Stage submitted CoCo LoRA adapter and model card

README.md

@@ -0,0 +1,59 @@
+---
+base_model: amazon/chronos-2
+base_model_relation: adapter
+library_name: peft
+pipeline_tag: time-series-forecasting
+tags:
+- lora
+- chronos
+- time-series
+- forecasting
+- multimodal
+- coco
+---
+
+# CoCo: Chronos2 LoRA adapter
+
+The multivariate time-series forecasting component of **TSFM Meets LLM: Context as Covariates (CoCo)**, shared by SWARM-Lab. This repository contains the adapter from the paper's submitted supplementary package, not the base model weights.
+
+This adapter teaches Chronos2 to use an LLM's forecast and confidence covariates together with numerical history. Its companion LLM adapter is [SWARM-Lab/CoCo-Qwen3-4B-LoRA](https://huggingface.co/SWARM-Lab/CoCo-Qwen3-4B-LoRA).
+
+## Checkpoint
+
+- Base model: `amazon/chronos-2`.
+- PEFT LoRA rank: 8; alpha: 16; dropout: 0.
+- Target modules: `self_attention.q`, `self_attention.k`, `self_attention.v`, `self_attention.o`, `output_patch_embedding.output_layer`.
+- Adapter file: 4,854,584 bytes.
+- Adapter SHA-256: `e2ff6bcf5e35ad9d7e9199481ece4f095c53754423d7f925613e12138638f39c`.
+- Adapter configuration records PEFT 0.18.1.
+- Exact historical base-model revision was not recorded in the submitted adapter configuration; it remains to be established.
+
+## Loading the component
+
+```python
+import torch
+from chronos.chronos2 import Chronos2Model, Chronos2Pipeline
+from peft import PeftModel
+
+base = Chronos2Model.from_pretrained(
+    "amazon/chronos-2", torch_dtype=torch.bfloat16, device_map="cuda"
+)
+model = PeftModel.from_pretrained(base, "SWARM-Lab/CoCo-Chronos2-LoRA")
+model = model.merge_and_unload()
+model.eval()
+pipeline = Chronos2Pipeline(model)
+```
+
+Merging happens in memory; this repository stores only the LoRA adapter. This follows the submitted loader, but the remote-loading example has not yet been GPU-tested as part of the release.
+
+Use the paper's covariate construction rather than supplying arbitrary text embeddings: the forecast channel is shifted, numerical history is normalized using history-only statistics, and raw rollout variance is divided by squared history standard deviation (with the implementation's numerical stabilizer). The submitted implementation uses history noise standard deviation 0.05. A unified public CoCo inference package is being prepared.
+
+The submitted environment pins `chronos-forecasting==2.1.0`, `peft==0.18.1`, and `torch==2.9.0`.
+
+## Training and intended use
+
+The paper describes second-stage LoRA adaptation on pre-generated LLM forecast and confidence covariates. Intended use is research on text-aided time-series forecasting. The confidence covariate is a rollout-variance signal, not a calibrated probability of correctness.
+
+## Licensing status
+
+The base Chronos2 checkpoint is distributed under Apache-2.0 by its publisher. **A license for this adapter has not yet been assigned.** Do not interpret the base-model license as a separate license grant for these adapter weights. Training-data licensing is under review. This card does not grant unrestricted commercial-use rights.

adapter_config.json

@@ -0,0 +1,47 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Chronos2Model",
+    "parent_library": "chronos.chronos2.model"
+  },
+  "base_model_name_or_path": "amazon/chronos-2",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "output_patch_embedding.output_layer",
+    "self_attention.o",
+    "self_attention.k",
+    "self_attention.v",
+    "self_attention.q"
+  ],
+  "target_parameters": null,
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2ff6bcf5e35ad9d7e9199481ece4f095c53754423d7f925613e12138638f39c
+size 4854584