初始化项目,由ModelHub XC社区提供模型
Model: MaliDDD/deepseek_legal_L_8B_8n Source: Original Platform
This commit is contained in:
67
grpo_bonus1/README.md
Normal file
67
grpo_bonus1/README.md
Normal file
@@ -0,0 +1,67 @@
|
||||
---
|
||||
base_model: Qwen/Qwen3-8B
|
||||
library_name: transformers
|
||||
model_name: grpo_bonus1
|
||||
tags:
|
||||
- generated_from_trainer
|
||||
- trl
|
||||
- grpo
|
||||
licence: license
|
||||
---
|
||||
|
||||
# Model Card for grpo_bonus1
|
||||
|
||||
This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B).
|
||||
It has been trained using [TRL](https://github.com/huggingface/trl).
|
||||
|
||||
## Quick start
|
||||
|
||||
```python
|
||||
from transformers import pipeline
|
||||
|
||||
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
||||
generator = pipeline("text-generation", model="None", device="cuda")
|
||||
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
||||
print(output["generated_text"])
|
||||
```
|
||||
|
||||
## Training procedure
|
||||
|
||||
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/madisonlijingxuan-ucla/agent_routing/runs/amlavul4)
|
||||
|
||||
|
||||
|
||||
This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
|
||||
|
||||
### Framework versions
|
||||
|
||||
- TRL: 1.5.0
|
||||
- Transformers: 5.8.1
|
||||
- Pytorch: 2.12.0
|
||||
- Datasets: 4.8.5
|
||||
- Tokenizers: 0.22.2
|
||||
|
||||
## Citations
|
||||
|
||||
Cite GRPO as:
|
||||
|
||||
```bibtex
|
||||
@article{shao2024deepseekmath,
|
||||
title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
|
||||
author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
|
||||
year = 2024,
|
||||
eprint = {arXiv:2402.03300},
|
||||
}
|
||||
```
|
||||
|
||||
Cite TRL as:
|
||||
|
||||
```bibtex
|
||||
@software{vonwerra2020trl,
|
||||
title = {{TRL: Transformers Reinforcement Learning}},
|
||||
author = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
|
||||
license = {Apache-2.0},
|
||||
url = {https://github.com/huggingface/trl},
|
||||
year = {2020}
|
||||
}
|
||||
```
|
||||
89
grpo_bonus1/chat_template.jinja
Normal file
89
grpo_bonus1/chat_template.jinja
Normal file
@@ -0,0 +1,89 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- messages[0].content + '\n\n' }}
|
||||
{%- endif %}
|
||||
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||
{%- else %}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
||||
{%- for message in messages[::-1] %}
|
||||
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
||||
{%- set ns.multi_step_tool = false %}
|
||||
{%- set ns.last_query_index = index %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- for message in messages %}
|
||||
{%- if message.content is string %}
|
||||
{%- set content = message.content %}
|
||||
{%- else %}
|
||||
{%- set content = '' %}
|
||||
{%- endif %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{%- set reasoning_content = '' %}
|
||||
{%- if message.reasoning_content is string %}
|
||||
{%- set reasoning_content = message.reasoning_content %}
|
||||
{%- else %}
|
||||
{%- if '</think>' in content %}
|
||||
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
||||
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- if loop.index0 > ns.last_query_index %}
|
||||
{%- if loop.last or (not loop.last and reasoning_content) %}
|
||||
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- if message.tool_calls %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if (loop.first and content) or (not loop.first) %}
|
||||
{{- '\n' }}
|
||||
{%- endif %}
|
||||
{%- if tool_call.function %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{%- if tool_call.arguments is string %}
|
||||
{{- tool_call.arguments }}
|
||||
{%- else %}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{%- endif %}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- content }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- if enable_thinking is defined and enable_thinking is false %}
|
||||
{{- '<think>\n\n</think>\n\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
3
grpo_bonus1/completions/completions_00001.parquet
Normal file
3
grpo_bonus1/completions/completions_00001.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:18fa0d77846f8862f8a7e70869fb99bc5e748f8f6c60a1659e12156ff1bfed8b
|
||||
size 40192
|
||||
3
grpo_bonus1/completions/completions_00002.parquet
Normal file
3
grpo_bonus1/completions/completions_00002.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d7e4448f2141ca54a34d965e3b32004be7eb289fb5faf74c31d3efdc4c7eada4
|
||||
size 45689
|
||||
3
grpo_bonus1/completions/completions_00003.parquet
Normal file
3
grpo_bonus1/completions/completions_00003.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5ad3ba795a7268158900f81629c08b078ead0195ce88a4cb311cd215f27a7764
|
||||
size 30225
|
||||
3
grpo_bonus1/completions/completions_00004.parquet
Normal file
3
grpo_bonus1/completions/completions_00004.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bda3a5cb45cb151849cb4ad1fba5c1e33c68a6a9dc05ffb062981c546c4b06c6
|
||||
size 37562
|
||||
3
grpo_bonus1/completions/completions_00005.parquet
Normal file
3
grpo_bonus1/completions/completions_00005.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:dc5ac5e9a18481bbd5002188f9956a5ed1d15cc7ebcf3c92c78552f07a6d4e28
|
||||
size 38047
|
||||
3
grpo_bonus1/completions/completions_00006.parquet
Normal file
3
grpo_bonus1/completions/completions_00006.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ff71fbc09f02a6c43b8c6d61d6b4eca0b721f6f75f1bb2277245b77b1ec080d0
|
||||
size 30900
|
||||
3
grpo_bonus1/completions/completions_00007.parquet
Normal file
3
grpo_bonus1/completions/completions_00007.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:39c28726f2ec324952ac185706c201c10d8bf129cbb3420877915e3332ff5a4d
|
||||
size 44230
|
||||
3
grpo_bonus1/completions/completions_00008.parquet
Normal file
3
grpo_bonus1/completions/completions_00008.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:dfd0cf818820420902de2fda9b7be1d29628c9015233a73dd8e215e2d86e4798
|
||||
size 22645
|
||||
3
grpo_bonus1/completions/completions_00009.parquet
Normal file
3
grpo_bonus1/completions/completions_00009.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0be7944cdddb58c0a180f9e191f0e997a5a31fecd97194bc031baf6c3f97bb7f
|
||||
size 32375
|
||||
3
grpo_bonus1/completions/completions_00010.parquet
Normal file
3
grpo_bonus1/completions/completions_00010.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d78556bb5e0997f494c9b442fcfe57243a418e95fe0ccb4433ff835eb8dce0df
|
||||
size 26381
|
||||
3
grpo_bonus1/completions/completions_00011.parquet
Normal file
3
grpo_bonus1/completions/completions_00011.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a2fb25d1e3f59de0ef8e3635db10c872a1c03941a9a2ec86aeeec6ac1559fdd8
|
||||
size 33874
|
||||
3
grpo_bonus1/completions/completions_00012.parquet
Normal file
3
grpo_bonus1/completions/completions_00012.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d2313689b07ffe47f564b497ebafe439f993b3ce2086c8afc2723e80ac821d91
|
||||
size 31581
|
||||
3
grpo_bonus1/completions/completions_00013.parquet
Normal file
3
grpo_bonus1/completions/completions_00013.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2dc36cdf36e3028b6d534f961be4d35b7a39d754308c263cb6fd0f1ae511ba25
|
||||
size 36098
|
||||
3
grpo_bonus1/completions/completions_00014.parquet
Normal file
3
grpo_bonus1/completions/completions_00014.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:55a12313fdd3ccaaf305b7282a737f90311733aeb85fcf12f663789b2ba45512
|
||||
size 40384
|
||||
3
grpo_bonus1/completions/completions_00015.parquet
Normal file
3
grpo_bonus1/completions/completions_00015.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:048315f468fd59ebe8b92dc53e0e6b567b1cd64fc0853cc7bff76f80558da19e
|
||||
size 30030
|
||||
3
grpo_bonus1/completions/completions_00016.parquet
Normal file
3
grpo_bonus1/completions/completions_00016.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4d071a58d5715d59dc3b70c77abf504116ea27a5eacaf8b6a41709da4b7861eb
|
||||
size 31690
|
||||
3
grpo_bonus1/completions/completions_00017.parquet
Normal file
3
grpo_bonus1/completions/completions_00017.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7e3490a86c018789ce57ce3a784bacf10ada2b9760de4563a496698e48755a9b
|
||||
size 36944
|
||||
3
grpo_bonus1/completions/completions_00018.parquet
Normal file
3
grpo_bonus1/completions/completions_00018.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:546727fa1d648f3cdbcd6eba2375038931438f9c8c8758eb8f747ac411822458
|
||||
size 33495
|
||||
3
grpo_bonus1/completions/completions_00019.parquet
Normal file
3
grpo_bonus1/completions/completions_00019.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c13d0326239c898bcba77d751f78dce938dcae409bc76d2e11aa822720dbe42f
|
||||
size 38603
|
||||
3
grpo_bonus1/completions/completions_00020.parquet
Normal file
3
grpo_bonus1/completions/completions_00020.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f9ab66787619fa9a0bd06d003b20a2c3dc83910315aeaa08e91606703e6a966b
|
||||
size 37566
|
||||
3
grpo_bonus1/completions/completions_00021.parquet
Normal file
3
grpo_bonus1/completions/completions_00021.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:77ecbf14b68e643a54dcffae218de9694d9bffa87be3fd429a23d8fb25fb788d
|
||||
size 35096
|
||||
3
grpo_bonus1/completions/completions_00022.parquet
Normal file
3
grpo_bonus1/completions/completions_00022.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:172699eec9f82da5a822e974629370b1d78ba32305a2cf06d3ecc8fd1f18acc2
|
||||
size 40682
|
||||
3
grpo_bonus1/completions/completions_00023.parquet
Normal file
3
grpo_bonus1/completions/completions_00023.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:047ee0d04ecf41ff2c3a7dee230e5564a0e7317137189a53d71812075a655bef
|
||||
size 38404
|
||||
3
grpo_bonus1/completions/completions_00024.parquet
Normal file
3
grpo_bonus1/completions/completions_00024.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0d9a2a7b1db5206c78c5d348a5fa00e7f3813591e5bf7370e8e216ab94f0c07a
|
||||
size 32974
|
||||
3
grpo_bonus1/completions/completions_00025.parquet
Normal file
3
grpo_bonus1/completions/completions_00025.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:706f00ae87e05b1ffba5d555bc40d6ff2e8ee56167bc05dbda2d93d69db45217
|
||||
size 36890
|
||||
3
grpo_bonus1/completions/completions_00026.parquet
Normal file
3
grpo_bonus1/completions/completions_00026.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:44a168fae49b974d74b079c2bef609973e88ae60726e4cca88f6280e2325a01b
|
||||
size 33781
|
||||
3
grpo_bonus1/completions/completions_00027.parquet
Normal file
3
grpo_bonus1/completions/completions_00027.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bbf802ab4bc21c0f69e6faa753eeb6a2c5a45ad555cdd38682fbf836005907e7
|
||||
size 37914
|
||||
3
grpo_bonus1/completions/completions_00028.parquet
Normal file
3
grpo_bonus1/completions/completions_00028.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a87ec40c6426632bdce20322886c32440cc3c5989fe25e32ea655b57309db35e
|
||||
size 40130
|
||||
3
grpo_bonus1/completions/completions_00029.parquet
Normal file
3
grpo_bonus1/completions/completions_00029.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:07cb31705482eb75e4b11f08c44df805c5f12ef424e0ebf9fe4f5a513e735cfa
|
||||
size 34197
|
||||
3
grpo_bonus1/completions/completions_00030.parquet
Normal file
3
grpo_bonus1/completions/completions_00030.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9cdc20b9dbe05dc38ac1b3571308dce1a83a54ec184ec5507d7e2daa88d05b6f
|
||||
size 36840
|
||||
3
grpo_bonus1/completions/completions_00031.parquet
Normal file
3
grpo_bonus1/completions/completions_00031.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:02eefe16f0391049e0a0c32f86272b00ceb959167badd9d38012e07361b9fd3b
|
||||
size 28089
|
||||
3
grpo_bonus1/completions/completions_00032.parquet
Normal file
3
grpo_bonus1/completions/completions_00032.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:97ad1c81702a02c1703fd535034a5b86cf832b59cd8535adadc4914d3872a95c
|
||||
size 33978
|
||||
3
grpo_bonus1/completions/completions_00033.parquet
Normal file
3
grpo_bonus1/completions/completions_00033.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4eb47bde1389677006b870294a26f24c3b4fde4a470319dd72f63ffc7f06f37b
|
||||
size 27630
|
||||
3
grpo_bonus1/completions/completions_00034.parquet
Normal file
3
grpo_bonus1/completions/completions_00034.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fdbd744021bc960d7b495016c30c864a2d8c02471e05392bf789aed7197d84ab
|
||||
size 33314
|
||||
3
grpo_bonus1/completions/completions_00035.parquet
Normal file
3
grpo_bonus1/completions/completions_00035.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1300bed23bc30d3f4e14637cc1666c9d301f57f1d6f56bdc2bc5f37003145a87
|
||||
size 41678
|
||||
3
grpo_bonus1/completions/completions_00036.parquet
Normal file
3
grpo_bonus1/completions/completions_00036.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5b2457887fa27f895656640b74de61c47167a4aa523bccdeaf63e759101b5f4d
|
||||
size 36251
|
||||
3
grpo_bonus1/completions/completions_00037.parquet
Normal file
3
grpo_bonus1/completions/completions_00037.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e611123d749fa9085086c7e2ed474b189f352edb67f7ff4bcb01886116579b86
|
||||
size 33365
|
||||
3
grpo_bonus1/completions/completions_00038.parquet
Normal file
3
grpo_bonus1/completions/completions_00038.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6336a78451265ffd4a4d80e60090d2e8d99980fae435ab50a3c51a25a71e918b
|
||||
size 34215
|
||||
3
grpo_bonus1/completions/completions_00039.parquet
Normal file
3
grpo_bonus1/completions/completions_00039.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f80bc39fb4eedcd494b72bb7eaff8893389c84e71f2031a23ddd30eaba52f3ae
|
||||
size 30687
|
||||
3
grpo_bonus1/completions/completions_00040.parquet
Normal file
3
grpo_bonus1/completions/completions_00040.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:04083014df2296e39f4e673212b375545c43ef56adec1e3495f36fed89359f80
|
||||
size 40997
|
||||
3
grpo_bonus1/completions/completions_00041.parquet
Normal file
3
grpo_bonus1/completions/completions_00041.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ca6bbd42408ce71c36b4bfd1319d4a24e9bd8e4367734a0be1bdb61f06fc1120
|
||||
size 42040
|
||||
3
grpo_bonus1/completions/completions_00042.parquet
Normal file
3
grpo_bonus1/completions/completions_00042.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:46116d88adf40b00fbb59c99275c6958c9d8fdcf047d936d87c3e1a4790701c9
|
||||
size 35041
|
||||
3
grpo_bonus1/completions/completions_00043.parquet
Normal file
3
grpo_bonus1/completions/completions_00043.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:15a70f645f7e189c14ea12a017bbc2a5b8d9d0a4e1b55ada306099c215ecb150
|
||||
size 32815
|
||||
3
grpo_bonus1/completions/completions_00044.parquet
Normal file
3
grpo_bonus1/completions/completions_00044.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:743e20fa396f63b9e6ec8709a6338f3c1901c6956e1ad44ac3efd077ac3e56f3
|
||||
size 24951
|
||||
3
grpo_bonus1/completions/completions_00045.parquet
Normal file
3
grpo_bonus1/completions/completions_00045.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4131630c63e44064479e796eb3f3c9e2ba7ec9fbcfba2ff6e1149cc0b9262ac7
|
||||
size 38541
|
||||
3
grpo_bonus1/completions/completions_00046.parquet
Normal file
3
grpo_bonus1/completions/completions_00046.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4d219fe37b8b032c13e2407231e04d6154f91d87838c517e53c62b4c16b1efd5
|
||||
size 30833
|
||||
3
grpo_bonus1/completions/completions_00047.parquet
Normal file
3
grpo_bonus1/completions/completions_00047.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7c297f78a0f8f49efb4f09edca2c38739c5bc0b238fce2cf9eb8e32a438bf82b
|
||||
size 34763
|
||||
3
grpo_bonus1/completions/completions_00048.parquet
Normal file
3
grpo_bonus1/completions/completions_00048.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fb0618716e8dbcdb1ef11470c3140196e148342b076acd02da229888ccd1e909
|
||||
size 31726
|
||||
3
grpo_bonus1/completions/completions_00049.parquet
Normal file
3
grpo_bonus1/completions/completions_00049.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:44edf34567609518f30b92ed2a7e15ec788c8a06ce6587d68c1353b0504bc5a4
|
||||
size 38223
|
||||
3
grpo_bonus1/completions/completions_00050.parquet
Normal file
3
grpo_bonus1/completions/completions_00050.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:892d67498c06854c1ac9fae0f77715f05725cc2551a81a8cc9d29368a36f36a1
|
||||
size 27536
|
||||
3
grpo_bonus1/completions/completions_00051.parquet
Normal file
3
grpo_bonus1/completions/completions_00051.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:11452408b2824e5ebb23419f01f53e2667df96af4afa1f97539193abd13dbc8e
|
||||
size 33294
|
||||
3
grpo_bonus1/completions/completions_00052.parquet
Normal file
3
grpo_bonus1/completions/completions_00052.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:20df3feca1b647d56f2455c46e24466bc55aab6b9d194cec0b2eb089ca0b8315
|
||||
size 25162
|
||||
3
grpo_bonus1/completions/completions_00053.parquet
Normal file
3
grpo_bonus1/completions/completions_00053.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cb3ddb59e54f36de2fcdb6a1f4a29f012d4defe6cc0429a6b8c1a7e329b693c9
|
||||
size 24680
|
||||
3
grpo_bonus1/completions/completions_00054.parquet
Normal file
3
grpo_bonus1/completions/completions_00054.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:257a4bed41d63bf9bee50b6919ae5e2ce6ef9c32c872949bb199f996dfe35fb1
|
||||
size 25462
|
||||
3
grpo_bonus1/completions/completions_00055.parquet
Normal file
3
grpo_bonus1/completions/completions_00055.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:800ec39b5fc312262648f659f818c800011f695e6ce12916004c18a808795005
|
||||
size 34483
|
||||
3
grpo_bonus1/completions/completions_00056.parquet
Normal file
3
grpo_bonus1/completions/completions_00056.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cbf3782358376d9a90b582b93a095defbaa2e5b8a64c011db7f5f5a74ea2609f
|
||||
size 32984
|
||||
3
grpo_bonus1/completions/completions_00057.parquet
Normal file
3
grpo_bonus1/completions/completions_00057.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bb57550594a17e7cb7e10c98fd298fdbdb01e46aff387845067a8688babfbd25
|
||||
size 35380
|
||||
3
grpo_bonus1/completions/completions_00058.parquet
Normal file
3
grpo_bonus1/completions/completions_00058.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:12e4d37baa460240454fdde9937edf623f1ab6b03ba5ec8e45d714e28760f284
|
||||
size 30500
|
||||
3
grpo_bonus1/completions/completions_00059.parquet
Normal file
3
grpo_bonus1/completions/completions_00059.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:00186d8d5ccd71c45c3055231d56ae428af5cfadf9252e9b3a436203d9a12a5c
|
||||
size 31634
|
||||
3
grpo_bonus1/completions/completions_00060.parquet
Normal file
3
grpo_bonus1/completions/completions_00060.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9664a46b06d68663dd303b6067d711d20394d4da9b358ee61750c94406a9ba8c
|
||||
size 38073
|
||||
3
grpo_bonus1/completions/completions_00061.parquet
Normal file
3
grpo_bonus1/completions/completions_00061.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a92ae3bb156cddfd3cdd90df8c4027c366cd324318fe0e661648e29e21c9cde8
|
||||
size 25798
|
||||
3
grpo_bonus1/completions/completions_00062.parquet
Normal file
3
grpo_bonus1/completions/completions_00062.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:943fe930e67e4b7da90cc818ce1ab21f11503d68ab0b944ed5fc0c3995588c46
|
||||
size 25926
|
||||
3
grpo_bonus1/completions/completions_00063.parquet
Normal file
3
grpo_bonus1/completions/completions_00063.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7522bd385cd458123416b29ac7bc1720855be608571b78edc739d588067a9a32
|
||||
size 26616
|
||||
3
grpo_bonus1/completions/completions_00064.parquet
Normal file
3
grpo_bonus1/completions/completions_00064.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:835bac25689b6df6b90281550100a6b5f25b24a3cef43b94b980529a8b0a0955
|
||||
size 28446
|
||||
3
grpo_bonus1/completions/completions_00065.parquet
Normal file
3
grpo_bonus1/completions/completions_00065.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d88d754b6ffda41e55207508cfe2e739d64b19337ca61da2a0854038d15bc61d
|
||||
size 34163
|
||||
3
grpo_bonus1/completions/completions_00066.parquet
Normal file
3
grpo_bonus1/completions/completions_00066.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:39c2abf1ccbb906d23a90ca403cb51a2bc48c0911fcae131e057b29744ebdcda
|
||||
size 28750
|
||||
3
grpo_bonus1/completions/completions_00067.parquet
Normal file
3
grpo_bonus1/completions/completions_00067.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cdc77d999f16f041739ae630941221c636ab4a39cc1441b9562e78fa4e46d17b
|
||||
size 27193
|
||||
3
grpo_bonus1/completions/completions_00068.parquet
Normal file
3
grpo_bonus1/completions/completions_00068.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:546513db6bc61be9221023b1e6444a9758ae0e40cdd9a37a903689a7d33cd95d
|
||||
size 25680
|
||||
3
grpo_bonus1/completions/completions_00069.parquet
Normal file
3
grpo_bonus1/completions/completions_00069.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f83b70b938d5c2d81a4e34b4f19e905e2508491d071da1dab77febc1723f1b06
|
||||
size 19907
|
||||
3
grpo_bonus1/completions/completions_00070.parquet
Normal file
3
grpo_bonus1/completions/completions_00070.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3dd88b4c577c57ae55f84e99f933cedf0f20867924db5b1c636be79228be2eca
|
||||
size 33213
|
||||
3
grpo_bonus1/completions/completions_00071.parquet
Normal file
3
grpo_bonus1/completions/completions_00071.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5b6731673fbcb48755b393cee495c4d20150964f51f8ffe24413a391c7be4000
|
||||
size 24896
|
||||
3
grpo_bonus1/completions/completions_00072.parquet
Normal file
3
grpo_bonus1/completions/completions_00072.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2e13606b9f98d38d9f8fbeea95eaea2dbb2f98c312d84a485d523dc6f117d5b7
|
||||
size 28507
|
||||
3
grpo_bonus1/completions/completions_00073.parquet
Normal file
3
grpo_bonus1/completions/completions_00073.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1c8a8d4de26b595656f7389468e0addd62b7e79afba18a581d174240fadbd259
|
||||
size 36024
|
||||
3
grpo_bonus1/completions/completions_00074.parquet
Normal file
3
grpo_bonus1/completions/completions_00074.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:13a0f0851bdb1ed6c8d7593c59af68615a0e05fd8fa9f9cba8f61fb3f3777189
|
||||
size 32111
|
||||
3
grpo_bonus1/completions/completions_00075.parquet
Normal file
3
grpo_bonus1/completions/completions_00075.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ab3da507e102b0abec0eb6d9d728ee136f01e87cdcdc48312878fa18cfa4f2b7
|
||||
size 39455
|
||||
3
grpo_bonus1/completions/completions_00076.parquet
Normal file
3
grpo_bonus1/completions/completions_00076.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:83860fcc964e6ae2ece6be922da70d0951d42503d18d4f3237a46a42288d975a
|
||||
size 33411
|
||||
3
grpo_bonus1/completions/completions_00077.parquet
Normal file
3
grpo_bonus1/completions/completions_00077.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a4a3f9e812dc701f85607264d3c6bd069489c908e95f8682c2eeb43ab17cfd85
|
||||
size 42767
|
||||
3
grpo_bonus1/completions/completions_00078.parquet
Normal file
3
grpo_bonus1/completions/completions_00078.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:39b62f53a91cff18983ceee0f706e3ca686dfbe99c843c6792ec4f4031f5fd81
|
||||
size 39199
|
||||
3
grpo_bonus1/completions/completions_00079.parquet
Normal file
3
grpo_bonus1/completions/completions_00079.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c078a0743ea14b3a3883ac36e40a8afda17089c4a3eafc2109912cc83b7908b6
|
||||
size 42133
|
||||
3
grpo_bonus1/completions/completions_00080.parquet
Normal file
3
grpo_bonus1/completions/completions_00080.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3a64795c44dc11da061c9898334a27c5acf79328fe91877285391dd4909e199f
|
||||
size 29621
|
||||
3
grpo_bonus1/completions/completions_00081.parquet
Normal file
3
grpo_bonus1/completions/completions_00081.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:33faca82c89e3a86639ebfbca647fb1ef55a12c932fe29b2c09a8fa2a0204b94
|
||||
size 23501
|
||||
3
grpo_bonus1/completions/completions_00082.parquet
Normal file
3
grpo_bonus1/completions/completions_00082.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b0bb2e971a59b3963888b83ce44e5ea81895c6bc4d60054bd2b681ce68f308d6
|
||||
size 35283
|
||||
3
grpo_bonus1/completions/completions_00083.parquet
Normal file
3
grpo_bonus1/completions/completions_00083.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:101d6572d2a0907e93926c6cf7c6f190e634370073305a0461b454ef084a3ba9
|
||||
size 42382
|
||||
3
grpo_bonus1/completions/completions_00084.parquet
Normal file
3
grpo_bonus1/completions/completions_00084.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8e528cb5700fb0bef10ffb2f4c1211b1a456052ac5ce89904345a3863740d35c
|
||||
size 28171
|
||||
3
grpo_bonus1/completions/completions_00085.parquet
Normal file
3
grpo_bonus1/completions/completions_00085.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f9f2ee35c9338ad41aa36dfe68d01aaa614899b53721be04e5350d66f669d268
|
||||
size 23275
|
||||
3
grpo_bonus1/completions/completions_00086.parquet
Normal file
3
grpo_bonus1/completions/completions_00086.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0423bb42b0ff7c5b3b92acace992c7e3b1abcdac666b8100fd6886bbf8043112
|
||||
size 36561
|
||||
3
grpo_bonus1/completions/completions_00087.parquet
Normal file
3
grpo_bonus1/completions/completions_00087.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:19ca8ede5eb43e132af9749d6ce7392ca1631b80d1c3a16b1c55756d46d93080
|
||||
size 30046
|
||||
3
grpo_bonus1/completions/completions_00088.parquet
Normal file
3
grpo_bonus1/completions/completions_00088.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:917927f41979598b7c5f6e449ed3ba0ed02b8f3d9a48e48922105b2ef2870b49
|
||||
size 37427
|
||||
3
grpo_bonus1/completions/completions_00089.parquet
Normal file
3
grpo_bonus1/completions/completions_00089.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:536eab7c6bc066deee6eae22f9a0f7f3a77b23ce1900b03ebf6412088aa3cd9c
|
||||
size 34077
|
||||
3
grpo_bonus1/completions/completions_00090.parquet
Normal file
3
grpo_bonus1/completions/completions_00090.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8ccb341a795b32cc3437e2b73796b0d53d8691671f8eec3c3d36b2be9a75416d
|
||||
size 32745
|
||||
3
grpo_bonus1/completions/completions_00091.parquet
Normal file
3
grpo_bonus1/completions/completions_00091.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:07c0a2666d4326d8de823a9cfea361cef3d0038fb81452b0f9404ebec9c2182b
|
||||
size 27546
|
||||
3
grpo_bonus1/completions/completions_00092.parquet
Normal file
3
grpo_bonus1/completions/completions_00092.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:61355d925f468e92884755ae2d39b793b674ff8f46193ca05d5fb25534b7f957
|
||||
size 38997
|
||||
3
grpo_bonus1/completions/completions_00093.parquet
Normal file
3
grpo_bonus1/completions/completions_00093.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:065e3041c503a0485438d9a10b84b26f0d439c5c9e106f53e8979fc9af4e218b
|
||||
size 35798
|
||||
3
grpo_bonus1/completions/completions_00094.parquet
Normal file
3
grpo_bonus1/completions/completions_00094.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:770b036acd4982ebe8d0ee4cc53ce5fb07a39d75773436eafbb104a44c681b90
|
||||
size 38326
|
||||
3
grpo_bonus1/completions/completions_00095.parquet
Normal file
3
grpo_bonus1/completions/completions_00095.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1cf5f83d1fcb1e9529e2a77e290c6ed3b66725f01a92f47a067259fe213eae26
|
||||
size 33347
|
||||
3
grpo_bonus1/completions/completions_00096.parquet
Normal file
3
grpo_bonus1/completions/completions_00096.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b38b9e2510d0ec55d8e73c85570e02875900fe940f13e265366b5d6caa396e3e
|
||||
size 32036
|
||||
3
grpo_bonus1/completions/completions_00097.parquet
Normal file
3
grpo_bonus1/completions/completions_00097.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5862b0609b348a1c7b50fb54492f290e1e548d4d590b64c3b61927e3d48c71ef
|
||||
size 29544
|
||||
3
grpo_bonus1/completions/completions_00098.parquet
Normal file
3
grpo_bonus1/completions/completions_00098.parquet
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c6ef188ca76c4198ecfe0be1c8eb3a2021b8784008f04a8d8078186766758d0c
|
||||
size 39891
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user