Upload 9 files

.gitattributes

@@ -1,35 +1,2 @@
-*.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
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,33 @@
+---
+language:
+- en
+base_model: mikahniehaus/Tern
+pipeline_tag: text-generation
+tags:
+- tinycode
+- onnx
+- python
+- reasoning
+---
+# tinycode-generator
+
+Accepted TinyCode model, based on Tern 124M. English request -> short plan -> Python code. Uses lossless whitespace-separated GPT-2 BPE.
+
+## Files
+- `model.onnx`: complete FP32 browser inference graph, no external tensor files.
+- `manifest.json`: SHA-256, graph dimensions and inference settings.
+- `checkpoint.pt`: native PyTorch model (custom Tern architecture, not Transformers AutoModel).
+- `runtime/codenarrator/`: Python architecture, tokenizer, preprocessing and decoding implementation.
+- `gpt2.tiktoken`: complete GPT-2 mergeable token ranks (base64 token + rank).
+- `tinycode_config.json`: architecture and task settings.
+
+Upload ALL contents of this folder to the ROOT of a public Hugging Face model repository.
+Keep filenames unchanged. The website downloads `model.onnx` using
+`https://huggingface.co/USERNAME/REPO/resolve/main/model.onnx`.
+The native checkpoints are provided for reproducibility; they are not downloaded by the website.
+No hosted inference server is needed. Weights execute on the visitor's CPU via ONNX Runtime Web.
+
+Reasoning is supervised generated text, not a correctness guarantee.
+This custom model is not directly compatible with the Hugging Face inference widget.
+Original pretraining model: https://huggingface.co/mikahniehaus/Tern .
+Consult its terms and the original sources before redistribution under another license.

SHA256SUMS.json

@@ -0,0 +1,57 @@
+{
+  ".gitattributes": "ca098ca8eca6e69ef98d2daa4129247463790411023701112cbe967351d63d44",
+  "checkpoint.pt": "afabbf733b819f821303772c0e92c2fe5fb837e628d73f1207cd5676fd1dce83",
+  "generator_encoding.js": "1a28e6fb69d0480256bb3cf4b996ff1b77fafd9681f88f2339e5ac38be9517e3",
+  "gpt2.tiktoken": "ccf876776dd2a896257e3427ff8627bd1d3538023617d507ebba654d57d36557",
+  "manifest.json": "0931eccf243c6ee5a997eca999aaa77aa9f1d100795b14675e09819b6cdbdcc2",
+  "model.onnx": "5aab2f0c537998ca385c677785d4e8ca5b30e65606942ddae2a9bf892762d383",
+  "README.md": "67461accf298de96046d7caba68dd905394df6087782a839ac3dc576026d6127",
+  "runtime/codenarrator/__init__.py": "4916984c1150037cc1d66cbb0b3e5bf957cf9cbda4aa490ec7bdbd1a01f1dc6a",
+  "runtime/codenarrator/advanced.py": "1f4ff191181db3f78fab692c7dcce4399e9146467176bdcbdceab62354b34ad8",
+  "runtime/codenarrator/batch_decode.py": "7c7bc690fd2956498001f436c3eb1f94de4676f52ac9487754bbe4f1ff5c138f",
+  "runtime/codenarrator/cached_decode.py": "a3f6d02aad7cd46ff7e022c3b2ee326abbe77c26ed7caab5014eaf43841a31bc",
+  "runtime/codenarrator/canonical_reasoning.py": "3717b2b79c2c9db89c7d958823174dddf859adc245e7181c412a3da1a4065c23",
+  "runtime/codenarrator/codegen.py": "b7a5cdcad2b30922537cce28399e07b2d023423ca0c7b1a17ad473231b018e2a",
+  "runtime/codenarrator/codegen_decode.py": "91735921a86f7cbbb49c23b2e976d4361bab9c57c01ae5998b4204057020ff53",
+  "runtime/codenarrator/codegen_encoding.py": "a54815abfaf0af0ca5a07f35fdf3e938857b8b34dd4d511a24f8cd4a3bbc9eed",
+  "runtime/codenarrator/codegen_lora.py": "05a1cdcc54fa525001e505a7d401ee3a192db6fc9d176e1f995cab0fa2a0ce6d",
+  "runtime/codenarrator/codegen_plan.py": "155b0cb71e007e17fdc654b9af24783ecb8774d3ee55efb37dcc489a5ec6f031",
+  "runtime/codenarrator/codegen_prompt_encoding.py": "70f2a9f33b3d41832962654549a4b42e98698963c086c79ec054a30b3764d2d6",
+  "runtime/codenarrator/common.py": "4e82e3ee623e2917b6f0674b2a40341e1b8fc6e1208735653eca566f3460edfb",
+  "runtime/codenarrator/compositional_teacher.py": "a9505960e65dd0f29208df59830a7706f75ebc4df4a91dc988dd0daa343590a0",
+  "runtime/codenarrator/dataset.py": "f9ecbf550f40cf87fa4e4af2844672e0410f147ddffa77cb8deeab4e2a00458c",
+  "runtime/codenarrator/evaluate.py": "b213d4a04d13a7dadf8381cc866805e875f1e43bf13206f5fa13b96f29c373f3",
+  "runtime/codenarrator/execution.py": "107ecfaaa278f0736087da54a41ce66169cb3d071644c64f063a7897959501e8",
+  "runtime/codenarrator/experiments.py": "544f37043d08eab460822e51634f1a2314327762ed185d2fd8465355e05d3123",
+  "runtime/codenarrator/finetune.py": "ab9314e9ab1265a85e279aec23c64c2ec84ce84e3ad87e145fbf7de68be246ff",
+  "runtime/codenarrator/generator.py": "7b534b2ed412d5a21162cca18abdc0b96250201d61930661a30f4488f60db62d",
+  "runtime/codenarrator/grounded_trace.py": "41ceab11f73fd9b21b19b929680cf1754829c54e25340fe4bcb5e836bee530e8",
+  "runtime/codenarrator/line_steps_teacher.py": "1ababd242f7f5d3098a081153dbf5f61281d923d52b4024fb34c6c4e69cf7367",
+  "runtime/codenarrator/metrics.py": "5ee1a65420caa02a1b1be27d4952cef054ec71b5df42c9bfe0bd900ec9eb3179",
+  "runtime/codenarrator/model.py": "7c01703240dbec5d554527dc666e35b3df8391d0b117fddc07afcf325a21d11c",
+  "runtime/codenarrator/model_loader.py": "5ac9413c47810a604cad78f56c031d3f280755d460074a86e7b1daff8ec603d5",
+  "runtime/codenarrator/NANOGPT_LICENSE": "a59ec5cdb1c1e447e5266a014b3e7ded511f8d6e5a08931e931c87490ff821fe",
+  "runtime/codenarrator/padded_decode.py": "b92e6d357d7caeb3426cb22e24a114b675d55e69db075c2ffde9e60650e9f912",
+  "runtime/codenarrator/phased_reasoning.py": "981f9a60eba4e78c3be9db1a578aaead601bd530b2bf79b12c857744e3cfdf6b",
+  "runtime/codenarrator/phased_training.py": "9a95842e6a33230a2f57ddd7dedd1d46de5e06286e1d140c0efa183d8f764d4f",
+  "runtime/codenarrator/preprocessing.py": "1eafe412c33becad14bfe737e35929de93cfb5ced70e413f37846b4cbaba08f3",
+  "runtime/codenarrator/prompts.py": "24f5f21025ec996f8c7335015c1e2af295b7d577d1a635a6823d411ed4b5c817",
+  "runtime/codenarrator/reasoning.py": "cf5f3f9df3cdb1ef3a790c5225fa27da66a09a996e82660dd77683ce905c112f",
+  "runtime/codenarrator/reasoning_teacher.py": "db03a8158ade02284050ab29fad91b3a01b8f4d80914cd80ca2c30048b8a4f64",
+  "runtime/codenarrator/recursive_training.py": "0deb7c65dd84b43ec53082d0b25c0307e5a988cd2fdd8b77d2683345614cda06",
+  "runtime/codenarrator/reporting.py": "7a858d321807b0477043f85e526b623f6786b0ba10282cf0429cb99ab2f2db35",
+  "runtime/codenarrator/section_loss.py": "2cb2bdf01f2826ba455d3fb451844d7cc50740e67f73515cc9f691832a1ea8ef",
+  "runtime/codenarrator/snippet_adapter.py": "142dc17cf17c97a6bc50dab4496cbc9c5acbde209c31faec007fd15daa59aa15",
+  "runtime/codenarrator/snippet_narrator.py": "0410ca3f0a35eb5388c0e5c54f015230edfc7492de0903187501648eaaf21152",
+  "runtime/codenarrator/snippets.py": "ffa1a27396db9d95140548916865c2737baa79de00d1e765168827b66ded249d",
+  "runtime/codenarrator/state_loss.py": "7975fb7a252ab658e90cda7035d3bd7868ea5ad1a6896ab24c1d92ae568f14fd",
+  "runtime/codenarrator/steps.py": "6e43137b991bcba39ed668e478b25ba3faf54a12b880256daee5a386620e5d80",
+  "runtime/codenarrator/steps_semantics.py": "ff9a93b1a9ac0d235b2ce7eeaf13fcd7eaac55c677990009892751e3363a696d",
+  "runtime/codenarrator/streaming.py": "13ad3d2fb00d884848e587657f7b635493d05a3d64c49d50e210f7de574808e7",
+  "runtime/codenarrator/summary_codec.py": "ade40b46aaa34aafc4e9f6996a7b7c5a114b02668ad5d40aa65a085432e151f1",
+  "runtime/codenarrator/symbolic_check.py": "d4a8dbbebf5d3030cab5bd416217a32ec28415061d5166e00fbcc465a0a082a3",
+  "runtime/codenarrator/text_checks.py": "3fe54faaceb9732e56dd38cd0bd15860b2a1a9351dd766fb8beae85639123751",
+  "runtime/codenarrator/tokenizer.py": "b5a11c460b8f5a798afe972d31041f2947e40a6a75434dcc65dd90ca078eafe8",
+  "runtime/codenarrator/trace_metrics.py": "cd6ab0f6a2b5fe3e1385b529b4cc6e5311dd81b90046adb536941d7255f4c5e2",
+  "tinycode_config.json": "02ac3379ff44c2cb74d697967081bfb3a082d5e96353711c261781c0e53b38fc"
+}

checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afabbf733b819f821303772c0e92c2fe5fb837e628d73f1207cd5676fd1dce83
+size 497528450

generator_encoding.js

@@ -0,0 +1,13 @@
+export function encodeFor(text,encoding,mode='bpe'){
+  if(mode==='dual_bpe'){
+    const prefix='Write a short plan, then simple Python code.\nRequest: ',suffix='\nPlan:\n';
+    if(text.startsWith(prefix)&&text.endsWith(suffix)){
+      const request=text.slice(prefix.length,-suffix.length);
+      return [...encoding.encode(prefix+request+'\nVerbatim request:\n',[],[]),...encodeFor(request,encoding,'space_bpe'),...encoding.encode(suffix,[],[])];
+    }
+    return encoding.encode(text,[],[]);
+  }
+  return mode==='space_bpe'
+    ? text.split(/([ \t\r\n\v\f]+)/).filter(Boolean).flatMap(part=>encoding.encode(part,[],[]))
+    : encoding.encode(text,[],[]);
+}

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aab2f0c537998ca385c677785d4e8ca5b30e65606942ddae2a9bf892762d383
+size 652164920

tinycode_config.json

@@ -0,0 +1,13 @@
+{
+  "architecture": "Tern GPT",
+  "n_layer": 12,
+  "n_head": 12,
+  "n_embd": 768,
+  "vocab_size": 50304,
+  "block_size": 1024,
+  "bias": true,
+  "tokenizer": "GPT-2 BPE",
+  "tokenization": "space_bpe",
+  "eos_token_id": 50256,
+  "output_format": "plan_then_code"
+}