rnow 0.2.4__py3-none-any.whl → 0.3.9__py3-none-any.whl

rnow/templates/tutorial-tool/config.yml

@@ -9,7 +9,7 @@ data:
   batch_size: 32
   group_size: 16
 model:
-  path: Qwen/Qwen3-8B
+  path: Qwen/Qwen3-30B-A3B-Instruct-2507
   qlora_rank: 32
   name: "BrowseComp Agent"
   description: "Multi-turn RL model trained on BrowseComp web research tasks"

{rnow-0.2.4.dist-info → rnow-0.3.9.dist-info}/METADATA

@@ -1,8 +1,8 @@
 Metadata-Version: 2.4
 Name: rnow
-Version: 0.2.4
+Version: 0.3.9
 Summary: ReinforceNow CLI - Reinforcement Learning platform command-line interface
-Requires-Python: >=3.10
+Requires-Python: <3.15,>=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: click>=8.0.0
@@ -16,6 +16,7 @@ Requires-Dist: tokenizers>=0.15.0
 Requires-Dist: openai-harmony>=0.0.8
 Provides-Extra: test
 Requires-Dist: tinker-cookbook>=0.1.0; extra == "test"
+Requires-Dist: transformers>=4.40.0; extra == "test"
 Provides-Extra: api
 Requires-Dist: fastapi>=0.68.0; extra == "api"
 Requires-Dist: uvicorn>=0.15.0; extra == "api"
@@ -23,6 +24,7 @@ Provides-Extra: mcp
 Requires-Dist: fastmcp>=0.1.0; extra == "mcp"
 Provides-Extra: all
 Requires-Dist: tinker-cookbook>=0.1.0; extra == "all"
+Requires-Dist: transformers>=4.40.0; extra == "all"
 Requires-Dist: fastapi>=0.68.0; extra == "all"
 Requires-Dist: uvicorn>=0.15.0; extra == "all"
 Requires-Dist: fastmcp>=0.1.0; extra == "all"
@@ -38,7 +40,7 @@ Dynamic: license-file
 
 [![PyPI version](https://img.shields.io/pypi/v/rnow?color=blue)](https://pypi.org/project/rnow/)
 [![Docs](https://img.shields.io/badge/docs-reinforcenow.ai-blue)](https://reinforcenow.ai/docs)
-[![Follow on X](https://img.shields.io/badge/Follow_on_X-@reinforcenow-black?labelColor=white)](https://x.com/reinforcenowai)
+[![Follow on X](https://img.shields.io/badge/Follow_on_X-@reinforcenow-black?labelColor=white)](https://x.com/reinforcenow)
 [![MIT License](https://img.shields.io/badge/license-MIT-green)](./LICENSE)
 
 </div>
@@ -49,22 +51,34 @@ See the [documentation](https://www.reinforcenow.ai/docs/getting-started/quickst
 
 # Quick Start
 
-### 1. Install
+### 1. Install uv (Python package manager)
 
 ```bash
-pip install rnow
+# macOS/Linux:
+$ curl -LsSf https://astral.sh/uv/install.sh | sh
+
+# Windows:
+PS> powershell -c "irm https://astral.sh/uv/install.ps1 | iex"
+```
+
+### 2. Install ReinforceNow
+
+```bash
+uv init && uv venv --python 3.11
+source .venv/bin/activate  # Windows: .\.venv\Scripts\Activate.ps1
+uv pip install rnow
 ```
 
-### 2. Authenticate
+### 3. Authenticate
 
 ```bash
 rnow login
 ```
 
-### 3. Create & Run Your First Project
+### 4. Create & Run Your First Project
 
 ```bash
-rnow init --template rl-single
+rnow init --template sft
 rnow run
 ```
 
@@ -123,7 +137,7 @@ Create a `train.jsonl` file with your prompts and reward assignments:
 
 # Contributing
 
-We welcome contributions! ❤️ Please open an issue to discuss your ideas before submitting a PR.
+We welcome contributions! ❤️ Please open an issue to discuss your ideas before submitting a PR
 
 <br>
 <div align="center">

{rnow-0.2.4.dist-info → rnow-0.3.9.dist-info}/RECORD

@@ -1,22 +1,22 @@
 rnow/__init__.py,sha256=eZZ4ojxcXfvZy6DKVUCnABXwaa6qJG2i9Jaw0UG4UNk,105
 rnow/__main__.py,sha256=I7C-8zwJh2X48frHLIp256g9wNyIvs6EJbxrGg70lmQ,141
-rnow/models.py,sha256=DP2s8QTmXyPlzukWIvQPLkfuyKPmyszdnAcBPBOHGY0,9194
+rnow/models.py,sha256=4gcjXv3reuRw3ICh60RSrm9LwomNCRP_g0Tsj0sC-lM,12001
 rnow/cli/__init__.py,sha256=9jch1FcYtWwO3xa239DQkoJDo07xna4qL9m_IS_kHR8,103
 rnow/cli/auth.py,sha256=M12S4pzocOlRqUM5LLGJDrPfRREh4_wqEyIiLs65Wr4,1797
 rnow/cli/blob.py,sha256=ZdGNoeT_q--K60qbzNRllP9ejYcbHAf5_PrHmQcu43o,2739
-rnow/cli/commands.py,sha256=2kOIw3fi68gR5C19ALFeCb_0GysB7CYkUFWBHX5klWQ,84411
+rnow/cli/commands.py,sha256=NXeicEgyAksvy25R5VH2Fm5LSAyaGG8Gp8LBVWRidKk,89624
 rnow/cli/common.py,sha256=ayRStKviHMFatb1nJg6zrUzl_hfdmyoKNTXLFLQrmCA,679
 rnow/cli/cube.py,sha256=oZzhKQia58DPsp78QtWntDX4OZmQHSNyRxWfw4kMzgk,8614
 rnow/cli/main.py,sha256=EpF3XUxEVIwwgO3tblKAdxWf0WW3lntHGkTeK5nwsQE,1169
-rnow/cli/test.py,sha256=ATnnnrfLcyJm7RFFC6J61st-9-dbIlG-3ZiuqAvY-Cs,24854
+rnow/cli/test.py,sha256=JlVZpckXsvXXQHnH9zatPyh2AilFG3zJAiHSySt7M8M,26098
 rnow/cli/token_count.py,sha256=2F22yeg9R-Ai9TmTZsloi9RHDlVsQ9YJ9oX-zN2TUIY,9930
-rnow/core/__init__.py,sha256=uGQliIeuxFxdswtob6Jmkw8gu3FHpN24DWtIQQSMRLA,737
-rnow/core/reward.py,sha256=DVTKeTtYgSZXxVqglW-KMEozSnyrt0ZpxupjPyn9r_8,11529
-rnow/core/tool.py,sha256=x0F_1PyGdzV8S-D67KcVX6ZrXD2oTkiZDTQUy0L4vIY,15927
-rnow/templates/deepseek-aha/config.yml,sha256=MhbpfjJa3DF6jGy5puSsLQxYcptr-lDa1DRN9_v9f18,578
+rnow/core/__init__.py,sha256=nztnclAYoccH92KcT4lcFHX4c4Niu7FCSZHyYU9eJDQ,825
+rnow/core/reward.py,sha256=K9u6ukYABNIVNc21g5tqBcr1CLtp0NKlI2lvT-NNJMU,12808
+rnow/core/tool.py,sha256=ISIgRIWlMXfSUKFozIQ7N71Bswy-yBZTGbIvhXYcHtE,17025
+rnow/templates/deepseek-aha/config.yml,sha256=_r1yoFraOwxQsmkOxTksbS4J9aBpZSlq--NtLE6iGHg,573
 rnow/templates/deepseek-aha/rewards.py,sha256=Wawuu5wU8j3h4ggvFd6tmhSUOOjNuw7p_UZvIFt5Usw,1018
 rnow/templates/deepseek-aha/train.jsonl,sha256=TvX96zObfGxYc5KLQNV9rlwrqaYSx_08iHyTb3VqybU,321106
-rnow/templates/mcp-tavily/config.yml,sha256=3mwy5fN8S7-q7uXgZN_Xg7JXYCDePJFy0WVWmojYX7s,683
+rnow/templates/mcp-tavily/config.yml,sha256=xjcZfx-N7UL4Sq-qrxrNPxaCP-6GkTjlXz0mU_HpVQc,702
 rnow/templates/mcp-tavily/requirements.txt,sha256=1ZpQJZiqb5W7yO6tXGAqVUSWMilSTadxqVmwsRhmgz4,17
 rnow/templates/mcp-tavily/rewards.py,sha256=5z6dI2AO9WeSIIVfhx9LOBMgVGR23rP8Cis4Xyndq4M,776
 rnow/templates/mcp-tavily/train.jsonl,sha256=YjfEErhtfuJko3ZvzHFsNXTEmxNnSNMMTWZHgwg4d9g,225204
@@ -28,29 +28,29 @@ rnow/templates/rl-nextjs/config.yml,sha256=5b9Gs7thcqjUXJ6bv0chlxQdvsdTARyRduWES
 rnow/templates/rl-nextjs/requirements.txt,sha256=Ul1DVTJGLJBXgqujOiyIDLKXgkvl6XlpjNexy4fGoMc,36
 rnow/templates/rl-nextjs/rewards.py,sha256=IAHhWIJY9ah3YksoHkimQaC1folP-FO9Bgae27xhmvA,14625
 rnow/templates/rl-nextjs/train.jsonl,sha256=98mb5S81p6a6lgG4uP35IEIcP_cir0CfJ7BYx0rHMp0,522550
-rnow/templates/rl-single/config.yml,sha256=K6kMCDzSsUc9yRvacJrdb7bZjMzUmhNX5j7DqBOhOw4,541
+rnow/templates/rl-single/config.yml,sha256=eqXCCDcitp9Kxolglc8uDmYXpzF_SxIB2EkIw__sisk,522
 rnow/templates/rl-single/requirements.txt,sha256=yJceROMgmW4o1Vb4oOo7cMPK597rUw-GxcRkYDWnjrk,19
 rnow/templates/rl-single/rewards.py,sha256=gk4ZYEF8RyH1zcMg_K1Fp23gmDq4JmppN9_vR8L3nUM,426
-rnow/templates/rl-single/train.jsonl,sha256=hBq4VVIdEsWfG4GrwSW5AotbNrN7Z9bTDmbobwsLcHk,477718
-rnow/templates/rl-tools/config.yml,sha256=NpZZPVGIV7OQHNaiKSFHSs3bcyduDtPKaRzhFekOZXE,574
-rnow/templates/rl-tools/env.py,sha256=mPzuYS6cNia9Q-sxn3h8a_uyYsXAHOrxk9oYfeIg4gA,1151
+rnow/templates/rl-single/train.jsonl,sha256=onEU-2g9Pl4aNfpAvFOWopojHRYwp7QV2XZTg22aHhg,43338
+rnow/templates/rl-tools/config.yml,sha256=Dzd2WnIdRzvG4WHhRUrLe91rGQx2BzImELYzZV8VDsw,593
 rnow/templates/rl-tools/requirements.txt,sha256=WonZpO2bsLj-HWyU9B5BzQ0qagcgF2zNcnjRvmOFrik,57
 rnow/templates/rl-tools/rewards.py,sha256=5z6dI2AO9WeSIIVfhx9LOBMgVGR23rP8Cis4Xyndq4M,776
+rnow/templates/rl-tools/tools.py,sha256=mPzuYS6cNia9Q-sxn3h8a_uyYsXAHOrxk9oYfeIg4gA,1151
 rnow/templates/rl-tools/train.jsonl,sha256=YjfEErhtfuJko3ZvzHFsNXTEmxNnSNMMTWZHgwg4d9g,225204
 rnow/templates/sft/config.yml,sha256=2o65W43zSEOp63Y0t_sOSeyBBI_5UpLUj3LrH_FHhRw,393
 rnow/templates/sft/train.jsonl,sha256=e3IlKIHj7x2neTTnpOnbc5hNsdT8gwEBBSalKwWHErU,508674
-rnow/templates/tutorial-reward/config.yml,sha256=K6kMCDzSsUc9yRvacJrdb7bZjMzUmhNX5j7DqBOhOw4,541
+rnow/templates/tutorial-reward/config.yml,sha256=eqXCCDcitp9Kxolglc8uDmYXpzF_SxIB2EkIw__sisk,522
 rnow/templates/tutorial-reward/requirements.txt,sha256=yJceROMgmW4o1Vb4oOo7cMPK597rUw-GxcRkYDWnjrk,19
 rnow/templates/tutorial-reward/rewards.py,sha256=ue6tzd7wDjogKwE28inQZjwjfK_F0Y_mYZvVP1PnzVY,440
-rnow/templates/tutorial-reward/train.jsonl,sha256=hBq4VVIdEsWfG4GrwSW5AotbNrN7Z9bTDmbobwsLcHk,477718
-rnow/templates/tutorial-tool/config.yml,sha256=vcxEImXofTveXl4jKPL2t-2oXkj6rGN1luAjucjH-0Y,573
-rnow/templates/tutorial-tool/env.py,sha256=2ziGzkDLOzrCGEcYPgk7-bQi80EL4-hiJLG0MMxNIS0,166
+rnow/templates/tutorial-reward/train.jsonl,sha256=onEU-2g9Pl4aNfpAvFOWopojHRYwp7QV2XZTg22aHhg,43338
+rnow/templates/tutorial-tool/config.yml,sha256=44IhP2GFZEVS0zb5psIYsTWqfDRoDCPpkyztTKPQnP8,592
 rnow/templates/tutorial-tool/requirements.txt,sha256=WonZpO2bsLj-HWyU9B5BzQ0qagcgF2zNcnjRvmOFrik,57
 rnow/templates/tutorial-tool/rewards.py,sha256=jxik_6dZh3gTlMsmgbIYz7xQVn9EAqR_mXpWfd4rPe0,182
+rnow/templates/tutorial-tool/tools.py,sha256=2ziGzkDLOzrCGEcYPgk7-bQi80EL4-hiJLG0MMxNIS0,166
 rnow/templates/tutorial-tool/train.jsonl,sha256=wUkObyXyR2k7nn89CCscE3eS-IOwBvn_ar-LGEw8LJE,1216463
-rnow-0.2.4.dist-info/licenses/LICENSE,sha256=zp3v0kxFKoto-UBNj-yWfZv5LuLWI3QRLt3EFKrMkDw,1069
-rnow-0.2.4.dist-info/METADATA,sha256=c2_y9CrIoDTRtrl3AR-bMnhP3IFro42Y0SM4inDi1hw,4096
-rnow-0.2.4.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-rnow-0.2.4.dist-info/entry_points.txt,sha256=UDq6s3IvmtJPGQskgZyvoFmSI6sUExM9VS0sGep4Eik,44
-rnow-0.2.4.dist-info/top_level.txt,sha256=7UzwktxX6U3A5mExEBPKZB2TlxDAYEBywZeJ4uwNPyY,5
-rnow-0.2.4.dist-info/RECORD,,
+rnow-0.3.9.dist-info/licenses/LICENSE,sha256=zp3v0kxFKoto-UBNj-yWfZv5LuLWI3QRLt3EFKrMkDw,1069
+rnow-0.3.9.dist-info/METADATA,sha256=dZzxXblOxUhgF4F5GF2CZqL7InW0QRv8YSgyF2fAMLI,4511
+rnow-0.3.9.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+rnow-0.3.9.dist-info/entry_points.txt,sha256=UDq6s3IvmtJPGQskgZyvoFmSI6sUExM9VS0sGep4Eik,44
+rnow-0.3.9.dist-info/top_level.txt,sha256=7UzwktxX6U3A5mExEBPKZB2TlxDAYEBywZeJ4uwNPyY,5
+rnow-0.3.9.dist-info/RECORD,,