consolidate: absorb ties__aligned

ties__aligned/.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

ties__aligned/README.md

@@ -0,0 +1,43 @@
+---
+library_name: transformers
+tags: [model-merging, mergeability, training-free, quotient-merge-distance]
+---
+
+# codegen-mono-multi__ties__aligned
+
+Training-free merged checkpoint from the **Mergeability** sweep
+(`benchmark/emit_lm.py --real`), produced by weight-space merging of two independently
+trained parents. No gradient steps were taken.
+
+| field | value |
+|---|---|
+| pair_id | `codegen-mono-multi` |
+| parent_a | `Salesforce/codegen-350M-mono` |
+| parent_b | `Salesforce/codegen-350M-multi` |
+| ceiling | `Salesforce/codegen-350M-nl` |
+| operator | `ties` |
+| alignment | `aligned` |
+| align_method | `permutation` |
+| regime | `shared_base` |
+| eval_langs | `wikitext` |
+| nll_merge | `9.1151` |
+| nll_floor | `6.2402` |
+| param_coverage | `1.0` |
+| MS | `-1.8115` |
+
+## How it was made
+
+Parents were loaded, activations extracted on a shared calibration corpus, and the merge applied
+either **naive** (parents combined in their own coordinates) or **aligned** (parent B carried into
+parent A's residual-stream basis via `common.alignment.residual_basis_map` before merging —
+permutation for same-width pairs, orthogonal/rectangular for cross-width).
+
+`MS` is the recovery score from `common.eval.mergeability_score` (merged vs. floor vs. ceiling), the
+same normalisation used by Zhou et al., so it is comparable across rows of the sweep.
+
+## Caveats
+
+Sub-1B merges are noisy; an aligned signal where the naive one is noise is the finding, not a bug.
+Rows without a joint ceiling are floor-relative and must not be read as absolute recovery.
+
+Generated automatically — see the [mergeability repo](https://github.com/suchirsalhan/mergeability).

ties__aligned/config.json

@@ -0,0 +1,41 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "CodeGenForCausalLM"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float16",
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "codegen",
+  "n_ctx": 2048,
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 20,
+  "n_positions": 2048,
+  "resid_pdrop": 0.0,
+  "rotary_dim": 32,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50,
+      "temperature": 1.0
+    }
+  },
+  "tie_word_embeddings": false,
+  "tokenizer_class": "GPT2Tokenizer",
+  "transformers_version": "5.14.1",
+  "use_cache": true,
+  "vocab_size": 51200
+}

ties__aligned/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 50256,
+  "transformers_version": "5.14.1",
+  "use_cache": true
+}

ties__aligned/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6ba172d6efeec1fc2369f1025e5d9f11c66e84f2fba9fcfc2461147f7578db7
+size 713442224

ties__aligned/tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "return_token_type_ids": false,
+  "tokenizer_class": "CodeGenTokenizer",
+  "unk_token": "<|endoftext|>"
+}