearch/Llama-2-13b-chat-hf",
-  "alpha": 1.0,
-  "temperature": 1.0,
-  "lr": 2e-05,
-  "tokens_seen": 59998208,
-  "epochs": 0.228,
-  "global_batch_tokens": 32768,
-  "dataset_mixture_pre_exclusion": {
-    "alpaca": 50000,
-    "openhermes": 200000,
-    "ultrachat": 100000
-  },
-  "dataset_revisions": {
-    "tatsu-lab/alpaca": "dce01c9b08f87459cf36a430d809084718273017",
-    "teknium/OpenHermes-2.5": "b82037821055c377bed0d495e72e46de3bc72e84",
-    "HuggingFaceH4/ultrachat_200k": "8049631c405ae6576f93f445c6b8166f76f5505a"
-  },
-  "canonical_pool_excluded_texts": 10000,
-  "train_texts_after_exclusion": 356000,
-  "chat_texts": 340000,
-  "mmlu_aux_texts_kept": 16000,
-  "mmlu_aux_split": "cais/mmlu auxiliary_train (official TRAIN split, disjoint from the evaluated test split; audit verified 0/99842 exact overlap)",
-  "mmlu_aux_stats": {
-    "requested_groups": 16000,
-    "rendered_groups": 16000,
-    "shots": 5,
-    "rows_total": 99842,
-    "rows_dropped_by_decontam": 71,
-    "rows_clean": 99771,
-    "revision": "c30699e8356da336a370243923dbaf21066bb9fe",
-    "format": "MMLU-shaped (NOT byte-identical to lm-eval; auxiliary_train has no subject)"
-  },
-  "gold_label_supervision": false,
-  "attribution_note": "alpha=1.0 => pure KD, no gold-label CE, so any MMLU change is attributable to distillation on in-domain text. alpha<1 adds CE on text containing answers = labeled MCQ training, which is a DIFFERENT and weaker claim.",
-  "train_tokens_total": 263112704,
-  "decontamination": {
-    "removed": {
-      "alpaca": 11,
-      "openhermes": 120,
-      "ultrachat": 33
-    }
-  },
-  "start_kl": 2.0904040336608887,
-  "final_kl": 0.30065654776990414,
-  "start_mmlu": 0.24561403508771928,
-  "final_mmlu": 0.46535087719298246,
-  "history": [
-    {
-      "tokens_m": 5.01,
-      "step": 153,
-      "held_out_kl": 0.5967434793710709,
-      "mmlu": 0.3929824561403509
-    },
-    {
-      "tokens_m": 10.03,
-      "step": 306,
-      "held_out_kl": 0.5406020767986774,
-      "mmlu": 0.3956140350877193
-    },
-    {
-      "tokens_m": 15.01,
-      "step": 458,
-      "held_out_kl": 0.5206542909145355,
-      "mmlu": 0.4083333333333333
-    },
-    {
-      "tokens_m": 20.02,
-      "step": 611,
-      "held_out_kl": 0.4988052695989609,
-      "mmlu": 0.40087719298245617
-    },
-    {
-      "tokens_m": 25.0,
-      "step": 763,
-      "held_out_kl": 0.4575178399682045,
-      "mmlu": 0.40350877192982454
-    },
-    {
-      "tokens_m": 30.02,
-      "step": 916,
-      "held_out_kl": 0.4198819752782583,
-      "mmlu": 0.4298245614035088
-    },
-    {
-      "tokens_m": 35.03,
-      "step": 1069,
-      "held_out_kl": 0.38331497088074684,
-      "mmlu": 0.43157894736842106
-    },
-    {
-      "tokens_m": 40.01,
-      "step": 1221,
-      "held_out_kl": 0.34914770163595676,
-      "mmlu": 0.4425438596491228
-    },
-    {
-      "tokens_m": 45.02,
-      "step": 1374,
-      "held_out_kl": 0.32529739663004875,
-      "mmlu": 0.44956140350877194
-    },
-    {
-      "tokens_m": 50.0,
-      "step": 1526,
-      "held_out_kl": 0.31298027001321316,
-      "mmlu": 0.4587719298245614
-    },
-    {
-      "tokens_m": 55.02,
-      "step": 1679,
-      "held_out_kl": 0.30493565648794174,
-      "mmlu": 0.46403508771929824
-    },
-    {
-      "tokens_m": 60.0,
-      "step": 1831,
-      "held_out_kl": 0.30065654776990414,
-      "mmlu": 0.46535087719298246,
-      "final": true
-    }
-  ],
-  "teacher_mmlu_same_limit": 0.5442982456140351,
-  "checkpoint": "/data1/rkp00022/zixuan/projects/TR3_main/checkpoints/kdheal_svdllm1r04158_h1/state_dict_fp16.pt",
-  "sha256": "42b2f5c959e8fdd07ef526e6d182cab2f7685354859e1262b035eef39ba98387",
-  "seed": 1234,
-  "mmlu_limit_per_subtask": 40,
-  "teacher_revision": "d73f5fa9c4bc135502e04c27b39660747172d76b",
-  "student_init_sha256": "5625041bed874f21664b6a2bff3ce4722612302630028c9b60ac7f2cb8d7c605",
-  "ranks_file": "/data1/rkp00022/zixuan/projects/TR3_main/checkpoints/svdllm1_r04158_tr3fmt/ranks.json",
-  "ranks_sha256": "5c9ed0db91c9c81c51e62e6f82c7c2772478cc353c6f28040164843e64219b55",
-  "input_identity_gate": {
-    "student_ckpt": {
-      "key": "svdllm1_r04158_tr3fmt",
-      "sha256": "5625041bed874f21664b6a2bff3ce4722612302630028c9b60ac7f2cb8d7c605",
-      "status": "unregistered_allowed"
-    },
-    "ranks": {
-      "key": "svdllm1_r04158_tr3fmt",
-      "sha256": "5c9ed0db91c9c81c51e62e6f82c7c2772478cc353c6f28040164843e64219b55",
-      "status": "unregistered_allowed"
-    }
-  },
-  "train_seed": 1234,
-  "mmlu_seed": 1234,
-  "dynamic_batch": false,
-  "dbl": null,
-  "snapshot_milestones": true,
-  "snapshots": [
-    "(PosixPath('/data1/rkp00022/zixuan/projects/TR3_main/checkpoints/kdheal_svdllm1r04158_h1_snap15m'), 15.007744)",
-    "(PosixPath('/data1/rkp00022/zixuan/projects/TR3_main/checkpoints/kdheal_svdllm1r04158_h1_snap30m'), 30.015488)",
-    "(PosixPath('/data1/rkp00022/zixuan/projects/TR3_main/checkpoints/kdheal_svdllm1r04158_h1_snap45m'), 45.023232)",
-    "(PosixPath('/data1/rkp00022/zixuan/projects/TR3_main/checkpoints/kdheal_svdllm1r04158_h1_snap50m'), 50.003968)",
-    "(PosixPath('/data1/rkp00022/zixuan/projects/TR3_main/checkpoints/kdheal_svdllm1r04158_h1_snap55m'), 55.017472)"
-  ],
-  "stream_skip_tokens_m": 0.0,
-  "stream_blocks_consumed": [
-    0,
-    58592
-  ],
-  "stream_note": "the block order is a seeded permutation consumed from index 0; stages sharing a --seed with stream_skip=0 re-train on the SAME blocks. [start, end] block indices are recorded so any continuation can be checked for overlap with what earlier stages consumed.",
-  "student_master_dtype": "bf16",
-  "fake_quant": null,
-  "rebalance_report": null,
-  "student_param_count": 7737799680,
-  "micro": 8,
-  "grad_accum": 4,
-  "seq_len": 1024,
-  "held_out_source": "canonical: mixture 2000/4000/4000, seed 1234, seq 1024, blocks 256:264 (identical to the compression gates)",
-  "decontam_stats": {
-    "mmlu": {
-      "items": 14042,
-      "new_ngrams": 764261,
-      "revision": "c30699e8356da336a370243923dbaf21066bb9fe"
-    },
-    "hellaswag": {
-      "items": 10042,
-      "new_ngrams": 1334302,
-      "revision": "218ec52e09a7e7462a5400043bb9a69a41d06b76"
-    },
-    "boolq": {
-      "items": 3270,
-      "new_ngrams": 276806,
-      "revision": "3de24cf8022e94f4ee4b9d55a6f539891524d646"
-    },
-    "triviaqa": {
-      "items": 17944,
-      "new_ngrams": 32608,
-      "revision": "0f7faf33a3908546c6fd5b73a660e0f8ff173c2f"
-    },
-    "gsm8k": {
-      "items": 1319,
-      "new_ngrams": 46281,
-      "revision": "740312add88f781978c0658806c59bc2815b9866"
-    }
-  }
-}

svd-llm-13b/ranks.json

@@ -1,282 +0,0 @@
-{
- "model.layers.0.self_attn.q_proj": 1495,
- "model.layers.0.self_attn.k_proj": 1495,
- "model.layers.0.self_attn.v_proj": 1495,
- "model.layers.0.self_attn.o_proj": 1495,
- "model.layers.0.mlp.gate_proj": 2182,
- "model.layers.0.mlp.up_proj": 2182,
- "model.layers.0.mlp.down_proj": 2182,
- "model.layers.1.self_attn.q_proj": 1495,
- "model.layers.1.self_attn.k_proj": 1495,
- "model.layers.1.self_attn.v_proj": 1495,
- "model.layers.1.self_attn.o_proj": 1495,
- "model.layers.1.mlp.gate_proj": 2182,
- "model.layers.1.mlp.up_proj": 2182,
- "model.layers.1.mlp.down_proj": 2182,
- "model.layers.2.self_attn.q_proj": 1495,
- "model.layers.2.self_attn.k_proj": 1495,
- "model.layers.2.self_attn.v_proj": 1495,
- "model.layers.2.self_attn.o_proj": 1495,
- "model.layers.2.mlp.gate_proj": 2182,
- "model.layers.2.mlp.up_proj": 2182,
- "model.layers.2.mlp.down_proj": 2182,
- "model.layers.3.self_attn.q_proj": 1495,
- "model.layers.3.self_attn.k_proj": 1495,
- "model.layers.3.self_attn.v_proj": 1495,
- "model.layers.3.self_attn.o_proj": 1495,
- "model.layers.3.mlp.gate_proj": 2182,
- "model.layers.3.mlp.up_proj": 2182,
- "model.layers.3.mlp.down_proj": 2182,
- "model.layers.4.self_attn.q_proj": 1495,
- "model.layers.4.self_attn.k_proj": 1495,
- "model.layers.4.self_attn.v_proj": 1495,
- "model.layers.4.self_attn.o_proj": 1495,
- "model.layers.4.mlp.gate_proj": 2182,
- "model.layers.4.mlp.up_proj": 2182,
- "model.layers.4.mlp.down_proj": 2182,
- "model.layers.5.self_attn.q_proj": 1495,
- "model.layers.5.self_attn.k_proj": 1495,
- "model.layers.5.self_attn.v_proj": 1495,
- "model.layers.5.self_attn.o_proj": 1495,
- "model.layers.5.mlp.gate_proj": 2182,
- "model.layers.5.mlp.up_proj": 2182,
- "model.layers.5.mlp.down_proj": 2182,
- "model.layers.6.self_attn.q_proj": 1495,
- "model.layers.6.self_attn.k_proj": 1495,
- "model.layers.6.self_attn.v_proj": 1495,
- "model.layers.6.self_attn.o_proj": 1495,
- "model.layers.6.mlp.gate_proj": 2182,
- "model.layers.6.mlp.up_proj": 2182,
- "model.layers.6.mlp.down_proj": 2182,
- "model.layers.7.self_attn.q_proj": 1495,
- "model.layers.7.self_attn.k_proj": 1495,
- "model.layers.7.self_attn.v_proj": 1495,
- "model.layers.7.self_attn.o_proj": 1495,
- "model.layers.7.mlp.gate_proj": 2182,
- "model.layers.7.mlp.up_proj": 2182,
- "model.layers.7.mlp.down_proj": 2182,
- "model.layers.8.self_attn.q_proj": 1495,
- "model.layers.8.self_attn.k_proj": 1495,
- "model.layers.8.self_attn.v_proj": 1495,
- "model.layers.8.self_attn.o_proj": 1495,
- "model.layers.8.mlp.gate_proj": 2182,
- "model.layers.8.mlp.up_proj": 2182,
- "model.layers.8.mlp.down_proj": 2182,
- "model.layers.9.self_attn.q_proj": 1495,
- "model.layers.9.self_attn.k_proj": 1495,
- "model.layers.9.self_attn.v_proj": 1495,
- "model.layers.9.self_attn.o_proj": 1495,
- "model.layers.9.mlp.gate_proj": 2182,
- "model.layers.9.mlp.up_proj": 2182,
- "model.layers.9.mlp.down_proj": 2182,
- "model.layers.10.self_attn.q_proj": 1495,
- "model.layers.10.self_attn.k_proj": 1495,
- "model.layers.10.self_attn.v_proj": 1495,
- "model.layers.10.self_attn.o_proj": 1495,
- "model.layers.10.mlp.gate_proj": 2182,
- "model.layers.10.mlp.up_proj": 2182,
- "model.layers.10.mlp.down_proj": 2182,
- "model.layers.11.self_attn.q_proj": 1495,
- "model.layers.11.self_attn.k_proj": 1495,
- "model.layers.11.self_attn.v_proj": 1495,
- "model.layers.11.self_attn.o_proj": 1495,
- "model.layers.11.mlp.gate_proj": 2182,
- "model.layers.11.mlp.up_proj": 2182,
- "model.layers.11.mlp.down_proj": 2182,
- "model.layers.12.self_attn.q_proj": 1495,
- "model.layers.12.self_attn.k_proj": 1495,
- "model.layers.12.self_attn.v_proj": 1495,
- "model.layers.12.self_attn.o_proj": 1495,
- "model.layers.12.mlp.gate_proj": 2182,
- "model.layers.12.mlp.up_proj": 2182,
- "model.layers.12.mlp.down_proj": 2182,
- "model.layers.13.self_attn.q_proj": 1495,
- "model.layers.13.self_attn.k_proj": 1495,
- "model.layers.13.self_attn.v_proj": 1495,
- "model.layers.13.self_attn.o_proj": 1495,
- "model.layers.13.mlp.gate_proj": 2182,
- "model.layers.13.mlp.up_proj": 2182,
- "model.layers.13.mlp.down_proj": 2182,
- "model.layers.14.self_attn.q_proj": 1495,
- "model.layers.14.self_attn.k_proj": 1495,
- "model.layers.14.self_attn.v_proj": 1495,
- "model.layers.14.self_attn.o_proj": 1495,
- "model.layers.14.mlp.gate_proj": 2182,
- "model.layers.14.mlp.up_proj": 2182,
- "model.layers.14.mlp.down_proj": 2182,
- "model.layers.15.self_attn.q_proj": 1495,
- "model.layers.15.self_attn.k_proj": 1495,
- "model.layers.15.self_attn.v_proj": 1495,
- "model.layers.15.self_attn.o_proj": 1495,
- "model.layers.15.mlp.gate_proj": 2182,
- "model.layers.15.mlp.up_proj": 2182,
- "model.layers.15.mlp.down_proj": 2182,
- "model.layers.16.self_attn.q_proj": 1495,
- "model.layers.16.self_attn.k_proj": 1495,
- "model.layers.16.self_attn.v_proj": 1495,
- "model.layers.16.self_attn.o_proj": 1495,
- "model.layers.16.mlp.gate_proj": 2182,
- "model.layers.16.mlp.up_proj": 2182,
- "model.layers.16.mlp.down_proj": 2182,
- "model.layers.17.self_attn.q_proj": 1495,
- "model.layers.17.self_attn.k_proj": 1495,
- "model.layers.17.self_attn.v_proj": 1495,
- "model.layers.17.self_attn.o_proj": 1495,
- "model.layers.17.mlp.gate_proj": 2182,
- "model.layers.17.mlp.up_proj": 2182,
- "model.layers.17.mlp.down_proj": 2182,
- "model.layers.18.self_attn.q_proj": 1495,
- "model.layers.18.self_attn.k_proj": 1495,
- "model.layers.18.self_attn.v_proj": 1495,
- "model.layers.18.self_attn.o_proj": 1495,
- "model.layers.18.mlp.gate_proj": 2182,
- "model.layers.18.mlp.up_proj": 2182,
- "model.layers.18.mlp.down_proj": 2182,
- "model.layers.19.self_attn.q_proj": 1495,
- "model.layers.19.self_attn.k_proj": 1495,
- "model.layers.19.self_attn.v_proj": 1495,
- "model.layers.19.self_attn.o_proj": 1495,
- "model.layers.19.mlp.gate_proj": 2182,
- "model.layers.19.mlp.up_proj": 2182,
- "model.layers.19.mlp.down_proj": 2182,
- "model.layers.20.self_attn.q_proj": 1495,
- "model.layers.20.self_attn.k_proj": 1495,
- "model.layers.20.self_attn.v_proj": 1495,
- "model.layers.20.self_attn.o_proj": 1495,
- "model.layers.20.mlp.gate_proj": 2182,
- "model.layers.20.mlp.up_proj": 2182,
- "model.layers.20.mlp.down_proj": 2182,
- "model.layers.21.self_attn.q_proj": 1495,
- "model.layers.21.self_attn.k_proj": 1495,
- "model.layers.21.self_attn.v_proj": 1495,
- "model.layers.21.self_attn.o_proj": 1495,
- "model.layers.21.mlp.gate_proj": 2182,
- "model.layers.21.mlp.up_proj": 2182,
- "model.layers.21.mlp.down_proj": 2182,
- "model.layers.22.self_attn.q_proj": 1495,
- "model.layers.22.self_attn.k_proj": 1495,
- "model.layers.22.self_attn.v_proj": 1495,
- "model.layers.22.self_attn.o_proj": 1495,
- "model.layers.22.mlp.gate_proj": 2182,
- "model.layers.22.mlp.up_proj": 2182,
- "model.layers.22.mlp.down_proj": 2182,
- "model.layers.23.self_attn.q_proj": 1495,
- "model.layers.23.self_attn.k_proj": 1495,
- "model.layers.23.self_attn.v_proj": 1495,
- "model.layers.23.self_attn.o_proj": 1495,
- "model.layers.23.mlp.gate_proj": 2182,
- "model.layers.23.mlp.up_proj": 2182,
- "model.layers.23.mlp.down_proj": 2182,
- "model.layers.24.self_attn.q_proj": 1495,
- "model.layers.24.self_attn.k_proj": 1495,
- "model.layers.24.self_attn.v_proj": 1495,
- "model.layers.24.self_attn.o_proj": 1495,
- "model.layers.24.mlp.gate_proj": 2182,
- "model.layers.24.mlp.up_proj": 2182,
- "model.layers.24.mlp.down_proj": 2182,
- "model.layers.25.self_attn.q_proj": 1495,
- "model.layers.25.self_attn.k_proj": 1495,
- "model.layers.25.self_attn.v_proj": 1495,
- "model.layers.25.self_attn.o_proj": 1495,
- "model.layers.25.mlp.gate_proj": 2182,
- "model.layers.25.mlp.up_proj": 2182,
- "model.layers.25.mlp.down_proj": 2182,
- "model.layers.26.self_attn.q_proj": 1495,
- "model.layers.26.self_attn.k_proj": 1495,
- "model.layers.26.self_attn.v_proj": 1495,
- "model.layers.26.self_attn.o_proj": 1495,
- "model.layers.26.mlp.gate_proj": 2182,
- "model.layers.26.mlp.up_proj": 2182,
- "model.layers.26.mlp.down_proj": 2182,
- "model.layers.27.self_attn.q_proj": 1495,
- "model.layers.27.self_attn.k_proj": 1495,
- "model.layers.27.self_attn.v_proj": 1495,
- "model.layers.27.self_attn.o_proj": 1495,
- "model.layers.27.mlp.gate_proj": 2182,
- "model.layers.27.mlp.up_proj": 2182,
- "model.layers.27.mlp.down_proj": 2182,
- "model.layers.28.self_attn.q_proj": 1495,
- "model.layers.28.self_attn.k_proj": 1495,
- "model.layers.28.self_attn.v_proj": 1495,
- "model.layers.28.self_attn.o_proj": 1495,
- "model.layers.28.mlp.gate_proj": 2182,
- "model.layers.28.mlp.up_proj": 2182,
- "model.layers.28.mlp.down_proj": 2182,
- "model.layers.29.self_attn.q_proj": 1495,
- "model.layers.29.self_attn.k_proj": 1495,
- "model.layers.29.self_attn.v_proj": 1495,
- "model.layers.29.self_attn.o_proj": 1495,
- "model.layers.29.mlp.gate_proj": 2182,
- "model.layers.29.mlp.up_proj": 2182,
- "model.layers.29.mlp.down_proj": 2182,
- "model.layers.30.self_attn.q_proj": 1495,
- "model.layers.30.self_attn.k_proj": 1495,
- "model.layers.30.self_attn.v_proj": 1495,
- "model.layers.30.self_attn.o_proj": 1495,
- "model.layers.30.mlp.gate_proj": 2182,
- "model.layers.30.mlp.up_proj": 2182,
- "model.layers.30.mlp.down_proj": 2182,
- "model.layers.31.self_attn.q_proj": 1495,
- "model.layers.31.self_attn.k_proj": 1495,
- "model.layers.31.self_attn.v_proj": 1495,
- "model.layers.31.self_attn.o_proj": 1495,
- "model.layers.31.mlp.gate_proj": 2182,
- "model.layers.31.mlp.up_proj": 2182,
- "model.layers.31.mlp.down_proj": 2182,
- "model.layers.32.self_attn.q_proj": 1495,
- "model.layers.32.self_attn.k_proj": 1495,
- "model.layers.32.self_attn.v_proj": 1495,
- "model.layers.32.self_attn.o_proj": 1495,
- "model.layers.32.mlp.gate_proj": 2182,
- "model.layers.32.mlp.up_proj": 2182,
- "model.layers.32.mlp.down_proj": 2182,
- "model.layers.33.self_attn.q_proj": 1495,
- "model.layers.33.self_attn.k_proj": 1495,
- "model.layers.33.self_attn.v_proj": 1495,
- "model.layers.33.self_attn.o_proj": 1495,
- "model.layers.33.mlp.gate_proj": 2182,
- "model.layers.33.mlp.up_proj": 2182,
- "model.layers.33.mlp.down_proj": 2182,
- "model.layers.34.self_attn.q_proj": 1495,
- "model.layers.34.self_attn.k_proj": 1495,
- "model.layers.34.self_attn.v_proj": 1495,
- "model.layers.34.self_attn.o_proj": 1495,
- "model.layers.34.mlp.gate_proj": 2182,
- "model.layers.34.mlp.up_proj": 2182,
- "model.layers.34.mlp.down_proj": 2182,
- "model.layers.35.self_attn.q_proj": 1495,
- "model.layers.35.self_attn.k_proj": 1495,
- "model.layers.35.self_attn.v_proj": 1495,
- "model.layers.35.self_attn.o_proj": 1495,
- "model.layers.35.mlp.gate_proj": 2182,
- "model.layers.35.mlp.up_proj": 2182,
- "model.layers.35.mlp.down_proj": 2182,
- "model.layers.36.self_attn.q_proj": 1495,
- "model.layers.36.self_attn.k_proj": 1495,
- "model.layers.36.self_attn.v_proj": 1495,
- "model.layers.36.self_attn.o_proj": 1495,
- "model.layers.36.mlp.gate_proj": 2182,
- "model.layers.36.mlp.up_proj": 2182,
- "model.layers.36.mlp.down_proj": 2182,
- "model.layers.37.self_attn.q_proj": 1495,
- "model.layers.37.self_attn.k_proj": 1495,
- "model.layers.37.self_attn.v_proj": 1495,
- "model.layers.37.self_attn.o_proj": 1495,
- "model.layers.37.mlp.gate_proj": 2182,
- "model.layers.37.mlp.up_proj": 2182,
- "model.layers.37.mlp.down_proj": 2182,
- "model.layers.38.self_attn.q_proj": 1495,
- "model.layers.38.self_attn.k_proj": 1495,
- "model.layers.38.self_attn.v_proj": 1495,
- "model.layers.38.self_attn.o_proj": 1495,
- "model.layers.38.mlp.gate_proj": 2182,
- "model.layers.38.mlp.up_proj": 2182,
- "model.layers.38.mlp.down_proj": 2182,
- "model.layers.39.self_attn.q_proj": 1495,
- "model.layers.39.self_attn.k_proj": 1495,
- "model.layers.39.self_attn.v_proj": 1495,
- "model.layers.39.self_attn.o_proj": 1495,
- "model.layers.39.mlp.gate_proj": 2182,
- "model.layers.39.mlp.up_proj": 2182,
- "model.layers.39.mlp.down_proj": 2182
-}

svd-llm-13b/state_dict_fp16.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:42b2f5c959e8fdd07ef526e6d182cab2f7685354859e1262b035eef39ba98387
-size 15475814672