bump transformers 4.57.3

* feat: add exaone4 chat template and update enums

* fix: handle first message as system or tools in exaone4 chat template

* Update src/axolotl/utils/chat_templates/templates/exaone4.jinja

Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>

* fix: lint

---------

Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
Co-authored-by: NanoCode012 <nano@axolotl.ai>

.github/workflows/base.yml

@@ -57,14 +57,14 @@ jobs:
             cuda_version: 12.8.1
             cudnn_version: ""
             python_version: "3.11"
-            pytorch: 2.9.0
+            pytorch: 2.9.1
             torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX"
             dockerfile: "Dockerfile-base"
           - cuda: "130"
             cuda_version: 13.0.0
             cudnn_version: ""
             python_version: "3.11"
-            pytorch: 2.9.0
+            pytorch: 2.9.1
             torch_cuda_arch_list: "9.0+PTX"
             dockerfile: "Dockerfile-base"
 #          - cuda: "128"
@@ -146,14 +146,14 @@ jobs:
             cuda_version: 12.8.1
             cudnn_version: ""
             python_version: "3.11"
-            pytorch: 2.9.0
+            pytorch: 2.9.1
             torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX"
             dockerfile: "Dockerfile-uv-base"
           - cuda: "130"
             cuda_version: 13.0.0
             cudnn_version: ""
             python_version: "3.11"
-            pytorch: 2.9.0
+            pytorch: 2.9.1
             torch_cuda_arch_list: "9.0+PTX"
             dockerfile: "Dockerfile-uv-base"
     steps:

.github/workflows/main.yml

@@ -36,6 +36,16 @@ jobs:
             pytorch: 2.8.0
             axolotl_extras:
             is_latest: true
+          - cuda: 128
+            cuda_version: 12.8.1
+            python_version: "3.11"
+            pytorch: 2.9.0
+            axolotl_extras:
+          - cuda: 128
+            cuda_version: 12.8.1
+            python_version: "3.11"
+            pytorch: 2.9.1
+            axolotl_extras:
     runs-on: axolotl-gpu-runner
     steps:
       - name: Checkout
@@ -109,6 +119,16 @@ jobs:
             pytorch: 2.8.0
             axolotl_extras:
             is_latest: true
+          - cuda: 128
+            cuda_version: 12.8.1
+            python_version: "3.11"
+            pytorch: 2.9.0
+            axolotl_extras:
+          - cuda: 128
+            cuda_version: 12.8.1
+            python_version: "3.11"
+            pytorch: 2.9.1
+            axolotl_extras:
     runs-on: axolotl-gpu-runner
     steps:
       - name: Checkout

.pre-commit-config.yaml

@@ -11,13 +11,13 @@ repos:
     -   id: no-commit-to-branch
         args: ['--branch', 'main']
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.14.3
+    rev: v0.14.7
     hooks:
     -   id: ruff
         args: [--fix]
     -   id: ruff-format
 -   repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v1.18.2
+    rev: v1.19.0
     hooks:
     - id: mypy
       additional_dependencies:
@@ -26,7 +26,7 @@ repos:
             'pydantic>=2.5.3',
         ]
 -   repo: https://github.com/PyCQA/bandit
-    rev: 1.8.6
+    rev: 1.9.2
     hooks:
     -   id: bandit
         args: [

README.md

@@ -29,6 +29,7 @@
 
 ## 🎉 Latest Updates
 
+- 2025/11: Axolotl now includes support for [Olmo3](https://github.com/axolotl-ai-cloud/axolotl/blob/main/examples/olmo3).
 - 2025/10: New model support has been added in Axolotl for: [Qwen3 Next](https://github.com/axolotl-ai-cloud/axolotl/blob/main/examples/qwen3-next), [Qwen2.5-vl, Qwen3-vl](https://github.com/axolotl-ai-cloud/axolotl/tree/main/examples/qwen2_5-vl), [Qwen3, Qwen3MoE](https://github.com/axolotl-ai-cloud/axolotl/tree/main/examples/qwen3), [Granite 4](https://github.com/axolotl-ai-cloud/axolotl/tree/main/examples/granite4), [HunYuan](https://github.com/axolotl-ai-cloud/axolotl/tree/main/examples/hunyuan), [Magistral 2509](https://github.com/axolotl-ai-cloud/axolotl/tree/main/examples/magistral#vision), [Apertus](https://github.com/axolotl-ai-cloud/axolotl/tree/main/examples/apertus), and [Seed-OSS](https://github.com/axolotl-ai-cloud/axolotl/tree/main/examples/seed-oss).
 - 2025/09: Axolotl now has text diffusion training. Read more [here](https://github.com/axolotl-ai-cloud/axolotl/tree/main/src/axolotl/integrations/diffusion).
 - 2025/08: QAT has been updated to include NVFP4 support. See [PR](https://github.com/axolotl-ai-cloud/axolotl/pull/3107).

docker/Dockerfile-base

@@ -51,7 +51,7 @@ RUN git lfs install --skip-repo && \
     pip3 install -U --no-cache-dir pydantic==1.10.10 && \
     pip3 cache purge
 
-RUN if [ "$PYTORCH_VERSION" = "2.9.0" ] && [ "$CUDA" = "128" ] ; then \
+RUN if [ "$PYTORCH_VERSION" = "2.9.1" ] && [ "$CUDA" = "128" ] ; then \
         wget https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/v0.4.17/flash_attn-2.8.3+cu128torch2.9-cp311-cp311-linux_x86_64.whl; \
         pip3 install --no-cache-dir flash_attn-2.8.3+cu128torch2.9-cp311-cp311-linux_x86_64.whl; \
         rm flash_attn-2.8.3+cu128torch2.9-cp311-cp311-linux_x86_64.whl; \

docs/multi-gpu.qmd

@@ -4,7 +4,7 @@ format:
   html:
     toc: true
     toc-depth: 3
-    number-sections: true
+    # number-sections: true
     code-tools: true
 execute:
   enabled: false
@@ -14,12 +14,18 @@ This guide covers advanced training configurations for multi-GPU setups using Ax
 
 ## Overview {#sec-overview}
 
-Axolotl supports several methods for multi-GPU training:
+When training on multiple GPUs, Axolotl supports 3 sharding/parallelism strategies. Additionally, you can layer specific optimization features on top of that strategy.
 
-- DeepSpeed (recommended)
-- FSDP (Fully Sharded Data Parallel)
-- Sequence parallelism
-- FSDP + QLoRA
+You generally cannot combine these strategies; they are mutually exclusive.
+
+1.  **DeepSpeed**: Powerful optimization library, supports ZeRO stages 1-3.
+2.  **FSDP (Fully Sharded Data Parallel)**: PyTorch's native sharding implementation (Recommended).
+3.  **DDP (Distributed Data Parallel)**: PyTorch's native parallelism implementation (Default if neither of the above are selected).
+
+These features can often be combined with the strategies above:
+
+*   **Sequence Parallelism**: Splits long sequences across GPUs (Compatible with DDP, DeepSpeed, and FSDP).
+*   **FSDP + QLoRA**: Combines 4-bit quantization with FSDP (Specific to FSDP).
 
 ## DeepSpeed {#sec-deepspeed}
 
@@ -65,12 +71,18 @@ Start from Stage 1 -> Stage 2 -> Stage 3.
 
 ## Fully Sharded Data Parallel (FSDP) {#sec-fsdp}
 
+FSDP allows you to shard model parameters, gradients, and optimizer states across data parallel workers.
+
 ::: {.callout-note}
 
 FSDP2 is recommended for new users. FSDP1 is deprecated and will be removed in an upcoming release of Axolotl.
 
 :::
 
+### FSDP + QLoRA {#sec-fsdp-qlora}
+
+For combining FSDP with QLoRA, see our [dedicated guide](fsdp_qlora.qmd).
+
 ### Migrating from FSDP1 to FSDP2 {#sec-migrate-fsdp1-fsdp2}
 
 To migrate your config from FSDP1 to FSDP2, you must use the `fsdp_version` top-level config field to specify the FSDP version, and
@@ -145,10 +157,6 @@ single sequence causes OOM errors during model training.
 
 See our [dedicated guide](sequence_parallelism.qmd) for more information.
 
-### FSDP + QLoRA {#sec-fsdp-qlora}
-
-For combining FSDP with QLoRA, see our [dedicated guide](fsdp_qlora.qmd).
-
 ## Performance Optimization {#sec-performance}
 
 ### Liger Kernel Integration {#sec-liger}

examples/colab-notebooks/colab-axolotl-example.ipynb

@@ -40,7 +40,7 @@
     "%%capture\n",
     "# This step can take ~5-10 minutes to install dependencies\n",
     "!pip install --no-build-isolation axolotl[flash-attn]>=0.9.1\n",
-    "!pip install \"cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@8a1a0ec\""
+    "!pip install \"cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@5eff953\""
    ]
   },
   {

examples/olmo3/README.md

@@ -0,0 +1,46 @@
+# Finetune Allenai's Olmo 3 with Axolotl
+
+[Olmo 3](https://huggingface.co/collections/allenai/olmo-3) are a family of 7B and 32B models open source models trained by The Allen Institute for Artificial Intelligence.
+
+This guide shows how to fine-tune it with Axolotl with multi-turn conversations and proper masking.
+
+## Getting started
+
+1.  Install Axolotl following the [installation guide](https://docs.axolotl.ai/docs/installation.html).
+
+    Here is an example of how to install from pip:
+    ```bash
+    # Ensure you have a compatible version of Pytorch installed
+    pip3 install packaging setuptools wheel ninja
+    pip3 install --no-build-isolation 'axolotl[flash-attn]>=0.12.0'
+
+    # Install Cut Cross Entropy
+    python scripts/cutcrossentropy_install.py | sh
+    ```
+
+2. Run the finetuning example:
+
+```bash
+axolotl train examples/olmo3/olmo3-7b-qlora.yaml
+```
+
+Let us know how it goes. Happy finetuning! 🚀
+
+### TIPS
+
+- The example config can be re-used for Olmo and Olmo 2.
+- You can run a full finetuning by removing the `adapter: qlora` and `load_in_4bit: true` from the config.
+- Read more on how to load your own dataset at [docs](https://docs.axolotl.ai/docs/dataset_loading.html).
+- The dataset format follows the OpenAI Messages format as seen [here](https://docs.axolotl.ai/docs/dataset-formats/conversation.html#chat_template).
+
+## Optimization Guides
+
+Please check the [Optimizations doc](https://docs.axolotl.ai/docs/optimizations.html).
+
+## Related Resources
+
+- [Olmo 3 Blog](https://allenai.org/blog/olmo3)
+- [Axolotl Docs](https://docs.axolotl.ai)
+- [Axolotl Website](https://axolotl.ai)
+- [Axolotl GitHub](https://github.com/axolotl-ai-cloud/axolotl)
+- [Axolotl Discord](https://discord.gg/7m9sfhzaf3)

examples/olmo3/olmo3-7b-qlora.yaml

@@ -0,0 +1,64 @@
+base_model: allenai/Olmo-3-7B-Instruct-SFT
+
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+
+plugins:
+  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
+
+load_in_8bit: false
+load_in_4bit: true
+
+datasets:
+  - path: fozziethebeat/alpaca_messages_2k_test
+    type: chat_template
+
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.1
+output_dir: ./outputs/lora-out
+
+adapter: qlora
+lora_model_dir:
+
+sequence_len: 2048
+sample_packing: true
+
+lora_r: 32
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_linear: true
+lora_target_modules:
+  - gate_proj
+  - down_proj
+  - up_proj
+  - q_proj
+  - v_proj
+  - k_proj
+  - o_proj
+
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 4
+micro_batch_size: 2
+num_epochs: 1
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 0.0002
+
+bf16: auto
+tf32: false
+
+gradient_checkpointing: true
+resume_from_checkpoint:
+logging_steps: 1
+flash_attention: true
+
+warmup_ratio: 0.1
+evals_per_epoch: 1
+saves_per_epoch: 1
+
+# save_first_step: true  # uncomment this to validate checkpoint saving works with your config

examples/seed-oss/README.md

@@ -6,21 +6,17 @@ This guide shows how to fine-tune it with Axolotl with multi-turn conversations
 
 ## Getting started
 
-1. Install Axolotl following the [installation guide](https://docs.axolotl.ai/docs/installation.html). You need to install from main as Seed-OSS is only on nightly or use our latest [Docker images](https://docs.axolotl.ai/docs/docker.html).
+1.  Install Axolotl following the [installation guide](https://docs.axolotl.ai/docs/installation.html).
 
-    Here is an example of how to install from main for pip:
+    Here is an example of how to install from pip:
+    ```bash
+    # Ensure you have a compatible version of Pytorch installed
+    pip3 install packaging setuptools wheel ninja
+    pip3 install --no-build-isolation 'axolotl[flash-attn]>=0.12.0'
 
-```bash
-# Ensure you have Pytorch installed (Pytorch 2.6.0 min)
-git clone https://github.com/axolotl-ai-cloud/axolotl.git
-cd axolotl
-
-pip3 install packaging==23.2 setuptools==75.8.0 wheel ninja
-pip3 install --no-build-isolation -e '.[flash-attn]'
-
-# Install Cut Cross Entropy
-python scripts/cutcrossentropy_install.py | sh
-```
+    # Install Cut Cross Entropy
+    python scripts/cutcrossentropy_install.py | sh
+    ```
 
 2. Run the finetuning example:
 
@@ -41,9 +37,7 @@ Let us know how it goes. Happy finetuning! 🚀
 
 ## Optimization Guides
 
-- [Multi-GPU Training](https://docs.axolotl.ai/docs/multi-gpu.html)
-- [Multi-Node Training](https://docs.axolotl.ai/docs/multi-node.html)
-- [LoRA Optimizations](https://docs.axolotl.ai/docs/lora_optims.html)
+Please check the [Optimizations doc](https://docs.axolotl.ai/docs/optimizations.html).
 
 ## Related Resources
 

examples/smolvlm2/README.md

@@ -37,9 +37,7 @@ This guide shows how to fine-tune SmolVLM2 models with Axolotl.
 
 ## Optimization Guides
 
-- [Multi-GPU Training](https://docs.axolotl.ai/docs/multi-gpu.html)
-- [LoRA Optimizations](https://docs.axolotl.ai/docs/lora_optims.html)
-- [Multi-Node Training](https://docs.axolotl.ai/docs/multi-node.html)
+Please check the [Optimizations doc](https://docs.axolotl.ai/docs/optimizations.html).
 
 ## Related Resources
 

requirements.txt

@@ -11,9 +11,9 @@ liger-kernel==0.6.3
 packaging==23.2
 
 huggingface_hub>=0.36.0
-peft>=0.17.1
+peft>=0.18.0
 tokenizers>=0.22.1
-transformers==4.57.1
+transformers==4.57.3
 accelerate==1.11.0
 datasets==4.4.1
 deepspeed>=0.17.0
@@ -42,7 +42,6 @@ numpy>=2.2.6
 # qlora things
 evaluate==0.4.1
 scipy
-scikit-learn==1.4.2
 nvidia-ml-py==12.560.30
 art
 tensorboard

scripts/cutcrossentropy_install.py

@@ -29,5 +29,5 @@ UV_PREFIX = "uv " if USE_UV else ""
 
 print(
     UNINSTALL_PREFIX
-    + f'{UV_PREFIX}pip install "cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@8a1a0ec"'
+    + f'{UV_PREFIX}pip install "cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@5eff953"'
 )

src/axolotl/integrations/cut_cross_entropy/README.md

@@ -19,7 +19,7 @@ python scripts/cutcrossentropy_install.py | sh
 
 - If you are installing from pip
 ```bash
-pip3 uninstall -y cut-cross-entropy && pip3 install "cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@8a1a0ec"
+pip3 uninstall -y cut-cross-entropy && pip3 install "cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@5eff953"
 ```
 
 ## Usage
@@ -65,6 +65,9 @@ plugins:
 - mistral3
 - mixtral
 - mllama
+- olmo
+- olmo2
+- olmo3
 - phi
 - phi3
 - phi4_multimodal

src/axolotl/integrations/cut_cross_entropy/__init__.py

@@ -35,7 +35,7 @@ LOG = get_logger(__name__)
 
 _CCE_INSTALL_MESSAGE = (
     "Please install Axolotl's fork of cut_cross_entropy with transformers support using "
-    '`pip install "cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@8a1a0ec"`'
+    '`pip install "cut-cross-entropy[transformers] @ git+https://github.com/axolotl-ai-cloud/ml-cross-entropy.git@5eff953"`'
 )
 
 

src/axolotl/loaders/adapter.py

@@ -102,6 +102,8 @@ def load_lora(
         lora_config_kwargs["layer_replication"] = cfg.peft_layer_replication
     if cfg.peft_trainable_token_indices:
         lora_config_kwargs["trainable_token_indices"] = cfg.peft_trainable_token_indices
+    if cfg.peft_ensure_weight_tying is not None:
+        lora_config_kwargs["ensure_weight_tying"] = cfg.peft_ensure_weight_tying
 
     # Determine the correct PEFT task type
     model_cls = type(model).__name__

src/axolotl/monkeypatch/multipack.py

@@ -49,6 +49,9 @@ SUPPORTED_MULTIPACK_MODEL_TYPES = [
     "seed_oss",
     "lfm2",
     "lfm2_moe",
+    "olmo",
+    "olmo2",
+    "olmo3",
 ]
 
 

src/axolotl/utils/chat_templates/templates/exaone4.jinja

@@ -0,0 +1,126 @@
+{%- if not skip_think is defined %}
+  {%- set skip_think = true %}
+{%- endif %}
+{%- set role_indicators = {
+    'user': '[|user|]\n',
+    'assistant': '[|assistant|]\n',
+    'system': '[|system|]\n',
+    'tool': '[|tool|]\n'
+} %}
+{%- set end_of_turn = '[|endofturn|]\n' %}
+{%- macro available_tools(tools) %}
+    {{- "# Available Tools" }}
+    {{- "\nYou can use none, one, or multiple of the following tools by calling them as functions to help with the user’s query." }}
+    {{- "\nHere are the tools available to you in JSON format within <tool> and </tool> tags:\n" }}
+    {%- for tool in tools %}
+        {{- "<tool>" }}
+        {{- tool | tojson(ensure_ascii=False) | safe }}
+        {{- "</tool>\n" }}
+    {%- endfor %}
+    {{- "\nFor each function call you want to make, return a JSON object with function name and arguments within <tool_call> and </tool_call> tags, like:" }}
+    {{- "\n<tool_call>{\"name\": function_1_name, \"arguments\": {argument_1_name: argument_1_value, argument_2_name: argument_2_value}}</tool_call>" }}
+    {{- "\n<tool_call>{\"name\": function_2_name, \"arguments\": {...}}</tool_call>\n..." }}
+    {{- "\nNote that if no argument name is specified for a tool, you can just print the argument value directly, without the argument name or JSON formatting." }}
+{%- endmacro %}
+{%- set ns = namespace(last_query_index = messages|length - 1) %}
+{%- for message in messages %}
+    {%- if message.role == "user" and message.content is string %}
+        {%- set ns.last_query_index = loop.index0 -%}
+    {%- endif %}
+{%- endfor %}
+{%- for i in range(messages | length) %}
+    {%- set msg = messages[i] %}
+    {%- set role = msg.role %}
+    {%- if role not in role_indicators %}
+        {{- raise_exception('Unknown role: ' ~ role) }}
+    {%- endif %}
+    {# ---- Case A: If the first message is "system", handle it here alone (without continue) ---- #}
+    {%- if i == 0 and role == 'system' %}
+            {{- role_indicators['system'] }}
+            {{- msg.content }}
+            {%- if tools is defined and tools %}
+                {{- "\n\n" }}{{- available_tools(tools) }}
+            {%- endif %}
+            {{- end_of_turn -}}
+    {%- else %}
+    {# ---- Case B: If the first message is tools instead of system, inject the system tools preamble ---- #}
+        {%- if i == 0 and tools is defined and tools %}
+            {{- role_indicators['system'] }}
+            {{- available_tools(tools) }}
+            {{- end_of_turn -}}
+        {%- endif %}
+    {%- endif %}
+    {%- if role == 'assistant' %}
+        {{- role_indicators['assistant'] }}
+        {%- if msg.content %}
+            {%- if "</think>" in msg.content %}
+                {%- set content = msg.content.split('</think>')[-1].strip() %}
+                {%- set reasoning_content = msg.content.split('</think>')[0].strip() %}
+                {%- if reasoning_content.startswith("<think>") %}
+                    {%- set reasoning_content = reasoning_content[7:].strip() %}
+                {%- endif %}
+            {%- else %}
+                {%- set content = msg.content %}
+            {%- endif %}
+            {%- if msg.reasoning_content %}
+                {%- set reasoning_content = msg.reasoning_content %}
+            {%- endif %}
+            {%- if (not skip_think and loop.last) and reasoning_content is defined %}
+                {{- "<think>\n" }}
+                {{- reasoning_content}}
+                {{- "\n</think>\n\n" }}
+            {%- else %}
+                {{- "<think>\n\n</think>\n\n" }}
+            {%- endif %}
+            {{- content }}
+        {%- endif %}
+        {%- if msg.tool_calls %}
+            {%- if msg.content %}
+                {{- "\n" }}
+            {%- else %}
+                {{- "<think>\n\n</think>\n\n" }}
+            {%- endif %}
+            {%- for tool_call in msg.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- set arguments = tool_call.arguments %}
+                {%- elif tool_call.parameters is defined %}
+                    {%- set arguments = tool_call.parameters %}
+                {%- else %}
+                    {{- raise_exception('arguments or parameters are mandatory: ' ~ tool_call) }}
+                {%- endif %}
+                {{- "<tool_call>" }}{"name": "{{- tool_call.name }}", "arguments": {{ arguments | tojson(ensure_ascii=False) | safe }}}{{- "</tool_call>" }}
+                {%- if not loop.last %}
+                    {{- "\n" }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- end_of_turn -}}
+    {%- elif role == "tool" %}
+        {%- if i == 0 or messages[i - 1].role != "tool" %}
+            {{- role_indicators['tool'] }}
+        {%- endif %}
+        {%- if msg.content is defined %}
+            {{- "<tool_result>" }}{"result": {{ msg.content | tojson(ensure_ascii=False) | safe }}}{{- "</tool_result>" }}
+        {%- endif %}
+        {%- if loop.last or messages[i + 1].role != "tool" %}
+            {{- end_of_turn -}}
+        {%- else %}
+            {{- "\n" }}
+        {%- endif %}
+    {%- else %}
+        {{- role_indicators[role] }}
+        {{- msg.content }}
+        {{- end_of_turn -}}
+    {%- endif %}
+{% endfor %}
+{%- if add_generation_prompt %}
+    {{- role_indicators['assistant'] }}
+    {%- if enable_thinking is defined and enable_thinking is true %}
+        {{- "<think>\n" }}
+    {%- else %}
+        {{- "<think>\n\n</think>\n\n" }}
+    {%- endif %}
+{%- endif %}

src/axolotl/utils/schemas/enums.py

@@ -58,6 +58,7 @@ class ChatTemplate(str, Enum):
     falcon_h1 = "falcon_h1"
     tokenizer_default = "tokenizer_default"
     exaone = "exaone"
+    exaone4 = "exaone4"
     metharme = "metharme"
     pixtral = "pixtral"
     llava = "llava"

src/axolotl/utils/schemas/peft.py

@@ -100,6 +100,15 @@ class LoraConfig(BaseModel):
             )
         },
     )
+    peft_ensure_weight_tying: bool | None = Field(
+        default=None,
+        json_schema_extra={
+            "description": (
+                "Whether to tie adapter weights for tied model weights. "
+                "See https://github.com/huggingface/peft/issues/2864"
+            )
+        },
+    )
 
     qlora_sharded_model_loading: bool | None = Field(
         default=False,