Instructions to use NTQuoc/OpenRS-GRPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use NTQuoc/OpenRS-GRPO with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("NTQuoc/OpenRS-GRPO", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Training in progress, step 50
Browse files- adapter_config.json +5 -10
- adapter_model.safetensors +2 -2
- chat_template.jinja +1 -154
- tokenizer.json +2 -2
- tokenizer_config.json +8 -25
- training_args.bin +1 -1
adapter_config.json
CHANGED
|
@@ -3,7 +3,7 @@
|
|
| 3 |
"alpha_pattern": {},
|
| 4 |
"arrow_config": null,
|
| 5 |
"auto_mapping": null,
|
| 6 |
-
"base_model_name_or_path": "
|
| 7 |
"bias": "none",
|
| 8 |
"corda_config": null,
|
| 9 |
"ensure_weight_tying": false,
|
|
@@ -29,18 +29,13 @@
|
|
| 29 |
"rank_pattern": {},
|
| 30 |
"revision": null,
|
| 31 |
"target_modules": [
|
| 32 |
-
"out_proj",
|
| 33 |
-
"in_proj_qkv",
|
| 34 |
"q_proj",
|
|
|
|
|
|
|
| 35 |
"o_proj",
|
| 36 |
-
"in_proj_z",
|
| 37 |
-
"up_proj",
|
| 38 |
-
"in_proj_b",
|
| 39 |
-
"down_proj",
|
| 40 |
"k_proj",
|
| 41 |
-
"
|
| 42 |
-
"
|
| 43 |
-
"v_proj"
|
| 44 |
],
|
| 45 |
"target_parameters": null,
|
| 46 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 3 |
"alpha_pattern": {},
|
| 4 |
"arrow_config": null,
|
| 5 |
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
|
| 7 |
"bias": "none",
|
| 8 |
"corda_config": null,
|
| 9 |
"ensure_weight_tying": false,
|
|
|
|
| 29 |
"rank_pattern": {},
|
| 30 |
"revision": null,
|
| 31 |
"target_modules": [
|
|
|
|
|
|
|
| 32 |
"q_proj",
|
| 33 |
+
"gate_proj",
|
| 34 |
+
"v_proj",
|
| 35 |
"o_proj",
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
"k_proj",
|
| 37 |
+
"down_proj",
|
| 38 |
+
"up_proj"
|
|
|
|
| 39 |
],
|
| 40 |
"target_parameters": null,
|
| 41 |
"task_type": "CAUSAL_LM",
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:938177476ed0f05ca65b54404346c79d5975a4f6172064aa75d88accfe8217c4
|
| 3 |
+
size 18516064
|
chat_template.jinja
CHANGED
|
@@ -1,154 +1 @@
|
|
| 1 |
-
{%
|
| 2 |
-
{%- set video_count = namespace(value=0) %}
|
| 3 |
-
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
|
| 4 |
-
{%- if content is string %}
|
| 5 |
-
{{- content }}
|
| 6 |
-
{%- elif content is iterable and content is not mapping %}
|
| 7 |
-
{%- for item in content %}
|
| 8 |
-
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
|
| 9 |
-
{%- if is_system_content %}
|
| 10 |
-
{{- raise_exception('System message cannot contain images.') }}
|
| 11 |
-
{%- endif %}
|
| 12 |
-
{%- if do_vision_count %}
|
| 13 |
-
{%- set image_count.value = image_count.value + 1 %}
|
| 14 |
-
{%- endif %}
|
| 15 |
-
{%- if add_vision_id %}
|
| 16 |
-
{{- 'Picture ' ~ image_count.value ~ ': ' }}
|
| 17 |
-
{%- endif %}
|
| 18 |
-
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
|
| 19 |
-
{%- elif 'video' in item or item.type == 'video' %}
|
| 20 |
-
{%- if is_system_content %}
|
| 21 |
-
{{- raise_exception('System message cannot contain videos.') }}
|
| 22 |
-
{%- endif %}
|
| 23 |
-
{%- if do_vision_count %}
|
| 24 |
-
{%- set video_count.value = video_count.value + 1 %}
|
| 25 |
-
{%- endif %}
|
| 26 |
-
{%- if add_vision_id %}
|
| 27 |
-
{{- 'Video ' ~ video_count.value ~ ': ' }}
|
| 28 |
-
{%- endif %}
|
| 29 |
-
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
|
| 30 |
-
{%- elif 'text' in item %}
|
| 31 |
-
{{- item.text }}
|
| 32 |
-
{%- else %}
|
| 33 |
-
{{- raise_exception('Unexpected item type in content.') }}
|
| 34 |
-
{%- endif %}
|
| 35 |
-
{%- endfor %}
|
| 36 |
-
{%- elif content is none or content is undefined %}
|
| 37 |
-
{{- '' }}
|
| 38 |
-
{%- else %}
|
| 39 |
-
{{- raise_exception('Unexpected content type.') }}
|
| 40 |
-
{%- endif %}
|
| 41 |
-
{%- endmacro %}
|
| 42 |
-
{%- if not messages %}
|
| 43 |
-
{{- raise_exception('No messages provided.') }}
|
| 44 |
-
{%- endif %}
|
| 45 |
-
{%- if tools and tools is iterable and tools is not mapping %}
|
| 46 |
-
{{- '<|im_start|>system\n' }}
|
| 47 |
-
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
|
| 48 |
-
{%- for tool in tools %}
|
| 49 |
-
{{- "\n" }}
|
| 50 |
-
{{- tool | tojson }}
|
| 51 |
-
{%- endfor %}
|
| 52 |
-
{{- "\n</tools>" }}
|
| 53 |
-
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
|
| 54 |
-
{%- if messages[0].role == 'system' %}
|
| 55 |
-
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 56 |
-
{%- if content %}
|
| 57 |
-
{{- '\n\n' + content }}
|
| 58 |
-
{%- endif %}
|
| 59 |
-
{%- endif %}
|
| 60 |
-
{{- '<|im_end|>\n' }}
|
| 61 |
-
{%- else %}
|
| 62 |
-
{%- if messages[0].role == 'system' %}
|
| 63 |
-
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 64 |
-
{{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
|
| 65 |
-
{%- endif %}
|
| 66 |
-
{%- endif %}
|
| 67 |
-
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 68 |
-
{%- for message in messages[::-1] %}
|
| 69 |
-
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 70 |
-
{%- if ns.multi_step_tool and message.role == "user" %}
|
| 71 |
-
{%- set content = render_content(message.content, false)|trim %}
|
| 72 |
-
{%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
|
| 73 |
-
{%- set ns.multi_step_tool = false %}
|
| 74 |
-
{%- set ns.last_query_index = index %}
|
| 75 |
-
{%- endif %}
|
| 76 |
-
{%- endif %}
|
| 77 |
-
{%- endfor %}
|
| 78 |
-
{%- if ns.multi_step_tool %}
|
| 79 |
-
{{- raise_exception('No user query found in messages.') }}
|
| 80 |
-
{%- endif %}
|
| 81 |
-
{%- for message in messages %}
|
| 82 |
-
{%- set content = render_content(message.content, true)|trim %}
|
| 83 |
-
{%- if message.role == "system" %}
|
| 84 |
-
{%- if not loop.first %}
|
| 85 |
-
{{- raise_exception('System message must be at the beginning.') }}
|
| 86 |
-
{%- endif %}
|
| 87 |
-
{%- elif message.role == "user" %}
|
| 88 |
-
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 89 |
-
{%- elif message.role == "assistant" %}
|
| 90 |
-
{%- set reasoning_content = '' %}
|
| 91 |
-
{%- if message.reasoning_content is string %}
|
| 92 |
-
{%- set reasoning_content = message.reasoning_content %}
|
| 93 |
-
{%- else %}
|
| 94 |
-
{%- if '</think>' in content %}
|
| 95 |
-
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 96 |
-
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 97 |
-
{%- endif %}
|
| 98 |
-
{%- endif %}
|
| 99 |
-
{%- set reasoning_content = reasoning_content|trim %}
|
| 100 |
-
{%- if loop.index0 > ns.last_query_index %}
|
| 101 |
-
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
|
| 102 |
-
{%- else %}
|
| 103 |
-
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 104 |
-
{%- endif %}
|
| 105 |
-
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
| 106 |
-
{%- for tool_call in message.tool_calls %}
|
| 107 |
-
{%- if tool_call.function is defined %}
|
| 108 |
-
{%- set tool_call = tool_call.function %}
|
| 109 |
-
{%- endif %}
|
| 110 |
-
{%- if loop.first %}
|
| 111 |
-
{%- if content|trim %}
|
| 112 |
-
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 113 |
-
{%- else %}
|
| 114 |
-
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 115 |
-
{%- endif %}
|
| 116 |
-
{%- else %}
|
| 117 |
-
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 118 |
-
{%- endif %}
|
| 119 |
-
{%- if tool_call.arguments is defined %}
|
| 120 |
-
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 121 |
-
{{- '<parameter=' + args_name + '>\n' }}
|
| 122 |
-
{%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
|
| 123 |
-
{{- args_value }}
|
| 124 |
-
{{- '\n</parameter>\n' }}
|
| 125 |
-
{%- endfor %}
|
| 126 |
-
{%- endif %}
|
| 127 |
-
{{- '</function>\n</tool_call>' }}
|
| 128 |
-
{%- endfor %}
|
| 129 |
-
{%- endif %}
|
| 130 |
-
{{- '<|im_end|>\n' }}
|
| 131 |
-
{%- elif message.role == "tool" %}
|
| 132 |
-
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 133 |
-
{{- '<|im_start|>user' }}
|
| 134 |
-
{%- endif %}
|
| 135 |
-
{{- '\n<tool_response>\n' }}
|
| 136 |
-
{{- content }}
|
| 137 |
-
{{- '\n</tool_response>' }}
|
| 138 |
-
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 139 |
-
{{- '<|im_end|>\n' }}
|
| 140 |
-
{%- elif loop.last %}
|
| 141 |
-
{{- '<|im_end|>\n' }}
|
| 142 |
-
{%- endif %}
|
| 143 |
-
{%- else %}
|
| 144 |
-
{{- raise_exception('Unexpected message role.') }}
|
| 145 |
-
{%- endif %}
|
| 146 |
-
{%- endfor %}
|
| 147 |
-
{%- if add_generation_prompt %}
|
| 148 |
-
{{- '<|im_start|>assistant\n' }}
|
| 149 |
-
{%- if enable_thinking is defined and enable_thinking is true %}
|
| 150 |
-
{{- '<think>\n' }}
|
| 151 |
-
{%- else %}
|
| 152 |
-
{{- '<think>\n\n</think>\n\n' }}
|
| 153 |
-
{%- endif %}
|
| 154 |
-
{%- endif %}
|
|
|
|
| 1 |
+
{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<|User|>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<|Assistant|><|tool▁calls▁begin|><|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<|tool▁call▁end|>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<|tool▁call▁end|>'}}{{'<|tool▁calls▁end|><|end▁of▁sentence|>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<|tool▁outputs▁end|>' + message['content'] + '<|end▁of▁sentence|>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<|Assistant|>' + content + '<|end▁of▁sentence|>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<|tool▁outputs▁begin|><|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<|tool▁outputs▁end|>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<|Assistant|><think>\n'}}{% endif %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3547cd5c0a59ff52d25a5986f2f7b87a9c6269e944428cbc77c1798457b6725d
|
| 3 |
+
size 11421965
|
tokenizer_config.json
CHANGED
|
@@ -1,32 +1,15 @@
|
|
| 1 |
{
|
| 2 |
-
"add_prefix_space":
|
| 3 |
-
"audio_bos_token": "<|audio_start|>",
|
| 4 |
-
"audio_eos_token": "<|audio_end|>",
|
| 5 |
-
"audio_token": "<|audio_pad|>",
|
| 6 |
"backend": "tokenizers",
|
| 7 |
-
"bos_token":
|
| 8 |
"clean_up_tokenization_spaces": false,
|
| 9 |
-
"eos_token": "<
|
| 10 |
-
"errors": "replace",
|
| 11 |
-
"image_token": "<|image_pad|>",
|
| 12 |
"is_local": false,
|
| 13 |
"local_files_only": false,
|
| 14 |
-
"model_max_length":
|
| 15 |
-
"
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
"audio_token": "<|audio_pad|>",
|
| 19 |
-
"image_token": "<|image_pad|>",
|
| 20 |
-
"video_token": "<|video_pad|>",
|
| 21 |
-
"vision_bos_token": "<|vision_start|>",
|
| 22 |
-
"vision_eos_token": "<|vision_end|>"
|
| 23 |
-
},
|
| 24 |
-
"pad_token": "<|endoftext|>",
|
| 25 |
-
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
| 26 |
-
"split_special_tokens": false,
|
| 27 |
-
"tokenizer_class": "Qwen2Tokenizer",
|
| 28 |
"unk_token": null,
|
| 29 |
-
"
|
| 30 |
-
"vision_bos_token": "<|vision_start|>",
|
| 31 |
-
"vision_eos_token": "<|vision_end|>"
|
| 32 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_prefix_space": null,
|
|
|
|
|
|
|
|
|
|
| 3 |
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<|begin▁of▁sentence|>",
|
| 5 |
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|end▁of▁sentence|>",
|
|
|
|
|
|
|
| 7 |
"is_local": false,
|
| 8 |
"local_files_only": false,
|
| 9 |
+
"model_max_length": 16384,
|
| 10 |
+
"pad_token": "<|end▁of▁sentence|>",
|
| 11 |
+
"sp_model_kwargs": {},
|
| 12 |
+
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
"unk_token": null,
|
| 14 |
+
"use_default_system_prompt": false
|
|
|
|
|
|
|
| 15 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 7672
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e01083a6a7526d58110a9d499ecebbe5df68ead7088236f43d8b4794d7349d68
|
| 3 |
size 7672
|