Release local GLM-5.3-Flash Remory 1.24B checkpoint

.gitattributes

@@ -1,35 +1 @@
-*.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

README.md

@@ -0,0 +1,32 @@
+---
+language:
+  - en
+library_name: pytorch
+base_model: zai-org/GLM-5.3-Flash
+base_model_relation: adapter
+tags:
+  - remory
+  - context-compression
+  - residual-memory
+  - soft-memory
+  - long-context
+  - glm
+  - arxiv:2610.11287
+---
+
+[📄 **arXiv**](https://arxiv.org/abs/2610.11287) · [💻 **GitHub**](https://github.com/1ring2rta/Remory)
+
+## Citation
+
+```bibtex
+@misc{xia2026remory,
+  title = {Remory: Learning Residual Memory for Context Compaction},
+  author = {Hanchen Xia and Baoyou Chen and Yutang Ge and Naihao Deng and
+            Senqiao Yang and Zilong Dong and Weihao Yuan and Siyu Zhu},
+  year = {2026},
+  eprint = {2610.11287},
+  archivePrefix = {arXiv},
+  primaryClass = {cs.CL},
+  url = {https://arxiv.org/abs/2610.11287}
+}
+```

SHA256SUMS

@@ -0,0 +1,5 @@
+ee05350c7fda0af4da116020dd7b976d731de3beed4f5e717d5bcc95ead24550  .gitattributes
+6b036ea72c585e8897f8ebd3a00217febea243cd8eb10f6e6558060a28f72a86  README.md
+fe943ed03e1f28c5b2c7e8e27cacc852b98f7fc5fcb4a5da33d74402594792d6  config.json
+f6435812dc7be330c7b46a957651fd664ea25964405f96b165d57cff7697558c  manifest.json
+6c6491eca473c8f1afab4359f933d47e9bd076a9798fc904ecade7529a3e7e22  model.safetensors

config.json

@@ -0,0 +1,94 @@
+{
+  "compressor": {
+    "architecture": "GrepSeekDFlashCompressor",
+    "target_layer_ids": [
+      0,
+      11,
+      22,
+      33,
+      44
+    ],
+    "target_hidden_size": 4096,
+    "selected_source_width": 20480,
+    "compression_ratio": 16,
+    "local_window": 2048,
+    "hidden_size": 4096,
+    "intermediate_size": 12288,
+    "num_hidden_layers": 6,
+    "num_attention_heads": 32,
+    "num_key_value_heads": 8,
+    "head_dim": 128,
+    "layer_types": [
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention"
+    ],
+    "gradient_checkpointing": true,
+    "output_embedding_rms": 0.01127698551863432,
+    "slot_padding_side": "left"
+  },
+  "feature_view": "decoder_block_attn_hc_collapsed_input",
+  "summary_conditioning": "explicit frozen-reader input only; no additional Compressor modules",
+  "token_contract": {
+    "schema": "glm53_flash_residual_token_contract",
+    "model": "zai-org/GLM-5.3-Flash",
+    "model_config_sha256": "bb8f01c42cb92a52ca72e65afb4d5bd8d11aef083cd210e8de25dfb904f23e9f",
+    "tokenizer_files": {
+      "tokenizer.json": "19e773648cb4e65de8660ea6365e10acca112d42a854923df93db4a6f333a82d",
+      "tokenizer_config.json": "98b1271574f41abf89427ae2dda030d94dc9478f0edc5a8bd240db213c6fd5fc",
+      "chat_template.jinja": "0c4099f3382d6c92700dfb99725025360966fd73032f0ecf32377c0d9e6309c5"
+    },
+    "reasoning_effort": "max",
+    "clear_thinking": false,
+    "base_prefix_ids": [
+      154822,
+      154824,
+      154826,
+      25062,
+      287,
+      29905,
+      371,
+      25,
+      7487
+    ],
+    "assistant_opening_ids": [
+      154828,
+      154841
+    ],
+    "student_summary_before_ids": [
+      154827,
+      1972,
+      29186,
+      510
+    ],
+    "student_summary_after_ids": [],
+    "student_memory_before_ids": [
+      154827,
+      1061,
+      3340,
+      2266,
+      4938,
+      510
+    ],
+    "student_memory_after_ids": [],
+    "contract_sha256": "951c8846e6cfe940f53d982cbe83742b521d3bc6850f690607126f994b57cf8a"
+  },
+  "source_global_step": 210,
+  "source_contract_sha256": "9eff07380c57228a9c18b943522b1e8bb2c3210a0e40c1cb980560d16414f21f",
+  "schema": "remory_glm53_local_evaluation_v1",
+  "format_version": 1,
+  "architectures": [
+    "GrepSeekDFlashCompressor"
+  ],
+  "torch_dtype": "float32",
+  "target_model": "zai-org/GLM-5.3-Flash",
+  "target_revision": "eb9eb208eb0d988989d07a6a12d0fdeb5f52574a",
+  "parameters": 1241576960,
+  "release_variant": "local-evaluation",
+  "serving_ready": false,
+  "serving_note": "The public Remory launcher supports Qwen; GLM actor integration is not included.",
+  "source_token_contract_sha256": "39339255222a660c140d31594d98288e183933e4e65a3de404cdf221d1c7dbec"
+}

manifest.json

@@ -0,0 +1,21 @@
+{
+  "schema": "remory_glm53_local_evaluation_release_v1",
+  "repo_id": "mocoV3/GLM-5.3-Flash-REMORY-1.24B",
+  "parameters": 1241576960,
+  "stored_tensor_elements": 1241576961,
+  "tensor_count": 71,
+  "dtype": "float32",
+  "safetensors_sha256": "6c6491eca473c8f1afab4359f933d47e9bd076a9798fc904ecade7529a3e7e22",
+  "config_sha256": "22df50b530d600deecd770f2852b113f62126a90b22be8c79834c71e400e3dd3",
+  "source_compressor_sha256": "80503f5864b3d64e3e64862981c75e8fcb4c7db77e02b76da2132d3d514904e9",
+  "source_global_step": 210,
+  "release_variant": "local-evaluation",
+  "paper_checkpoint": false,
+  "public_launcher_supported": false,
+  "validation": {
+    "tensor_values_unchanged": true,
+    "all_tensors_finite": true,
+    "safetensors_exact_reload": true,
+    "cuda_used": false
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c6491eca473c8f1afab4359f933d47e9bd076a9798fc904ecade7529a3e7e22
+size 4966315580