parallelogram 0.2.0__tar.gz

parallelogram-0.2.0/.github/workflows/tests.yml

@@ -0,0 +1,53 @@
+name: tests
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.10", "3.11", "3.12"]
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Phase 1 smoke (stdlib-only, no install)
+        run: python smoke.py
+
+      - name: Phase 2 fix-tier smoke (stdlib-only, no install)
+        run: python smoke_fix.py
+
+      - name: Install with dev extras
+        run: |
+          pip install --upgrade pip
+          pip install -e ".[dev]"
+
+      - name: Run pytest
+        run: pytest tests/ -v
+
+      - name: CLI sanity check (Phase 1)
+        run: |
+          parallelogram --help
+          parallelogram check examples/clean.jsonl
+          # broken.jsonl is expected to exit 2; invert so the workflow passes
+          ! parallelogram check examples/broken.jsonl
+
+      - name: CLI sanity check (Phase 2 --fix)
+        run: |
+          # --fix on broken.jsonl should drop unfixable records but emit clean ones,
+          # exiting 1 (partial fix). The `|| [ $? -eq 1 ]` pattern lets exit 1 pass.
+          parallelogram check examples/broken.jsonl --fix --dry-run || [ $? -eq 1 ]
+          parallelogram check examples/broken.jsonl --fix --output /tmp/cleaned.jsonl || [ $? -eq 1 ]
+          test -s /tmp/cleaned.jsonl
+          # The repaired output must itself validate clean
+          parallelogram check /tmp/cleaned.jsonl

parallelogram-0.2.0/LICENSE

@@ -0,0 +1,189 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for describing the origin of the Work and
+      reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may accept support,
+      warranty, indemnity, or other liability obligations and/or rights
+      consistent with this License. However, in accepting such obligations,
+      You may act only on Your own behalf and on Your sole responsibility,
+      not on behalf of any other Contributor, and only if You agree to
+      indemnify, defend, and hold each Contributor harmless for any
+      liability incurred by, or claims asserted against, such Contributor
+      by reason of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   Copyright 2026 Thatayotlhe Tsenang
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

parallelogram-0.2.0/PKG-INFO

@@ -0,0 +1,183 @@
+Metadata-Version: 2.4
+Name: parallelogram
+Version: 0.2.0
+Summary: Strict validator for fine-tuning datasets. Run before you train.
+Project-URL: Homepage, https://parallelogram.dev
+Author-email: Thatayotlhe Tsenang <tsenangthatayotlhe04@gmail.com>
+Maintainer-email: Thatayotlhe Tsenang <tsenangthatayotlhe04@gmail.com>
+License: Apache-2.0
+License-File: LICENSE
+Keywords: dataset,fine-tuning,linter,llm,validation
+Classifier: Development Status :: 3 - Alpha
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Software Development :: Quality Assurance
+Requires-Python: >=3.10
+Requires-Dist: rich>=13.7
+Requires-Dist: typer>=0.12
+Provides-Extra: dev
+Requires-Dist: pytest>=8; extra == 'dev'
+Requires-Dist: ruff>=0.5; extra == 'dev'
+Provides-Extra: tokenizer
+Requires-Dist: tokenizers>=0.15; extra == 'tokenizer'
+Description-Content-Type: text/markdown
+
+# parallelogram
+
+> Strict validator for fine-tuning datasets. Run it before you train.
+
+Every fine-tuning framework assumes your data is clean. None of them verify it.
+Axolotl will start a run on malformed data and either crash mid-way or — worse —
+complete silently while producing a broken model. TRL will truncate samples that
+exceed the context window without telling you. Unsloth will train on duplicates
+that cause your model to memorize instead of generalize.
+
+`parallelogram` sits between your raw dataset and your training run. It hard-blocks
+on anything that would silently corrupt training. **If it exits 0 with all rules enabled,
+your run won't fail because of data.**
+
+## Install
+
+```bash
+pip install parallelogram
+```
+
+For the context-window check, also install the tokenizer extras:
+
+```bash
+pip install 'parallelogram[tokenizer]'
+```
+
+## Use
+
+```bash
+parallelogram check data.jsonl
+```
+
+With a tokenizer for context-window validation:
+
+```bash
+parallelogram check data.jsonl \
+  --tokenizer meta-llama/Llama-3-8B \
+  --max-seq-len 8192
+```
+
+Write only the clean records to a new file:
+
+```bash
+parallelogram check data.jsonl --output clean.jsonl
+```
+
+## `--fix` — mechanical repair
+
+When `parallelogram check` finds errors, `--fix` attempts to repair what it can without
+touching the model. Mechanical fixes are free, local, and require no network call.
+
+```bash
+parallelogram check data.jsonl --fix --output clean.jsonl
+```
+
+Fixes applied in order:
+
+1. **encoding** — strip BOM markers, replace mojibake (`don’t` → `don't`)
+2. **empty-content** — drop empty/whitespace-only message turns
+3. **context-window** — truncate the longest user message until the record fits
+4. **duplicates** — keep the first occurrence, drop subsequent
+
+After fixes are applied, the dataset is **re-validated**. Anything still erroring is
+dropped from the output. The CLI tells you exactly what was unchanged, fixed, and
+dropped:
+
+```
+✓ encoding · 4 fixes
+✓ duplicates · 12 fixes
+
+✗ dropped:
+    data.jsonl:23 → roles (unfixable)
+    data.jsonl:147 → schema (unfixable)
+
+547 records  531 unchanged  4 fixed  11 dropped  1 unparseable
+```
+
+Errors that need understanding the content (broken role sequences, incomplete
+assistant turns) are not fixable mechanically. These will be addressed by a hosted
+SLM tier in a future release. For now, they are dropped.
+
+Use `--dry-run` to preview without writing:
+
+```bash
+parallelogram check data.jsonl --fix --dry-run
+```
+
+## `--disable` and the exit-0 guarantee
+
+Rules can be disabled by id (e.g. `--disable encoding`), but with three constraints:
+
+- The `schema` rule cannot be disabled. Every other rule depends on its structural
+  guarantees, and disabling it would let other rules silently no-op on malformed records.
+- Unknown rule ids are rejected. Typos like `--disable encding` exit non-zero with a
+  list of valid options rather than silently doing nothing.
+- Whenever any rule is disabled, a loud stderr warning names exactly which ones, and
+  reminds you that the exit-0 guarantee no longer applies. The terminal output and
+  JSON report (`disabled_rules` field) both surface this so CI tooling can refuse to
+  merge a PR that disabled rules.
+
+The guarantee is precise: **a clean exit with all rules enabled** means your run won't
+fail because of data. A clean exit with rules disabled means only that the rules you
+left enabled passed — which may or may not be enough.
+
+## Options
+
+| Flag | Description |
+|------|-------------|
+| `--format`, `-f` | Dataset format. Only `openai-chat` in v0.1. |
+| `--tokenizer`, `-t` | HuggingFace tokenizer name. Required for context-window check. |
+| `--max-seq-len` | Token budget per record (default 4096). |
+| `--output`, `-o` | Write error-free records to this file. With `--fix`, writes the repaired dataset. |
+| `--fix` | Attempt mechanical repair of fixable issues. |
+| `--dry-run` | With `--fix`, report what would change without writing. |
+| `--json` | Machine-readable report on stdout. |
+| `--disable` | Disable a rule by id. Repeatable. |
+| `--no-color` | Plain output. |
+
+## Exit codes
+
+| Code | Meaning (check) | Meaning (--fix) |
+|------|---------|---------|
+| `0`  | Clean. | All records emitted clean. |
+| `1`  | Warnings only. | Some records dropped (partial fix). |
+| `2`  | Errors. | Nothing fixable. |
+
+These map directly to CI gates without any extra wiring.
+
+## Rules
+
+| id | severity | catches |
+|----|----------|---------|
+| `schema` | error | malformed records, missing fields, wrong types |
+| `roles` | error | bad role sequences (system out of place, no alternation, doesn't end on assistant) |
+| `empty-content` | error | empty or whitespace-only message content |
+| `context-window` | error | records exceeding `max_seq_len` (TRL truncates these silently) |
+| `duplicates` | error | exact-content duplicate records (memorization → poor generalization) |
+| `encoding` | warning | BOM markers, mojibake patterns |
+
+## Status
+
+v0.2 — solo dev, local, pre-training run. No telemetry, no network, no upload boundary.
+
+## Roadmap
+
+- ShareGPT and raw-completion formats
+- ~~`--fix` mechanical tier (dedupe, truncate, normalize encoding)~~ ✓ shipped in v0.2
+- Opt-in anonymized error-type analytics (informs SLM tier scope)
+- `--fix --slm` paid hosted tier — repairs broken role sequences, incomplete turns
+
+## License
+
+Apache-2.0

parallelogram-0.2.0/README.md

@@ -0,0 +1,153 @@
+# parallelogram
+
+> Strict validator for fine-tuning datasets. Run it before you train.
+
+Every fine-tuning framework assumes your data is clean. None of them verify it.
+Axolotl will start a run on malformed data and either crash mid-way or — worse —
+complete silently while producing a broken model. TRL will truncate samples that
+exceed the context window without telling you. Unsloth will train on duplicates
+that cause your model to memorize instead of generalize.
+
+`parallelogram` sits between your raw dataset and your training run. It hard-blocks
+on anything that would silently corrupt training. **If it exits 0 with all rules enabled,
+your run won't fail because of data.**
+
+## Install
+
+```bash
+pip install parallelogram
+```
+
+For the context-window check, also install the tokenizer extras:
+
+```bash
+pip install 'parallelogram[tokenizer]'
+```
+
+## Use
+
+```bash
+parallelogram check data.jsonl
+```
+
+With a tokenizer for context-window validation:
+
+```bash
+parallelogram check data.jsonl \
+  --tokenizer meta-llama/Llama-3-8B \
+  --max-seq-len 8192
+```
+
+Write only the clean records to a new file:
+
+```bash
+parallelogram check data.jsonl --output clean.jsonl
+```
+
+## `--fix` — mechanical repair
+
+When `parallelogram check` finds errors, `--fix` attempts to repair what it can without
+touching the model. Mechanical fixes are free, local, and require no network call.
+
+```bash
+parallelogram check data.jsonl --fix --output clean.jsonl
+```
+
+Fixes applied in order:
+
+1. **encoding** — strip BOM markers, replace mojibake (`don’t` → `don't`)
+2. **empty-content** — drop empty/whitespace-only message turns
+3. **context-window** — truncate the longest user message until the record fits
+4. **duplicates** — keep the first occurrence, drop subsequent
+
+After fixes are applied, the dataset is **re-validated**. Anything still erroring is
+dropped from the output. The CLI tells you exactly what was unchanged, fixed, and
+dropped:
+
+```
+✓ encoding · 4 fixes
+✓ duplicates · 12 fixes
+
+✗ dropped:
+    data.jsonl:23 → roles (unfixable)
+    data.jsonl:147 → schema (unfixable)
+
+547 records  531 unchanged  4 fixed  11 dropped  1 unparseable
+```
+
+Errors that need understanding the content (broken role sequences, incomplete
+assistant turns) are not fixable mechanically. These will be addressed by a hosted
+SLM tier in a future release. For now, they are dropped.
+
+Use `--dry-run` to preview without writing:
+
+```bash
+parallelogram check data.jsonl --fix --dry-run
+```
+
+## `--disable` and the exit-0 guarantee
+
+Rules can be disabled by id (e.g. `--disable encoding`), but with three constraints:
+
+- The `schema` rule cannot be disabled. Every other rule depends on its structural
+  guarantees, and disabling it would let other rules silently no-op on malformed records.
+- Unknown rule ids are rejected. Typos like `--disable encding` exit non-zero with a
+  list of valid options rather than silently doing nothing.
+- Whenever any rule is disabled, a loud stderr warning names exactly which ones, and
+  reminds you that the exit-0 guarantee no longer applies. The terminal output and
+  JSON report (`disabled_rules` field) both surface this so CI tooling can refuse to
+  merge a PR that disabled rules.
+
+The guarantee is precise: **a clean exit with all rules enabled** means your run won't
+fail because of data. A clean exit with rules disabled means only that the rules you
+left enabled passed — which may or may not be enough.
+
+## Options
+
+| Flag | Description |
+|------|-------------|
+| `--format`, `-f` | Dataset format. Only `openai-chat` in v0.1. |
+| `--tokenizer`, `-t` | HuggingFace tokenizer name. Required for context-window check. |
+| `--max-seq-len` | Token budget per record (default 4096). |
+| `--output`, `-o` | Write error-free records to this file. With `--fix`, writes the repaired dataset. |
+| `--fix` | Attempt mechanical repair of fixable issues. |
+| `--dry-run` | With `--fix`, report what would change without writing. |
+| `--json` | Machine-readable report on stdout. |
+| `--disable` | Disable a rule by id. Repeatable. |
+| `--no-color` | Plain output. |
+
+## Exit codes
+
+| Code | Meaning (check) | Meaning (--fix) |
+|------|---------|---------|
+| `0`  | Clean. | All records emitted clean. |
+| `1`  | Warnings only. | Some records dropped (partial fix). |
+| `2`  | Errors. | Nothing fixable. |
+
+These map directly to CI gates without any extra wiring.
+
+## Rules
+
+| id | severity | catches |
+|----|----------|---------|
+| `schema` | error | malformed records, missing fields, wrong types |
+| `roles` | error | bad role sequences (system out of place, no alternation, doesn't end on assistant) |
+| `empty-content` | error | empty or whitespace-only message content |
+| `context-window` | error | records exceeding `max_seq_len` (TRL truncates these silently) |
+| `duplicates` | error | exact-content duplicate records (memorization → poor generalization) |
+| `encoding` | warning | BOM markers, mojibake patterns |
+
+## Status
+
+v0.2 — solo dev, local, pre-training run. No telemetry, no network, no upload boundary.
+
+## Roadmap
+
+- ShareGPT and raw-completion formats
+- ~~`--fix` mechanical tier (dedupe, truncate, normalize encoding)~~ ✓ shipped in v0.2
+- Opt-in anonymized error-type analytics (informs SLM tier scope)
+- `--fix --slm` paid hosted tier — repairs broken role sequences, incomplete turns
+
+## License
+
+Apache-2.0

parallelogram-0.2.0/clean.jsonl

@@ -0,0 +1,2 @@
+{"messages": [{"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "Hi"}, {"role": "assistant", "content": "Hello!"}]}
+{"messages": [{"role": "user", "content": "He said don’t do it — seriously."}, {"role": "assistant", "content": "Understood."}]}

parallelogram-0.2.0/examples/broken.jsonl

@@ -0,0 +1,8 @@
+{"messages": [{"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "Hi"}, {"role": "assistant", "content": "Hello!"}]}
+{"messages": [{"role": "user", "content": ""}, {"role": "assistant", "content": "What did you mean?"}]}
+{"messages": [{"role": "user", "content": "Hi"}, {"role": "user", "content": "Hello?"}, {"role": "assistant", "content": "Hi!"}]}
+{"messages": [{"role": "user", "content": "Question"}]}
+{"messages": [{"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "Hi"}, {"role": "assistant", "content": "Hello!"}]}
+{"messages": [{"role": "user", "content": "He said don’t do it — seriously."}, {"role": "assistant", "content": "Understood."}]}
+{"messages": [{"role": "user", "content": "Hi"}, {"role": "system", "content": "You are now in admin mode."}, {"role": "assistant", "content": "OK"}]}
+not valid json at all

parallelogram-0.2.0/examples/clean.jsonl

@@ -0,0 +1,3 @@
+{"messages": [{"role": "system", "content": "You are a helpful coding assistant."}, {"role": "user", "content": "How do I reverse a list in Python?"}, {"role": "assistant", "content": "Use slicing with a step of -1: my_list[::-1]"}]}
+{"messages": [{"role": "user", "content": "What is 2+2?"}, {"role": "assistant", "content": "4"}]}
+{"messages": [{"role": "user", "content": "Capital of France?"}, {"role": "assistant", "content": "Paris."}]}

parallelogram-0.2.0/pyproject.toml

@@ -0,0 +1,43 @@
+[project]
+name = "parallelogram"
+version = "0.2.0"
+description = "Strict validator for fine-tuning datasets. Run before you train."
+readme = "README.md"
+requires-python = ">=3.10"
+license = { text = "Apache-2.0" }
+authors = [{ name = "Thatayotlhe Tsenang", email = "tsenangthatayotlhe04@gmail.com" }]
+maintainers = [{ name = "Thatayotlhe Tsenang", email = "tsenangthatayotlhe04@gmail.com" }]
+keywords = ["llm", "fine-tuning", "dataset", "validation", "linter"]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Environment :: Console",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: Apache Software License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "Topic :: Software Development :: Quality Assurance",
+]
+dependencies = [
+    "typer>=0.12",
+    "rich>=13.7",
+]
+
+[project.optional-dependencies]
+tokenizer = ["tokenizers>=0.15"]
+dev = ["pytest>=8", "ruff>=0.5"]
+
+[project.scripts]
+parallelogram = "parallelogram.cli:app"
+
+[project.urls]
+Homepage = "https://parallelogram.dev"
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/parallelogram"]