Upload folder using huggingface_hub

README.md

@@ -0,0 +1,89 @@
+---
+license: apache-2.0
+library_name: transformers
+tags:
+  - torchwright
+  - compiled-transformer
+  - calculator_simple
+pipeline_tag: text-generation
+---
+
+# `calculator_simple`, max_digits=6 (torchwright)
+
+A **compiled** transformer: the
+[torchwright](https://github.com/physicsrob/torchwright) compiler emitted
+these weights directly from a computation graph — nothing was trained.  This
+bundle is the `calculator_simple` example built with `max_digits=6`: a computation graph for integer arithmetic (`A op B` with `op` in `+ - *`).
+
+The bundle uses the stock Phi-3 architecture and loads through `transformers`
+without custom model code or `trust_remote_code`.
+
+Run it in **fp32** with **greedy decoding** (`do_sample=False`).  Other
+precisions and decoding modes are outside the supported contract.
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+repo_id = 'physicsrob/torchwright-calculator-simple-max-digits-6'
+model = AutoModelForCausalLM.from_pretrained(repo_id).eval()
+tok = AutoTokenizer.from_pretrained(repo_id)
+
+enc = tok('12*34\n', return_tensors="pt")
+out = model.generate(enc["input_ids"], max_new_tokens=32, do_sample=False,
+                     eos_token_id=tok.eos_token_id, pad_token_id=tok.eos_token_id)
+print(tok.decode(out[0, enc["input_ids"].shape[1]:], skip_special_tokens=True))
+```
+
+## Input and output
+
+Prompts are `A op B` terminated by a newline: two non-negative decimal
+operands of up to 6 digits, with `op` one of `+`, `-`, `*`.
+Subtraction may produce a negative result.  Wider operands, or any character
+outside the model's small vocabulary, are outside the contract — the output
+is undefined.
+
+| prompt | output |
+|---|---|
+| `12*34` | `408` |
+| `7+8` | `15` |
+| `999999*999999` | `999998000001` |
+| `999999+1` | `1000000` |
+| `999999-123456` | `876543` |
+| `123456-999999` | `-876543` |
+
+## Intended use and limitations
+
+This model is a demonstration of a computation graph compiled into transformer
+weights.  It is not a general language model or a general-purpose calculator;
+only the input contract above is supported.
+
+## Verification
+
+The examples above are exact reference outputs.  The Modal publishing path
+reloads the emitted checkpoint through stock `transformers`, checks those
+examples plus additional width-limit cases against Python integer arithmetic,
+and refuses to upload on a mismatch.  This is a functional smoke test, not
+exhaustive verification of every allowed expression.
+
+## Size
+
+The checkpoint stores 61.67 GB of dense fp32 weights (15,416,598,528 entries) at
+the example family's shared compile width.  100.00% of those entries are
+exactly zero: the vast majority of the model is unused canvas, so size reflects
+the compile geometry rather than stored knowledge.
+
+The zero entries are not compressed, and dense `transformers` execution still
+pays their memory and compute cost.  CPU execution is supported; allow
+additional RAM beyond the checkpoint size.
+
+## Family
+
+One example of many compiled with torchwright.  Calculator siblings —
+`calculator-simple` (serial arithmetic, depth grows with the digit count),
+`calculator-advanced` (carry-lookahead, near-flat depth), and
+`calculator-scratchpad` (flat depth; the serial work streams out as visible
+thinking tokens) — are published at several digit widths.  Browse the
+[torchwright calculator models](https://huggingface.co/models?search=physicsrob%2Ftorchwright-calculator)
+on Hugging Face.

config.json

@@ -0,0 +1,33 @@
+{
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 15,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 16,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 8427,
+  "max_position_embeddings": 512,
+  "model_type": "phi3",
+  "num_attention_heads": 124,
+  "num_hidden_layers": 33,
+  "num_key_value_heads": 124,
+  "original_max_position_embeddings": 4096,
+  "pad_token_id": null,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "partial_rotary_factor": 1.0,
+    "rope_theta": 500000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.12.1",
+  "use_cache": true,
+  "vocab_size": 17
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 15,
+  "eos_token_id": 16,
+  "pad_token_id": 16,
+  "transformers_version": "5.12.1"
+}

model-00001-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec0b897a22d08e0af48b4916465d6ed7e12a24317389d07dc2b385b2cb1b5a90
+size 1868595664

model-00002-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c9b4c8cb4bcdf15ebefe35b2cfa723c898c605af4aab687838488958bc924f5
+size 1868595664

model-00003-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77550dd75f1a8268a0528f1269972c2282a5c952ae60eb0977867e91a8b9d9cb
+size 1868595664

model-00004-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca437b8a72917670171e8907e84bf9b14b8a6f47126669bfb43ed1a8e0b1a126
+size 1868595664

model-00005-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df9482364d730a2287a773347deded34c65888ab79119a30d7c0535457532832
+size 1868595664

model-00006-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c4bb5dfd4bf9604cbd5a1418d921ebd219ca272acc6519535cf84f3a61380cc
+size 1868595664

model-00007-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f09ba98cae48f3647622f886d6cfe0802fe31de7f4f24e2da1c3bd260e0c43d
+size 1868595664

model-00008-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e701926d5e5108a50887f2db6dfd7e181a9102ebcb5ec106fa58393e28de7d9d
+size 1868595664

model-00009-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b5a06ab69bf45388b6ab09910f76d76be1feaa63854078ed3266920dfc6eacf
+size 1868595664

model-00010-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbc1731be468ec1311a27d45e16788df7fd6dcc90cbff5c8c9e61cf5477edb29
+size 1868595664

model-00011-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d24873626dc2c574e0134a12e3fda6d092c8f32065e5f868034a8f5bd101aa8
+size 1868595672

model-00012-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:915c7d100efa793f5ac0b3f0e1898ae0e0c628ffc46049edd90f2f3801a852e7
+size 1868595672

model-00013-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9f3fab05e7a787d9cb1c62a9c443f5281998063bb4367ecd2f0f9366100c81a
+size 1868595672

model-00014-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2bd3b95947c6e8038dbeaf7ae891a5d4a5ab1cc83c276c93e5af18509cde23d
+size 1868595672

model-00015-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb261883ec787cb159c234664f5d82218ba11c22fe3987e97061945860f80aa6
+size 1868595672

model-00016-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb3f8675f583f55ad30ed49ef14f0f86ac8caf1237c4d929c4da24a1bf5b1c06
+size 1868595672

model-00017-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a82e8a10e2d34cc37b6248554659a4403114abd64767026ccfa92f1dcee58340
+size 1868595672

model-00018-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d47002792a9b3d45bc4cd2775f8820906d24f170c28df1e2ed663a9659623a39
+size 1868595672

model-00019-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bab2e9bbe49949923fad7d7561d485449c26bb2412c6a0a410b03befb193c7b
+size 1868595672

model-00020-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1a66cd3a8c66dd35c13e36fa113950c6f55aa4bdcfbeacbbd287b6549203f75
+size 1868595672

model-00021-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cb868ca286c462f0517f4e5c3e08ec96416cca5ad68b53ac163f6424c9e12d3
+size 1868595672

model-00022-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5603538d4b746a7be30d871ee4bc5792c3aa669432de80a5fb5a2ddb9f2cdbf7
+size 1868595672

model-00023-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2aac122d9ac70888906890d632d688575ce77ff7ae501d6c6657bf8537ded560
+size 1868595672

model-00024-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0855b4e9d8cbb7a79f4aa8bbbe73ece18206ac70125ce53c52bb7beb0c4e7aab
+size 1868595672

model-00025-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13a8bf66337dd30239ee0d3d056ef1e13bf40c9de1af0800c5aaa872ca0ad6b1
+size 1868595672

model-00026-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5709263bf83508f113a056a27a9e1ab140fffc3f43a02b5b09f5c40477a928ac
+size 1868595672

model-00027-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8226787ba6be2ae15ae00f495bae98b0d30076c82d323c9a99ce06ea87020a7
+size 1868595672

model-00028-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a386bd716e2e162ebb2ffd8400083b9dfbae76474e3d731a7ca50da757ed4d9
+size 1868595672

model-00029-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:567cc7fbaa469e25bdce8ba70030488f4d507d4b29a0c4fc757a8d56d75a57d7
+size 1868595672

model-00030-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5954be21b83acd730959377e636cea5ce6d38b849c6b2b8dd19d627474245c9f
+size 1868595672

model-00031-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:745382b82805719abc649bd3aa393861bbc52cf423fbf0167a42f5dd6410b5e7
+size 1868595672

model-00032-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19df1ea5cf3055c891d1c55a71d843289be858affa881909c21302ec124ea7a5
+size 1868595672

model-00033-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f74414609a56496978f2bec7412cf4ea271adac215399aef005d5d902649cc50
+size 1868595672

model-00034-of-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7f6bada6bad22961f3eee68f3fcd67b5df9bc773796b353d870ced4e10c1faa
+size 2759880

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"total_size": 61666394112}, "weight_map": {"model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00034.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00034.safetensors", "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00034.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00034.safetensors", "model.layers.1.self_attn.qkv_proj.weight": "model-00002-of-00034.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00034.safetensors", "model.layers.1.mlp.gate_up_proj.weight": "model-00002-of-00034.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00034.safetensors", "model.layers.2.self_attn.qkv_proj.weight": "model-00003-of-00034.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00034.safetensors", "model.layers.2.mlp.gate_up_proj.weight": "model-00003-of-00034.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00034.safetensors", "model.layers.3.self_attn.qkv_proj.weight": "model-00004-of-00034.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00034.safetensors", "model.layers.3.mlp.gate_up_proj.weight": "model-00004-of-00034.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00004-of-00034.safetensors", "model.layers.4.self_attn.qkv_proj.weight": "model-00005-of-00034.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00034.safetensors", "model.layers.4.mlp.gate_up_proj.weight": "model-00005-of-00034.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00005-of-00034.safetensors", "model.layers.5.self_attn.qkv_proj.weight": "model-00006-of-00034.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00034.safetensors", "model.layers.5.mlp.gate_up_proj.weight": "model-00006-of-00034.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00006-of-00034.safetensors", "model.layers.6.self_attn.qkv_proj.weight": "model-00007-of-00034.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00034.safetensors", "model.layers.6.mlp.gate_up_proj.weight": "model-00007-of-00034.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00007-of-00034.safetensors", "model.layers.7.self_attn.qkv_proj.weight": "model-00008-of-00034.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00034.safetensors", "model.layers.7.mlp.gate_up_proj.weight": "model-00008-of-00034.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00008-of-00034.safetensors", "model.layers.8.self_attn.qkv_proj.weight": "model-00009-of-00034.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00034.safetensors", "model.layers.8.mlp.gate_up_proj.weight": "model-00009-of-00034.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00009-of-00034.safetensors", "model.layers.9.self_attn.qkv_proj.weight": "model-00010-of-00034.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00010-of-00034.safetensors", "model.layers.9.mlp.gate_up_proj.weight": "model-00010-of-00034.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00010-of-00034.safetensors", "model.layers.10.self_attn.qkv_proj.weight": "model-00011-of-00034.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00011-of-00034.safetensors", "model.layers.10.mlp.gate_up_proj.weight": "model-00011-of-00034.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00011-of-00034.safetensors", "model.layers.11.self_attn.qkv_proj.weight": "model-00012-of-00034.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00012-of-00034.safetensors", "model.layers.11.mlp.gate_up_proj.weight": "model-00012-of-00034.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00012-of-00034.safetensors", "model.layers.12.self_attn.qkv_proj.weight": "model-00013-of-00034.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00013-of-00034.safetensors", "model.layers.12.mlp.gate_up_proj.weight": "model-00013-of-00034.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00013-of-00034.safetensors", "model.layers.13.self_attn.qkv_proj.weight": "model-00014-of-00034.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00014-of-00034.safetensors", "model.layers.13.mlp.gate_up_proj.weight": "model-00014-of-00034.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00014-of-00034.safetensors", "model.layers.14.self_attn.qkv_proj.weight": "model-00015-of-00034.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00015-of-00034.safetensors", "model.layers.14.mlp.gate_up_proj.weight": "model-00015-of-00034.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00015-of-00034.safetensors", "model.layers.15.self_attn.qkv_proj.weight": "model-00016-of-00034.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00016-of-00034.safetensors", "model.layers.15.mlp.gate_up_proj.weight": "model-00016-of-00034.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00016-of-00034.safetensors", "model.layers.16.self_attn.qkv_proj.weight": "model-00017-of-00034.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00017-of-00034.safetensors", "model.layers.16.mlp.gate_up_proj.weight": "model-00017-of-00034.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00017-of-00034.safetensors", "model.layers.17.self_attn.qkv_proj.weight": "model-00018-of-00034.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00018-of-00034.safetensors", "model.layers.17.mlp.gate_up_proj.weight": "model-00018-of-00034.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00018-of-00034.safetensors", "model.layers.18.self_attn.qkv_proj.weight": "model-00019-of-00034.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00019-of-00034.safetensors", "model.layers.18.mlp.gate_up_proj.weight": "model-00019-of-00034.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00019-of-00034.safetensors", "model.layers.19.self_attn.qkv_proj.weight": "model-00020-of-00034.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00020-of-00034.safetensors", "model.layers.19.mlp.gate_up_proj.weight": "model-00020-of-00034.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00020-of-00034.safetensors", "model.layers.20.self_attn.qkv_proj.weight": "model-00021-of-00034.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00021-of-00034.safetensors", "model.layers.20.mlp.gate_up_proj.weight": "model-00021-of-00034.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00021-of-00034.safetensors", "model.layers.21.self_attn.qkv_proj.weight": "model-00022-of-00034.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00022-of-00034.safetensors", "model.layers.21.mlp.gate_up_proj.weight": "model-00022-of-00034.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00022-of-00034.safetensors", "model.layers.22.self_attn.qkv_proj.weight": "model-00023-of-00034.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00023-of-00034.safetensors", "model.layers.22.mlp.gate_up_proj.weight": "model-00023-of-00034.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00023-of-00034.safetensors", "model.layers.23.self_attn.qkv_proj.weight": "model-00024-of-00034.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00024-of-00034.safetensors", "model.layers.23.mlp.gate_up_proj.weight": "model-00024-of-00034.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00024-of-00034.safetensors", "model.layers.24.self_attn.qkv_proj.weight": "model-00025-of-00034.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00025-of-00034.safetensors", "model.layers.24.mlp.gate_up_proj.weight": "model-00025-of-00034.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00025-of-00034.safetensors", "model.layers.25.self_attn.qkv_proj.weight": "model-00026-of-00034.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00026-of-00034.safetensors", "model.layers.25.mlp.gate_up_proj.weight": "model-00026-of-00034.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00026-of-00034.safetensors", "model.layers.26.self_attn.qkv_proj.weight": "model-00027-of-00034.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00027-of-00034.safetensors", "model.layers.26.mlp.gate_up_proj.weight": "model-00027-of-00034.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00027-of-00034.safetensors", "model.layers.27.self_attn.qkv_proj.weight": "model-00028-of-00034.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00028-of-00034.safetensors", "model.layers.27.mlp.gate_up_proj.weight": "model-00028-of-00034.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00028-of-00034.safetensors", "model.layers.28.self_attn.qkv_proj.weight": "model-00029-of-00034.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00029-of-00034.safetensors", "model.layers.28.mlp.gate_up_proj.weight": "model-00029-of-00034.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00029-of-00034.safetensors", "model.layers.29.self_attn.qkv_proj.weight": "model-00030-of-00034.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00030-of-00034.safetensors", "model.layers.29.mlp.gate_up_proj.weight": "model-00030-of-00034.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00030-of-00034.safetensors", "model.layers.30.self_attn.qkv_proj.weight": "model-00031-of-00034.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00031-of-00034.safetensors", "model.layers.30.mlp.gate_up_proj.weight": "model-00031-of-00034.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00031-of-00034.safetensors", "model.layers.31.self_attn.qkv_proj.weight": "model-00032-of-00034.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00032-of-00034.safetensors", "model.layers.31.mlp.gate_up_proj.weight": "model-00032-of-00034.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00032-of-00034.safetensors", "model.layers.32.self_attn.qkv_proj.weight": "model-00033-of-00034.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00033-of-00034.safetensors", "model.layers.32.mlp.gate_up_proj.weight": "model-00033-of-00034.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00033-of-00034.safetensors", "model.embed_tokens.weight": "model-00034-of-00034.safetensors", "model.norm.weight": "model-00034-of-00034.safetensors", "model.layers.0.input_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.1.input_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.2.input_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.3.input_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.4.input_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.5.input_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.6.input_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.7.input_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.8.input_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.9.input_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.10.input_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.11.input_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.12.input_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.13.input_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.14.input_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.15.input_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.16.input_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.17.input_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.18.input_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.19.input_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.20.input_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.21.input_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.22.input_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.23.input_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.24.input_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.25.input_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.26.input_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.27.input_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.28.input_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.29.input_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.30.input_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.31.input_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.32.input_layernorm.weight": "model-00034-of-00034.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00034-of-00034.safetensors"}}

tokenizer.json

@@ -0,0 +1,114 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 15,
+      "content": "<bos>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 16,
+      "content": "<eos>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "Split",
+    "pattern": {
+      "Regex": "[\\s\\S]"
+    },
+    "behavior": "Isolated",
+    "invert": false
+  },
+  "post_processor": {
+    "type": "TemplateProcessing",
+    "single": [
+      {
+        "SpecialToken": {
+          "id": "<bos>",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      }
+    ],
+    "pair": [
+      {
+        "SpecialToken": {
+          "id": "<bos>",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "<bos>",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 0
+        }
+      }
+    ],
+    "special_tokens": {
+      "<bos>": {
+        "id": "<bos>",
+        "ids": [
+          15
+        ],
+        "tokens": [
+          "<bos>"
+        ]
+      }
+    }
+  },
+  "decoder": {
+    "type": "Fuse"
+  },
+  "model": {
+    "type": "WordLevel",
+    "vocab": {
+      "0": 0,
+      "1": 1,
+      "2": 2,
+      "3": 3,
+      "4": 4,
+      "5": 5,
+      "6": 6,
+      "7": 7,
+      "8": 8,
+      "9": 9,
+      "+": 10,
+      "-": 11,
+      "*": 12,
+      "\n": 13,
+      " ": 14,
+      "<bos>": 15,
+      "<eos>": 16
+    },
+    "unk_token": "<unk>"
+  }
+}

tokenizer_config.json

@@ -0,0 +1,8 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<bos>",
+  "eos_token": "<eos>",
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null
+}