yujunjun/LLMs-from-scratch
1
0
Fork 0
mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2025-11-29 16:40:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

Make it easier to toggle between thinking and instruct variants (#887)

Browse Source
This commit is contained in:
Sebastian Raschka 2025-10-16 20:37:31 -05:00 committed by GitHub
parent 7fe4874dda
commit 27b6dfab9e
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 76 additions and 35 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

63
ch05/11_qwen3/standalone-qwen3-plus-kvcache.ipynb
View File

@ -82,8 +82,8 @@
"name": "stdout",
"output_type": "stream",
"text": [
"huggingface_hub version: 0.34.4\n",
"tokenizers version: 0.21.4\n",
"huggingface_hub version: 0.35.3\n",
"tokenizers version: 0.22.1\n",
"torch version: 2.8.0\n"
]
}
@ -105,7 +105,12 @@
"id": "07e96fbb-8e16-4f6d-835f-c6159321280b",
"metadata": {},
"source": [
"- This notebook supports both the base model and the reasoning (\"thinking\") model; which model to use can be controlled via the following flag:"
"- Note that there are two models, the \"base\" and the \"hybrid\" model, and the hybrid model can be used as either a reasoning or a regular instruction-following model:\n",
"- In short, the model types are as follows:\n",
" - `base`: the pretrained base model; note that the Qwen3 pretraining contained some reasoning data (chain-of-thought data), so the model sometimes emits reasoning traces even though it didn't undergo the reasoning training (reinforcement learning) stages\n",
" - `hybrid` \n",
" - `reasoning`: emits long reasoning traces inside `<think></think>` tags\n",
" - `instruct`: the same as above, but long reasoning traces can be suppressed by manually adding empty `<think></think>` (this is done by the tokenizer); this way, the model acts like a regular instruction-following model"
]
},
{
@ -115,14 +120,15 @@
"metadata": {},
"outputs": [],
"source": [
"USE_REASONING_MODEL = True\n",
"# Uses the base model if USE_REASONING_MODEL = False\n",
"# Select which model to use via the following flag; only one can be True\n",
"\n",
"USE_BASE_MODEL = False\n",
"USE_REASONING_MODEL = True \n",
"USE_INSTRUCT_MODEL = False\n",
"# Uses the instruct mode (without reasoning) if \n",
"# USE_REASONING_MODEL = True\n",
"# USE_INSTRUCT_MODEL = True\n",
"# This setting does have no effect if USE_REASONING_MODEL = False"
"\n",
"if (USE_BASE_MODEL + USE_REASONING_MODEL\n",
" + USE_INSTRUCT_MODEL) != 1:\n",
" raise AttributeError(\"Only one of the options above can be True.\")"
]
},
{
@ -916,7 +922,16 @@
"id": "699cb1b8-a67d-49fb-80a6-0dad9d81f392",
"outputId": "55b2f28c-142f-4698-9d23-d27456d3ed6d"
},
"outputs": [],
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/sebastian/Developer/LLMs-from-scratch/.venv/lib/python3.13/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
" from .autonotebook import tqdm as notebook_tqdm\n"
]
}
],
"source": [
"import json\n",
"import os\n",
@ -925,7 +940,7 @@
"from huggingface_hub import hf_hub_download, snapshot_download\n",
"\n",
"\n",
"if USE_REASONING_MODEL:\n",
"if USE_REASONING_MODEL or USE_INSTRUCT_MODEL:\n",
" repo_id = f\"Qwen/Qwen3-{CHOOSE_MODEL}\"\n",
"else:\n",
" repo_id = f\"Qwen/Qwen3-{CHOOSE_MODEL}-Base\"\n",
@ -1064,13 +1079,23 @@
" local_dir=local_dir,\n",
")\n",
"\n",
"tokenizer = Qwen3Tokenizer(\n",
" tokenizer_file_path=tokenizer_file_path,\n",
" repo_id=repo_id,\n",
" apply_chat_template=USE_REASONING_MODEL,\n",
" add_generation_prompt=USE_REASONING_MODEL,\n",
" add_thinking=not USE_INSTRUCT_MODEL\n",
")"
"if USE_REASONING_MODEL or USE_INSTRUCT_MODEL:\n",
" tokenizer = Qwen3Tokenizer(\n",
" tokenizer_file_path=tokenizer_file_path,\n",
" repo_id=repo_id,\n",
" apply_chat_template=True,\n",
" add_generation_prompt=True,\n",
" add_thinking=USE_REASONING_MODEL\n",
" )\n",
"\n",
"else:\n",
" tokenizer = Qwen3Tokenizer(\n",
" tokenizer_file_path=tokenizer_file_path,\n",
" repo_id=repo_id,\n",
" apply_chat_template=False,\n",
" add_generation_prompt=False,\n",
" add_thinking=False\n",
" )"
]
},
{
@ -1228,7 +1253,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.16"
"version": "3.13.5"
}
},
"nbformat": 4,

48
ch05/11_qwen3/standalone-qwen3.ipynb
View File

@ -103,7 +103,12 @@
"id": "07e96fbb-8e16-4f6d-835f-c6159321280b",
"metadata": {},
"source": [
"- This notebook supports both the base model and the reasoning (\"thinking\") model; which model to use can be controlled via the following flag:"
"- Note that there are two models, the \"base\" and the \"hybrid\" model, and the hybrid model can be used as either a reasoning or a regular instruction-following model:\n",
"- In short, the model types are as follows:\n",
" - `base`: the pretrained base model; note that the Qwen3 pretraining contained some reasoning data (chain-of-thought data), so the model sometimes emits reasoning traces even though it didn't undergo the reasoning training (reinforcement learning) stages\n",
" - `hybrid` \n",
" - `reasoning`: emits long reasoning traces inside `<think></think>` tags\n",
" - `instruct`: the same as above, but long reasoning traces can be suppressed by manually adding empty `<think></think>` (this is done by the tokenizer); this way, the model acts like a regular instruction-following model"
]
},
{
@ -113,14 +118,15 @@
"metadata": {},
"outputs": [],
"source": [
"USE_REASONING_MODEL = True\n",
"# Uses the base model if USE_REASONING_MODEL = False\n",
"# Select which model to use via the following flag; only one can be True\n",
"\n",
"USE_BASE_MODEL = False\n",
"USE_REASONING_MODEL = True \n",
"USE_INSTRUCT_MODEL = False\n",
"# Uses the instruct mode (without reasoning) if \n",
"# USE_REASONING_MODEL = True\n",
"# USE_INSTRUCT_MODEL = True\n",
"# This setting does have no effect if USE_REASONING_MODEL = False"
"\n",
"if (USE_BASE_MODEL + USE_REASONING_MODEL\n",
" + USE_INSTRUCT_MODEL) != 1:\n",
" raise AttributeError(\"Only one of the options above can be True.\")"
]
},
{
@ -867,7 +873,7 @@
"from huggingface_hub import hf_hub_download, snapshot_download\n",
"\n",
"\n",
"if USE_REASONING_MODEL:\n",
"if USE_REASONING_MODEL or USE_INSTRUCT_MODEL:\n",
" repo_id = f\"Qwen/Qwen3-{CHOOSE_MODEL}\"\n",
"else:\n",
" repo_id = f\"Qwen/Qwen3-{CHOOSE_MODEL}-Base\"\n",
@ -1006,13 +1012,23 @@
" local_dir=local_dir,\n",
")\n",
"\n",
"tokenizer = Qwen3Tokenizer(\n",
" tokenizer_file_path=tokenizer_file_path,\n",
" repo_id=repo_id,\n",
" apply_chat_template=USE_REASONING_MODEL,\n",
" add_generation_prompt=USE_REASONING_MODEL,\n",
" add_thinking=not USE_INSTRUCT_MODEL\n",
")"
"if USE_REASONING_MODEL or USE_INSTRUCT_MODEL:\n",
" tokenizer = Qwen3Tokenizer(\n",
" tokenizer_file_path=tokenizer_file_path,\n",
" repo_id=repo_id,\n",
" apply_chat_template=True,\n",
" add_generation_prompt=True,\n",
" add_thinking=USE_REASONING_MODEL\n",
" )\n",
"\n",
"else:\n",
" tokenizer = Qwen3Tokenizer(\n",
" tokenizer_file_path=tokenizer_file_path,\n",
" repo_id=repo_id,\n",
" apply_chat_template=False,\n",
" add_generation_prompt=False,\n",
" add_thinking=False\n",
" )"
]
},
{
@ -1163,7 +1179,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.16"
"version": "3.13.5"
}
},
"nbformat": 4,