Skip to content

fix dataset formatting and mapping for Magistral reasoning #136

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Nov 21, 2025
Merged

fix dataset formatting and mapping for Magistral reasoning #136

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
77bf865
fix dataset formatting and mapping for Magistral reasoning
rolandtannous Nov 21, 2025
e1b249d
fix remaining notebooks
rolandtannous Nov 21, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 11 additions & 13 deletions nb/Kaggle-Magistral_(24B)-Reasoning-Conversational.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -575,16 +575,14 @@
},
"outputs": [],
"source": [
"def generate_conversation(examples):\n",
" problems = examples[\"problem\"]\n",
" solutions = examples[\"generated_solution\"]\n",
" conversations = []\n",
" for problem, solution in zip(problems, solutions):\n",
" conversations.append([\n",
"def generate_conversation(example):\n",
" problem = example[\"problem\"]\n",
" solution = example[\"generated_solution\"]\n",
" conversation = [\n",
" {\"role\" : \"user\", \"content\" : problem},\n",
" {\"role\" : \"assistant\", \"content\" : solution},\n",
" ])\n",
" return { \"conversations\": conversations, }"
" ]\n",
" return { \"conversations\": conversation, }"
]
},
{
Expand Down Expand Up @@ -628,10 +626,10 @@
}
],
"source": [
"reasoning_conversations = tokenizer.apply_chat_template(\n",
" reasoning_dataset.map(generate_conversation, batched = True)[\"conversations\"],\n",
" tokenize = False,\n",
")"
"reasoning_conversations = [tokenizer.apply_chat_template(\n",
" conv[\"conversations\"],tokenize = False,)\n",
" for conv in reasoning_dataset.map(generate_conversation)\n",
"]"
]
},
{
Expand Down Expand Up @@ -6420,4 +6418,4 @@
},
"nbformat": 4,
"nbformat_minor": 0
}
}
24 changes: 11 additions & 13 deletions nb/Magistral_(24B)-Reasoning-Conversational.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -575,16 +575,14 @@
},
"outputs": [],
"source": [
"def generate_conversation(examples):\n",
" problems = examples[\"problem\"]\n",
" solutions = examples[\"generated_solution\"]\n",
" conversations = []\n",
" for problem, solution in zip(problems, solutions):\n",
" conversations.append([\n",
"def generate_conversation(example):\n",
" problem = example[\"problem\"]\n",
" solution = example[\"generated_solution\"]\n",
" conversation = [\n",
" {\"role\" : \"user\", \"content\" : problem},\n",
" {\"role\" : \"assistant\", \"content\" : solution},\n",
" ])\n",
" return { \"conversations\": conversations, }"
" ]\n",
" return { \"conversations\": conversation, }"
]
},
{
Expand Down Expand Up @@ -628,10 +626,10 @@
}
],
"source": [
"reasoning_conversations = tokenizer.apply_chat_template(\n",
" reasoning_dataset.map(generate_conversation, batched = True)[\"conversations\"],\n",
" tokenize = False,\n",
")"
"reasoning_conversations = [tokenizer.apply_chat_template(\n",
" conv[\"conversations\"],tokenize = False,)\n",
" for conv in reasoning_dataset.map(generate_conversation)\n",
"]"
Comment on lines +629 to +632
Copy link
Contributor

@gemini-code-assist gemini-code-assist bot Nov 21, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

The list comprehension is a bit difficult to read due to its formatting. The arguments to apply_chat_template are not clearly separated, and the for loop is on a separate line which is unusual for a list comprehension of this style. For better readability and adherence to common Python style (PEP 8), I suggest reformatting it.1

A more readable version would be:

reasoning_conversations = [
    tokenizer.apply_chat_template(conv["conversations"], tokenize=False)
    for conv in reasoning_dataset.map(generate_conversation)
]

Style Guide References

Footnotes

  1. PEP 8 provides guidelines on code layout, including how to format long lines and comprehensions, to improve readability. ↩

]
},
{
Expand Down Expand Up @@ -6420,4 +6418,4 @@
},
"nbformat": 4,
"nbformat_minor": 0
}
}
30 changes: 14 additions & 16 deletions original_template/Magistral_(24B)-Reasoning-Conversational.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -552,17 +552,15 @@
},
"outputs": [],
"source": [
"def generate_conversation(examples):\n",
" problems = examples[\"problem\"]\n",
" solutions = examples[\"generated_solution\"]\n",
" conversations = []\n",
" for problem, solution in zip(problems, solutions):\n",
" conversations.append([\n",
" {\"role\" : \"user\", \"content\" : problem},\n",
" {\"role\" : \"assistant\", \"content\" : solution},\n",
" ])\n",
" return { \"conversations\": conversations, }"
]
"def generate_conversation(example):\n",
" problem = example[\"problem\"]\n",
" solution = example[\"generated_solution\"]\n",
" conversation = [\n",
" {\"role\" : \"user\", \"content\" : problem},\n",
" {\"role\" : \"assistant\", \"content\" : solution},\n",
" ]\n",
" return { \"conversations\": conversation, }"
]
},
{
"cell_type": "code",
Expand Down Expand Up @@ -605,11 +603,11 @@
}
],
"source": [
"reasoning_conversations = tokenizer.apply_chat_template(\n",
" reasoning_dataset.map(generate_conversation, batched = True)[\"conversations\"],\n",
" tokenize = False,\n",
")"
]
"reasoning_conversations = [tokenizer.apply_chat_template(\n",
" conv[\"conversations\"],tokenize = False,)\n",
" for conv in reasoning_dataset.map(generate_conversation)\n",
"]"
]
},
{
"cell_type": "markdown",
Expand Down
69 changes: 33 additions & 36 deletions python_scripts/Magistral_(24B)-Reasoning-Conversational.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,34 +7,34 @@
# <a href="https://discord.gg/unsloth"><img src="https://github.com/unslothai/unsloth/raw/main/images/Discord button.png" width="145"></a>
# <a href="https://docs.unsloth.ai/"><img src="https://github.com/unslothai/unsloth/blob/main/images/documentation%20green%20button.png?raw=true" width="125"></a></a> Join Discord if you need help + ⭐ <i>Star us on <a href="https://github.com/unslothai/unsloth">Github</a> </i> ⭐
# </div>
#
#
# To install Unsloth your local device, follow [our guide](https://docs.unsloth.ai/get-started/install-and-update). This notebook is licensed [LGPL-3.0](https://github.com/unslothai/notebooks?tab=LGPL-3.0-1-ov-file#readme).
#
#
# You will learn how to do [data prep](#Data), how to [train](#Train), how to [run the model](#Inference), & [how to save it](#Save)
#
#

# ### News

#
#
# Unsloth's [Docker image](https://hub.docker.com/r/unsloth/unsloth) is here! Start training with no setup & environment issues. [Read our Guide](https://docs.unsloth.ai/new/how-to-train-llms-with-unsloth-and-docker).
#
#
# [gpt-oss RL](https://docs.unsloth.ai/new/gpt-oss-reinforcement-learning) is now supported with the fastest inference & lowest VRAM. Try our [new notebook](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/gpt-oss-(20B)-GRPO.ipynb) which creates kernels!
#
#
# Introducing [Vision](https://docs.unsloth.ai/new/vision-reinforcement-learning-vlm-rl) and [Standby](https://docs.unsloth.ai/basics/memory-efficient-rl) for RL! Train Qwen, Gemma etc. VLMs with GSPO - even faster with less VRAM.
#
#
# Unsloth now supports Text-to-Speech (TTS) models. Read our [guide here](https://docs.unsloth.ai/basics/text-to-speech-tts-fine-tuning).
#
#
# Visit our docs for all our [model uploads](https://docs.unsloth.ai/get-started/all-our-models) and [notebooks](https://docs.unsloth.ai/get-started/unsloth-notebooks).
#
#

# # ### Installation
#
#
# # In[ ]:
#
#
#
#
# get_ipython().run_cell_magic('capture', '', 'import os, re\nif "COLAB_" not in "".join(os.environ.keys()):\n !pip install unsloth\nelse:\n # Do this only in Colab notebooks! Otherwise use pip install unsloth\n import torch; v = re.match(r"[0-9\\.]{3,}", str(torch.__version__)).group(0)\n xformers = "xformers==" + ("0.0.32.post2" if v == "2.8.0" else "0.0.29.post3")\n !pip install --no-deps bitsandbytes accelerate {xformers} peft trl triton cut_cross_entropy unsloth_zoo\n !pip install sentencepiece protobuf "datasets>=3.4.1,<4.0.0" "huggingface_hub>=0.34.0" hf_transfer\n !pip install --no-deps unsloth\n!pip install transformers==4.56.2\n!pip install --no-deps trl==0.22.2\n')
#
#
#
#
# # ### Unsloth

# In[ ]:
Expand Down Expand Up @@ -114,25 +114,22 @@
# In[8]:


def generate_conversation(examples):
problems = examples["problem"]
solutions = examples["generated_solution"]
conversations = []
for problem, solution in zip(problems, solutions):
conversations.append([
def generate_conversation(example):
problem = example["problem"]
solution = example["generated_solution"]
conversation = [
{"role" : "user", "content" : problem},
{"role" : "assistant", "content" : solution},
])
return { "conversations": conversations, }
]
return { "conversations": conversation }


# In[9]:


reasoning_conversations = tokenizer.apply_chat_template(
reasoning_dataset.map(generate_conversation, batched = True)["conversations"],
tokenize = False,
)
reasoning_conversations = [
tokenizer.apply_chat_template(conv["conversations"],tokenize = False,) for conv in reasoning_dataset.map(generate_conversation)
]
Comment on lines +130 to +132
Copy link
Contributor

@gemini-code-assist gemini-code-assist bot Nov 21, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

This list comprehension is written across multiple lines, but line 131 is very long and contains multiple parts of the expression, which harms readability. According to PEP 8, lines should be limited to 79 or 99 characters for readability.1 It's better to format long list comprehensions over multiple lines. This will make the code easier to read and maintain.

Suggested change
reasoning_conversations = [
tokenizer.apply_chat_template(conv["conversations"],tokenize = False,) for conv in reasoning_dataset.map(generate_conversation)
]
reasoning_conversations = [
tokenizer.apply_chat_template(conv["conversations"], tokenize=False)
for conv in reasoning_dataset.map(generate_conversation)
]

Style Guide References

Footnotes

  1. PEP 8 suggests limiting all lines to a maximum of 79 characters (or 99 for some projects) to improve readability. ↩



# Let's see the first transformed row:
Expand Down Expand Up @@ -261,7 +258,7 @@ def generate_conversation(examples):
# <a name="Save"></a>
# ### Saving, loading finetuned models
# To save the final model as LoRA adapters, either use Huggingface's `push_to_hub` for an online save or `save_pretrained` for a local save.
#
#
# **[NOTE]** This ONLY saves the LoRA adapters, and not the full model. To save to 16bit or GGUF, scroll down!

# In[21]:
Expand All @@ -288,7 +285,7 @@ def generate_conversation(examples):


# ### Saving to float16 for VLLM
#
#
# We also support saving to `float16` directly. Select `merged_16bit` for float16 or `merged_4bit` for int4. We also allow `lora` adapters as a fallback. Use `push_to_hub_merged` to upload to your Hugging Face account! You can go to https://huggingface.co/settings/tokens for your personal tokens.

# In[ ]:
Expand Down Expand Up @@ -317,12 +314,12 @@ def generate_conversation(examples):

# ### GGUF / llama.cpp Conversion
# To save to `GGUF` / `llama.cpp`, we support it natively now! We clone `llama.cpp` and we default save it to `q8_0`. We allow all methods like `q4_k_m`. Use `save_pretrained_gguf` for local saving and `push_to_hub_gguf` for uploading to HF.
#
#
# Some supported quant methods (full list on our [Wiki page](https://github.com/unslothai/unsloth/wiki#gguf-quantization-options)):
# * `q8_0` - Fast conversion. High resource use, but generally acceptable.
# * `q4_k_m` - Recommended. Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q4_K.
# * `q5_k_m` - Recommended. Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q5_K.
#
#
# [**NEW**] To finetune and auto export to Ollama, try our [Ollama notebook](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3_(8B)-Ollama.ipynb)

# In[24]:
Expand Down Expand Up @@ -359,22 +356,22 @@ def generate_conversation(examples):


# Now, use the `model-unsloth.gguf` file or `model-unsloth-Q4_K_M.gguf` file in llama.cpp.
#
#
# And we're done! If you have any questions on Unsloth, we have a [Discord](https://discord.gg/unsloth) channel! If you find any bugs or want to keep updated with the latest LLM stuff, or need help, join projects etc, feel free to join our Discord!
#
#
# Some other links:
# 1. Train your own reasoning model - Llama GRPO notebook [Free Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.1_(8B)-GRPO.ipynb)
# 2. Saving finetunes to Ollama. [Free notebook](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3_(8B)-Ollama.ipynb)
# 3. Llama 3.2 Vision finetuning - Radiography use case. [Free Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.2_(11B)-Vision.ipynb)
# 6. See notebooks for DPO, ORPO, Continued pretraining, conversational finetuning and more on our [documentation](https://docs.unsloth.ai/get-started/unsloth-notebooks)!
#
#
# <div class="align-center">
# <a href="https://unsloth.ai"><img src="https://github.com/unslothai/unsloth/raw/main/images/unsloth%20new%20logo.png" width="115"></a>
# <a href="https://discord.gg/unsloth"><img src="https://github.com/unslothai/unsloth/raw/main/images/Discord.png" width="145"></a>
# <a href="https://docs.unsloth.ai/"><img src="https://github.com/unslothai/unsloth/blob/main/images/documentation%20green%20button.png?raw=true" width="125"></a>
#
#
# Join Discord if you need help + ⭐️ <i>Star us on <a href="https://github.com/unslothai/unsloth">Github</a> </i> ⭐️
# </div>
#
#
# This notebook and all Unsloth notebooks are licensed [LGPL-3.0](https://github.com/unslothai/notebooks?tab=LGPL-3.0-1-ov-file#readme).
#
#