Laya 0.3.7 checkpoints exported to ONNX for ruby-laya

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+multilingual/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,69 @@
+---
+license: apache-2.0
+library_name: onnx
+base_model: convaiinnovations/laya
+tags: [laya, onnx, system-one, calibrated-decisions, ruby, decision-model]
+---
+
+# Laya, exported to ONNX
+
+ONNX exports of the three [Laya](https://github.com/NandhaKishorM/laya) checkpoints, published for
+[ruby-laya](https://github.com/codenamev/ruby-laya). Laya is a non-autoregressive System 1 decision
+engine by [Convai Innovations](https://huggingface.co/convaiinnovations): typed decisions over any
+state in a single forward pass, with calibrated probabilities.
+
+These are conversions, not new models. All credit for the weights belongs to Convai Innovations.
+
+| folder | source | encoder | context |
+|---|---|---|---|
+| `english/` | [convaiinnovations/laya](https://huggingface.co/convaiinnovations/laya) (root) | ModernBERT-large | 512 |
+| `multilingual/` | the same repository's `multilingual/` | mmBERT-base | 1024 |
+| `typed-decisions/` | the same repository's `typed-decisions/` | ModernBERT-large | 1024 |
+
+Source revision: `convaiinnovations/laya` at commit `1c5edc17a7acd8701df6fc341c0d179f1c62c982`, exported with `laya` 0.3.7 and
+PyTorch 2.14.0.
+
+## What each folder holds
+
+    model.onnx             the decision model: encoder, typed decision head and action head
+    rl_agent_config.json   copied from the source checkpoint (token budgets, temperatures)
+    onnx_config.json       export provenance and the verified deviation from PyTorch
+    tokenizer/             copied from the source checkpoint
+
+## Graph
+
+Inputs are `input_ids`, `attention_mask` (int64 `[batch, seq]`), `marker_pos`, `marker_mask`
+(int64 and bool `[batch, markers]`) and `qtype` (int64 `[batch]`). Outputs are `logits`
+`[batch, markers]`, `act_logits` `[batch, 2]` and `last_hidden_state` `[batch, seq, dim]`, which
+the embedding shortlist uses. ONNX Runtime prunes the graph to the outputs you request, so asking
+for the first two costs nothing extra.
+
+A question with a single option is padded to two markers with the second masked off, and a batch
+shorter than eight tokens is padded up to it. Both are what the traced graph expects, and neither
+changes an answer.
+
+Weights are stored as float16 and cast to float32 in the graph. The published checkpoints are
+float16 on disk and upstream widens them at load, so the round trip is exact and the download
+stays the size of the original safetensors.
+
+## Verification
+
+Every export is checked against upstream `laya` on CPU: same sequence construction, same
+temperature buckets, same rounding. Each probability, score, confidence and action probability
+upstream reports is reproduced, and raw logits agree within 2.5e-5. Reproduce with
+[`tools/export_onnx.py`](https://github.com/codenamev/ruby-laya/blob/main/tools/export_onnx.py):
+
+    uv run tools/export_onnx.py <checkpoint-dir> <output-dir>
+
+## Use
+
+    gem install ruby-laya
+
+    require "laya"
+    agent = Laya.load("convaiinnovations/laya")   # resolves to english/ here
+
+Any ONNX Runtime can load these directly; the gem is a convenience, not a requirement.
+
+## License
+
+Apache 2.0, inherited from the source checkpoints. Laya was developed by Convai Innovations.

english/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea2a37ef3bea4c1ebf7484b3b3da51de51cf9949fdd8a0088129db10dbb83615
+size 846075711

english/onnx_config.json

@@ -0,0 +1,20 @@
+{
+  "format": "onnx",
+  "exported_from": "english",
+  "laya_version": "0.3.7",
+  "torch_version": "2.14.0",
+  "onnx_opset": 20,
+  "hidden_size": 1024,
+  "min_markers": 2,
+  "outputs": [
+    "logits",
+    "act_logits",
+    "last_hidden_state"
+  ],
+  "max_verified_diff": {
+    "logits": 2.4974346160888672e-05,
+    "act_logits": 0.00341796875,
+    "last_hidden_state": 0.00044655799865722656,
+    "predict_payload": 0.0
+  }
+}

english/rl_agent_config.json

@@ -0,0 +1,33 @@
+{
+  "encoder": "answerdotai/ModernBERT-large",
+  "head_layers": 2,
+  "max_len": 512,
+  "head_max_len": 192,
+  "max_prefixes": 6,
+  "act_costs": {
+    "escalate": 0.5
+  },
+  "cost_wrong_act": 3.0,
+  "amp_dtype": "bf16",
+  "model_name": "rl-agent",
+  "temperature": [
+    1.6369030475616455,
+    1.2514300346374512,
+    1.983399510383606
+  ],
+  "temperature_by_options": {
+    "choice:3-5": 1.7601518630981445,
+    "choice:6-10": 1.0000158548355103,
+    "score:3-5": 1.2514300346374512,
+    "noul:2": 1.983399510383606,
+    "choice:11+": 0.10058280825614929,
+    "choice:2": 1.9063563346862793
+  },
+  "training": {
+    "updates": 7313,
+    "epochs_completed": 1,
+    "hours": 1.96,
+    "world_size": 1,
+    "fine_tuned_from_checkpoint": true
+  }
+}

english/tokenizer/tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 8192,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "[UNK]"
+}

multilingual/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da6a0f87380597f679b12ce539e0a187e923fcffcf8dfc2f035728388dceacb0
+size 646693695

multilingual/onnx_config.json

@@ -0,0 +1,20 @@
+{
+  "format": "onnx",
+  "exported_from": "multilingual",
+  "laya_version": "0.3.7",
+  "torch_version": "2.14.0",
+  "onnx_opset": 20,
+  "hidden_size": 768,
+  "min_markers": 2,
+  "outputs": [
+    "logits",
+    "act_logits",
+    "last_hidden_state"
+  ],
+  "max_verified_diff": {
+    "logits": 4.3392181396484375e-05,
+    "act_logits": 0.001220703125,
+    "last_hidden_state": 0.0003654062747955322,
+    "predict_payload": 0.0
+  }
+}

multilingual/rl_agent_config.json

@@ -0,0 +1,26 @@
+{
+  "encoder": "jhu-clsp/mmBERT-base",
+  "head_layers": 2,
+  "max_len": 1024,
+  "head_max_len": 256,
+  "max_prefixes": 6,
+  "act_costs": {
+    "escalate": 0.5
+  },
+  "cost_wrong_act": 3.0,
+  "amp_dtype": "bf16",
+  "model_name": "rl-agent",
+  "temperature": [
+    1.0,
+    1.0,
+    1.0
+  ],
+  "temperature_by_options": {},
+  "training": {
+    "updates": 15987,
+    "epochs_completed": 4,
+    "hours": 4.97,
+    "world_size": 1,
+    "fine_tuned_from_checkpoint": false
+  }
+}

multilingual/tokenizer/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:609d8f4c067cd3950f88594c5a802616cea245823836ef5848ee4fc40aab5b6f
+size 34363188

multilingual/tokenizer/tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<bos>",
+  "eos_token": "<eos>",
+  "extra_special_tokens": {
+    "extra_0": "<start_of_turn>",
+    "extra_1": "<end_of_turn>"
+  },
+  "mask_token": "<mask>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sep_token": "<eos>",
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}

typed-decisions/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bc0662f05f69635291b1f823a946931b9936fcebd2ea98db85da70ebb8f4ba2
+size 846075712

typed-decisions/onnx_config.json

@@ -0,0 +1,20 @@
+{
+  "format": "onnx",
+  "exported_from": "typed-decisions",
+  "laya_version": "0.3.7",
+  "torch_version": "2.14.0",
+  "onnx_opset": 20,
+  "hidden_size": 1024,
+  "min_markers": 2,
+  "outputs": [
+    "logits",
+    "act_logits",
+    "last_hidden_state"
+  ],
+  "max_verified_diff": {
+    "logits": 6.4373016357421875e-06,
+    "act_logits": 0.001953125,
+    "last_hidden_state": 0.0009946823120117188,
+    "predict_payload": 0.0
+  }
+}

typed-decisions/rl_agent_config.json

@@ -0,0 +1,36 @@
+{
+  "encoder": "answerdotai/ModernBERT-large",
+  "head_layers": 2,
+  "max_len": 1024,
+  "head_max_len": 256,
+  "max_prefixes": 6,
+  "act_costs": {
+    "escalate": 0.5
+  },
+  "cost_wrong_act": 3.0,
+  "amp_dtype": "bf16",
+  "model_name": "laya-typed-decisions",
+  "temperature": [
+    1.0148024559020996,
+    1.0374259948730469,
+    1.0575125217437744
+  ],
+  "temperature_by_options": {
+    "choice:3-5": 1.7601518630981445,
+    "choice:6-10": 1.0000158548355103,
+    "score:3-5": 1.2514300346374512,
+    "noul:2": 1.983399510383606,
+    "choice:11+": 0.10058280825614929,
+    "choice:2": 1.9063563346862793
+  },
+  "training": {
+    "updates": 7313,
+    "epochs_completed": 1,
+    "hours": 1.96,
+    "world_size": 1,
+    "fine_tuned_from_checkpoint": true
+  },
+  "gradient_checkpointing": true,
+  "max_tokens_per_batch": 4096,
+  "fine_tuned": true
+}

typed-decisions/tokenizer/tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 8192,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "[UNK]"
+}