reorg: remove superseded path svd-llm-13b-unhealed/

svd-llm-13b-unhealed/README.md

@@ -1,16 +0,0 @@
----
-license: llama2
-base_model: NousResearch/Llama-2-13b-chat-hf
-tags: [svd, low-rank, model-compression, llama2]
----
-
-# SVD-LLM @ 7.74B (59.47% kept of LLaMA-2-13B-chat), UNHEALED
-
-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.
-
-- **UNHEALED checkpoint**: raw post-training compression weights, NO distillation. The KD-healed
-  counterpart is in `svd-llm-13b/`. This dir exists so the healing delta is
-  measurable; use it as the compression-stage artifact, not as a deployable model.
-- Same `ranks.json` as the healed dir; weights differ (see `provenance.json` SHA256).
-
-Load exactly as in the sibling dir (`lowrank_linear.py`).

svd-llm-13b-unhealed/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-unhealed/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-unhealed/provenance.json

@@ -1,7 +0,0 @@
-{
- "kind": "unhealed SVD compression (TR3-format conversion, verified pure re-keying)",
- "source_ckpt": "/data1/rkp00022/zixuan/projects/TR3_main/checkpoints/svdllm1_llama2_13b_chat_r04158/NousResearch_Llama_2_13b_chat_hf_whitening_then_update_0.5842.pt",
- "converted_state_dict": "/data1/rkp00022/zixuan/projects/TR3_main/scratch/hf_push_13b/svd-llm-13b-unhealed/state_dict_fp16.pt",
- "state_dict_sha256": "5625041bed874f21664b6a2bff3ce4722612302630028c9b60ac7f2cb8d7c605",
- "healed_counterpart": "svd-llm-13b/state_dict_fp16.pt"
-}

svd-llm-13b-unhealed/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-unhealed/state_dict_fp16.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5625041bed874f21664b6a2bff3ce4722612302630028c9b60ac7f2cb8d7c605
-size 15475812809