Duplicate from tiny-random/timestral

.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

.meta.json

@@ -0,0 +1,19 @@
+{
+  "source_model": {
+    "name": "mistralai/Timestral-209M",
+    "commit_id": "9874d252ab0aae16f7f7c999f98f98d6ad7d8365"
+  },
+  "env": {
+    "python": "3.12.13",
+    "packages": {
+      "huggingface_hub": "1.27.0",
+      "numpy": "2.5.2",
+      "safetensors": "0.8.0",
+      "timestral": "1.0.0",
+      "tokenizers": "0.23.0rc0",
+      "torch": "2.13.0+cu126",
+      "transformers": "5.15.0.dev0"
+    },
+    "cuda": "12.6"
+  }
+}

LICENSE

@@ -0,0 +1,10 @@
+Modified MIT License 
+
+Attribution notice: 2026 - Mistral AI
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of the weights of this model and associated documentation files (the “Model”), to deal in the Model without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Model, and to permit persons to whom the Model is furnished to do so, subject to the following conditions: 
+
+1. The above attribution notice and this permission notice shall be included in all copies or substantial portions of the Model. 
+2. You are not authorized to exercise any rights under this license if the global consolidated monthly revenue of your company (or that of your employer) exceeds $20 million (or its equivalent in another currency) for the preceding month. This restriction in (b) applies to the Model and any derivatives, modifications, or combined works based on it, whether provided by Mistral AI or by a third party. You may contact Mistral AI (sales@mistral.ai) to request a commercial license, which Mistral AI may grant you at its sole discretion, or choose to use the Model on Mistral AI's hosted services available at https://mistral.ai/.
+
+THE MODEL IS PROVIDED “AS IS”, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL MISTRAL AI BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE MODEL OR THE USE OR OTHER DEALINGS IN THE MODEL.

README.md

@@ -0,0 +1,214 @@
+---
+library_name: timestral
+base_model:
+- mistralai/Timestral-209M
+---
+
+This tiny model is intended for debugging. It is randomly initialized using the configuration adapted from [mistralai/Timestral-209M](https://huggingface.co/mistralai/Timestral-209M).
+
+Structural comparison with `mistralai/Timestral-209M`:
+
+| Feature | Source | Tiny |
+|---|---:|---:|
+| Forecasting interface | univariate, multivariate, past/known covariates | same |
+| Stored precision | F32 | F32 |
+| Patch size / block size | 32 / 32 | same |
+| Transformer layers | 24 | 8; two 3-time + 1-time/variate cycles |
+| Width / attention heads / head dimension | 768 / 12 / 64 | 64 / 1 / 64 |
+| SwiGLU intermediate width | 2,048 | 128 |
+| Quantile knots | 21 | same |
+| DHF two-stream decoder and monotone quantile head | present | same |
+
+This checkpoint uses Mistral's public `timestral` inference package (release
+commit `a534bdbd244d64f3d9d743f46c7bf6fc330ed4ff`): install it with
+`pip install git+https://github.com/mistralai/timestral.git` before running the
+example.  It is a forecasting model, not a Transformers causal-LM or SGLang/vLLM
+serving model.
+
+| File path | Size |
+|------|------|
+| model.safetensors | 2.7MB |
+
+
+### Example usage:
+
+- Transformers (✅ verified)
+
+```python
+import torch
+from timestral import TimestralForecaster
+
+model_id = "tiny-random/timestral"
+device = "cuda" if torch.cuda.is_available() else "cpu"
+forecaster = TimestralForecaster.from_pretrained(model_id, device=device, per_shot_horizon_patches=32)
+context = torch.sin(torch.arange(96, dtype=torch.float32) / 6).reshape(1, 1, -1)
+past = torch.cos(torch.arange(96, dtype=torch.float32) / 5).reshape(1, 1, -1)
+known = torch.linspace(0, 1, 128, dtype=torch.float32).reshape(1, 1, -1)
+forecast = forecaster.forecast(context, prediction_length=32, past_covariates=past, known_covariates=known)
+print(forecast.quantiles.shape)
+```
+
+### Codes to create this repo (✅ verified):
+
+<details><summary>Click to expand</summary>
+
+```python
+import json
+from pathlib import Path
+from shutil import copyfile
+
+import torch
+from huggingface_hub import hf_hub_download
+from safetensors.torch import save_file
+from timestral import TimestralConfig, TimestralModel
+
+source_model_id = "mistralai/Timestral-209M"
+save_folder = "/tmp/tiny-random/timestral"
+source_revision = "9874d252ab0aae16f7f7c999f98f98d6ad7d8365"
+torch.manual_seed(42)
+folder = Path(save_folder)
+folder.mkdir(parents=True, exist_ok=True)
+raw = json.loads(Path(hf_hub_download(source_model_id, "config.json", revision=source_revision)).read_text())
+# Keep two source 3-time + 1-time/variate cycles.  A 64-wide model with one
+# head preserves Timestral's 64-wide attention head exactly.
+raw.update(
+    d_model=64, num_heads=1, mlp_hidden_dim=128, context_length=1024,
+    block_schedule=["time", "time", "time", "time_variate"] * 2,
+)
+(folder / "config.json").write_text(json.dumps(raw, indent=2) + "\n", encoding="utf-8")
+config = TimestralConfig.load(folder / "config.json")
+model = TimestralModel(config).float()
+with torch.no_grad():
+    for name, parameter in sorted(model.named_parameters()):
+        if name.endswith("scale"):
+            parameter.fill_(1)
+        else:
+            torch.nn.init.normal_(parameter, mean=0, std=0.02)
+save_file(model.state_dict(), folder / "model.safetensors", metadata={"format": "pt"})
+for filename in ("LICENSE", "timestral-hourglass.png"):
+    try:
+        copyfile(hf_hub_download(source_model_id, filename, revision=source_revision), folder / filename)
+    except Exception:
+        # The executable checkpoint consists solely of config.json and model.safetensors.
+        # Preserve optional presentation assets when their source revision supplies them.
+        pass
+```
+
+</details>
+
+### Printing the model:
+
+<details><summary>Click to expand</summary>
+
+```text
+TimestralModel(
+  (representation): PatchRepresentation(
+    (patch_proj): ResidualBlock(
+      (hidden_layer): Linear(in_features=64, out_features=256, bias=True)
+      (output_layer): Linear(in_features=256, out_features=64, bias=True)
+      (residual_layer): Linear(in_features=64, out_features=64, bias=True)
+      (activation): SiLU()
+    )
+  )
+  (transformer): Transformer(
+    (layers): ModuleList(
+      (0-2): 3 x TransformerBlock(
+        (attn_norms): ModuleList(
+          (0): RMSNorm()
+        )
+        (attns): ModuleList(
+          (0): Attention(
+            (wQKV): Linear(in_features=64, out_features=192, bias=False)
+            (wO): Linear(in_features=64, out_features=64, bias=False)
+            (_gate): Linear(in_features=64, out_features=64, bias=False)
+          )
+        )
+        (mlp_norm): RMSNorm()
+        (mlp): FusedSwiGLU(
+          (w12): Linear(in_features=64, out_features=256, bias=False)
+          (w3): Linear(in_features=128, out_features=64, bias=False)
+        )
+      )
+      (3): TransformerBlock(
+        (attn_norms): ModuleList(
+          (0-1): 2 x RMSNorm()
+        )
+        (attns): ModuleList(
+          (0-1): 2 x Attention(
+            (wQKV): Linear(in_features=64, out_features=192, bias=False)
+            (wO): Linear(in_features=64, out_features=64, bias=False)
+            (_gate): Linear(in_features=64, out_features=64, bias=False)
+          )
+        )
+        (mlp_norm): RMSNorm()
+        (mlp): FusedSwiGLU(
+          (w12): Linear(in_features=64, out_features=256, bias=False)
+          (w3): Linear(in_features=128, out_features=64, bias=False)
+        )
+      )
+      (4-6): 3 x TransformerBlock(
+        (attn_norms): ModuleList(
+          (0): RMSNorm()
+        )
+        (attns): ModuleList(
+          (0): Attention(
+            (wQKV): Linear(in_features=64, out_features=192, bias=False)
+            (wO): Linear(in_features=64, out_features=64, bias=False)
+            (_gate): Linear(in_features=64, out_features=64, bias=False)
+          )
+        )
+        (mlp_norm): RMSNorm()
+        (mlp): FusedSwiGLU(
+          (w12): Linear(in_features=64, out_features=256, bias=False)
+          (w3): Linear(in_features=128, out_features=64, bias=False)
+        )
+      )
+      (7): TransformerBlock(
+        (attn_norms): ModuleList(
+          (0-1): 2 x RMSNorm()
+        )
+        (attns): ModuleList(
+          (0-1): 2 x Attention(
+            (wQKV): Linear(in_features=64, out_features=192, bias=False)
+            (wO): Linear(in_features=64, out_features=64, bias=False)
+            (_gate): Linear(in_features=64, out_features=64, bias=False)
+          )
+        )
+        (mlp_norm): RMSNorm()
+        (mlp): FusedSwiGLU(
+          (w12): Linear(in_features=64, out_features=256, bias=False)
+          (w3): Linear(in_features=128, out_features=64, bias=False)
+        )
+      )
+    )
+    (rope): SinCosRoPE()
+    (out_norm): RMSNorm()
+  )
+  (head): QuantileHead(
+    (projection): ResidualBlock(
+      (hidden_layer): Linear(in_features=64, out_features=256, bias=False)
+      (output_layer): Linear(in_features=256, out_features=672, bias=False)
+      (residual_layer): Linear(in_features=64, out_features=672, bias=False)
+      (activation): SiLU()
+    )
+  )
+)
+```
+
+</details>
+
+### Test environment:
+
+- huggingface_hub: 1.27.0
+- numpy: 2.5.2
+- safetensors: 0.8.0
+- timestral: 1.0.0
+- tokenizers: 0.23.0rc0
+- torch: 2.13.0+cu126
+- transformers: 5.15.0.dev0
+
+### Change log:
+
+- 2026-10-23: Initial version.
+
+This repo is generated by GPT-6.1-Sol

config.json

@@ -0,0 +1,55 @@
+{
+  "patch_size": 32,
+  "d_model": 64,
+  "num_heads": 1,
+  "mlp_hidden_dim": 128,
+  "block_schedule": [
+    "time",
+    "time",
+    "time",
+    "time_variate",
+    "time",
+    "time",
+    "time",
+    "time_variate"
+  ],
+  "quantile_knots": [
+    0.01,
+    0.05,
+    0.1,
+    0.15,
+    0.2,
+    0.25,
+    0.3,
+    0.35,
+    0.4,
+    0.45,
+    0.5,
+    0.55,
+    0.6,
+    0.65,
+    0.7,
+    0.75,
+    0.8,
+    0.85,
+    0.9,
+    0.95,
+    0.99
+  ],
+  "block_size": 32,
+  "context_length": 1024,
+  "rope_theta": 10000.0,
+  "rope_partial_factor": 0.5,
+  "norm_eps": 1e-06,
+  "attn_bias": false,
+  "mlp_bias": false,
+  "time_attn_gate": "sdpa_sigmoid",
+  "variate_attn_gate": "sdpa_sigmoid",
+  "minimum_scale": 1e-06,
+  "use_asinh": true,
+  "stabilize_with_global": false,
+  "covariate_enabled": true,
+  "split_context_horizon_attn": true,
+  "attend_missing_patches": true,
+  "quantile_width_factor": 3.0
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:564921d8f9e096df7bfecce109f6bc2ae52b93ca55b4c67d344fde3d587db1fb
+size 2693368