Clear repository before upload

README.md

@@ -1,75 +0,0 @@
----
-library_name: mouse-core
-tags:
-- mouse-core
-- reinforcement-learning
----
-
-# micahr234/mouse-example-model-augmented
-
-This repository contains a MOUSE model checkpoint.
-
-## Architecture
-
-- Backbone: `qwen3`
-- Hidden dimension: `1024`
-- Heads: `action_value`
-- Action head: `action_value`
-
-### Encoder
-
-`StepEmbedder` reads flat step-record dicts and projects each declared modality
-into the shared `1024`-dimensional token space before the
-backbone.
-
-| Field | Type | Required | Tensor shape | Dtype | Notes |
-|---|---|---:|---|---|---|
-| `action` | `discrete` | yes | `[B, S]` | `torch.long` | integer ids in `[0, 3]` |
-| `observation` | `discrete` | yes | `[B, S]` | `torch.long` | integer ids in `[0, 63]` |
-| `reward` | `rff` | yes | `[B, S]` | `torch.float32` | scalar value |
-| `done` | `discrete` | yes | `[B, S]` | `torch.long` | integer ids in `[0, 4]` |
-| - | `learnable` | no | `not read from step_stream` | `n/a` | learned tokens; no input field |
-
-## Install MouseCore
-
-```bash
-pip install mouse-core
-```
-
-## Load The Model
-
-```python
-import torch
-from mouse_core import load_model
-
-device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-model = load_model("micahr234/mouse-example-model-augmented", map_location="cpu").eval().to(device)
-```
-
-## Run Inference
-
-The model accepts a `list[list[dict]]` batch of shape `[B][S]` — B sequences,
-each containing S step-record dicts with flat keys matching the encoder's
-declared modalities above.
-
-```python
-# Batch shape: [B=1][S=1] — one sequence of one step.
-batch = [[
-    {
-    "action": 0,
-    "observation": 0,
-    "reward": 0.0,
-    "done": 0,
-    }
-]]
-predictions, objective_data, cache = model(batch)
-
-with torch.no_grad():
-    predictions, _, cache = model(batch)
-    action = model.get_action(predictions, temperature=0.0)
-```
-
-`model()` returns `(predictions, objective_data, cache)`. `objective_data` is a
-`TensorDict[B, S]` of the modality tensors extracted by the encoder — pass it
-to objectives during training. For cached one-step rollout, keep `cache` and
-pass it back on the next call with `use_cache=True`.

config.json

@@ -1,98 +0,0 @@
-{
-  "backbone": {
-    "hidden_dim": 1024,
-    "kwargs": {
-      "attention_bias": false,
-      "head_dim": 128,
-      "intermediate_size": 3072,
-      "max_position_embeddings": 40960,
-      "num_heads": 16,
-      "num_key_value_heads": 8,
-      "num_layers": 28,
-      "rms_norm_eps": 1e-06,
-      "use_sliding_window": false
-    },
-    "type": "qwen3"
-  },
-  "encoder": {
-    "kwargs": {
-      "concat_modalities": false,
-      "fourier_max": 10.0,
-      "fourier_min": 0.01,
-      "hidden_dim": 1024,
-      "include_type_token": false,
-      "modalities": [
-        {
-          "allow_none": false,
-          "field": "action",
-          "method": "rff",
-          "required": true,
-          "std": 0.02,
-          "tokens": 1,
-          "type": "discrete",
-          "vocab_size": 4
-        },
-        {
-          "allow_none": false,
-          "field": "observation",
-          "method": "rff",
-          "required": true,
-          "std": 0.02,
-          "tokens": 1,
-          "type": "discrete",
-          "vocab_size": 64
-        },
-        {
-          "allow_none": false,
-          "field": "reward",
-          "in_max": 100.0,
-          "in_min": 0.01,
-          "method": "rff",
-          "required": true,
-          "std": 0.02,
-          "tokens": 1,
-          "type": "rff"
-        },
-        {
-          "allow_none": false,
-          "field": "done",
-          "method": "rff",
-          "required": true,
-          "std": 0.02,
-          "tokens": 1,
-          "type": "discrete",
-          "vocab_size": 5
-        },
-        {
-          "allow_none": false,
-          "method": "rff",
-          "required": false,
-          "std": 0.02,
-          "tokens": 1,
-          "type": "learnable"
-        }
-      ],
-      "std": 0.02,
-      "token_data_len": 1,
-      "type_embedding_std": 0.0
-    },
-    "type": "step"
-  },
-  "format": "mouse-core-model-v1",
-  "heads": {
-    "action_head": "action_value",
-    "heads": [
-      {
-        "hidden_dim": 1024,
-        "in_features": 1024,
-        "name": "action_value",
-        "num_layers": 1,
-        "out_features": 4,
-        "scale": 0.1,
-        "type": "action_value",
-        "use_norm": true
-      }
-    ]
-  },
-  "hidden_dim": 1024
-}

pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:553fd62176e3140b7211639ff8d593086de2afff7e6cca42ff046a358935ab07
-size 1762623279