add: qwen 3.5

examples/qwen3.5/122b-a10b-moe-qlora.yaml

@@ -0,0 +1,71 @@
+base_model: Qwen/Qwen3.5-122B-A10B
+
+plugins:
+  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
+strict: false
+
+chat_template: qwen3_5
+datasets:
+  - path: mlabonne/FineTome-100k
+    type: chat_template
+    split: train[:20%]
+    field_messages: conversations
+    message_property_mappings:
+      role: from
+      content: value
+val_set_size: 0.0
+output_dir: ./outputs/out
+dataset_prepared_path: last_run_prepared
+
+sequence_len: 2048
+sample_packing: true
+
+load_in_4bit: true
+quantize_moe_experts: true
+adapter: qlora
+lora_r: 16
+lora_alpha: 32
+lora_dropout: 0
+lora_target_modules:
+  - q_proj
+  - k_proj
+  - v_proj
+  - o_proj
+
+#lora_target_parameters:
+#   - mlp.experts.gate_up_proj
+#   - mlp.experts.down_proj
+
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 2
+micro_batch_size: 1
+num_epochs: 1
+optimizer: adamw_torch_4bit
+lr_scheduler: cosine
+learning_rate: 0.0002
+
+bf16: auto
+tf32: true
+
+
+lora_mlp_kernel: false
+lora_qkv_kernel: false
+lora_o_kernel: false
+
+gradient_checkpointing: true
+gradient_checkpointing_kwargs:
+  use_reentrant: false
+resume_from_checkpoint:
+logging_steps: 1
+flash_attention: true
+
+warmup_ratio: 0.1
+evals_per_epoch: 4
+saves_per_epoch: 1
+weight_decay: 0.0
+special_tokens:

examples/qwen3.5/27b-qlora.yaml

@@ -0,0 +1,72 @@
+base_model: Qwen/Qwen3.5-27B
+# Automatically upload checkpoint and final model to HF
+# hub_model_id: username/custom_model_name
+# Note: Qwen3.5 is an early-fusion VLM (image+text). This config fine-tunes
+# the text-only path. For multimodal (image+text) fine-tuning, add image
+# columns to your dataset following axolotl's multimodal dataset format.
+
+plugins:
+  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
+strict: false
+
+chat_template: qwen3_5
+datasets:
+  - path: mlabonne/FineTome-100k
+    type: chat_template
+    split: train[:20%]
+    field_messages: conversations
+    message_property_mappings:
+      role: from
+      content: value
+val_set_size: 0.0
+output_dir: ./outputs/out
+dataset_prepared_path: last_run_prepared
+
+sequence_len: 2048
+sample_packing: true
+
+load_in_4bit: true
+adapter: qlora
+lora_r: 16
+lora_alpha: 32
+lora_target_modules:
+  - q_proj
+  - k_proj
+  - v_proj
+  - o_proj
+  - down_proj
+  - up_proj
+  # Uncomment below to also target the linear attention projections.
+  # These use separate in_proj_qkv / in_proj_z / out_proj (Qwen3.5-specific).
+  # - linear_attn.in_proj_qkv
+  # - linear_attn.in_proj_z
+  # - linear_attn.out_proj
+
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 2
+micro_batch_size: 1
+num_epochs: 1
+optimizer: adamw_torch_4bit
+lr_scheduler: cosine
+learning_rate: 0.0002
+
+bf16: auto
+tf32: true
+
+gradient_checkpointing: true
+gradient_checkpointing_kwargs:
+  use_reentrant: false
+resume_from_checkpoint:
+logging_steps: 1
+flash_attention: true
+
+warmup_ratio: 0.1
+evals_per_epoch: 4
+saves_per_epoch: 1
+weight_decay: 0.0
+special_tokens:

examples/qwen3.5/35b-a3b-moe-qlora.yaml

@@ -0,0 +1,70 @@
+base_model: Qwen/Qwen3.5-35B-A3B
+
+plugins:
+  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
+strict: false
+
+chat_template: qwen3_5
+datasets:
+  - path: mlabonne/FineTome-100k
+    type: chat_template
+    split: train[:20%]
+    field_messages: conversations
+    message_property_mappings:
+      role: from
+      content: value
+val_set_size: 0.0
+output_dir: ./outputs/out
+dataset_prepared_path: last_run_prepared
+
+sequence_len: 2048
+sample_packing: true
+
+load_in_4bit: true
+quantize_moe_experts: true
+adapter: qlora
+lora_r: 16
+lora_alpha: 32
+lora_dropout: 0
+lora_target_modules:
+  - q_proj
+  - k_proj
+  - v_proj
+  - o_proj
+
+#lora_target_parameters:
+#   - mlp.experts.gate_up_proj
+#   - mlp.experts.down_proj
+
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 2
+micro_batch_size: 1
+num_epochs: 1
+optimizer: adamw_torch_4bit
+lr_scheduler: cosine
+learning_rate: 0.0002
+
+bf16: auto
+tf32: true
+
+lora_mlp_kernel: false
+lora_qkv_kernel: false
+lora_o_kernel: false
+
+gradient_checkpointing: true
+gradient_checkpointing_kwargs:
+  use_reentrant: false
+resume_from_checkpoint:
+logging_steps: 1
+flash_attention: true
+
+warmup_ratio: 0.1
+evals_per_epoch: 4
+saves_per_epoch: 1
+weight_decay: 0.0
+special_tokens:

examples/qwen3.5/7b-lora-vision.yaml

@@ -0,0 +1,72 @@
+base_model: Qwen/Qwen3.5-7B
+processor_type: AutoProcessor
+
+# Qwen3.5-7B and above are early-fusion VLMs (Qwen3_5ForConditionalGeneration).
+# Vision and text tokens are processed together by the same transformer layers.
+# Note: Qwen3.5-2B is a text-only model — the smallest VLM is Qwen3.5-7B.
+
+# These 3 lines are required for vision/multimodal training
+skip_prepare_dataset: true
+remove_unused_columns: false
+sample_packing: false
+
+chat_template: qwen3_5
+datasets:
+  - path: HuggingFaceH4/llava-instruct-mix-vsft
+    type: chat_template
+    split: train[:1%]
+
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.0
+output_dir: ./outputs/out
+
+adapter: lora
+lora_model_dir:
+
+sequence_len: 8192
+pad_to_sequence_len: false
+
+lora_r: 32
+lora_alpha: 16
+lora_dropout: 0.05
+# Targets the language model attention and MLP layers.
+# Qwen3.5 is early-fusion: all layers (including those seeing vision tokens) share
+# the same transformer stack, so standard attention targets work for both modalities.
+lora_target_modules:
+  - q_proj
+  - k_proj
+  - v_proj
+  - o_proj
+  - down_proj
+  - up_proj
+  # Uncomment to also target the linear attention (GatedDeltaNet) projections:
+  # - linear_attn.in_proj_qkv
+  # - linear_attn.in_proj_z
+  # - linear_attn.out_proj
+
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 4
+micro_batch_size: 1
+num_epochs: 1
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 0.0002
+
+bf16: true
+tf32: true
+
+gradient_checkpointing: true
+gradient_checkpointing_kwargs:
+  use_reentrant: false
+logging_steps: 1
+flash_attention: true
+
+warmup_ratio: 0.1
+evals_per_epoch: 1
+saves_per_epoch: 1
+weight_decay: 0.0

examples/qwen3.5/README.md

@@ -0,0 +1,61 @@
+# Finetune Qwen3.5 with Axolotl
+
+[Qwen3.5](https://huggingface.co/collections/Qwen/qwen35-68452f3bc6e4b7cfb4e1c803) is a hybrid architecture model series combining Gated DeltaNet linear attention with standard Transformer attention. Models from 7B onwards are early-fusion vision-language models (`Qwen3_5ForConditionalGeneration`), meaning vision and text tokens are processed through the same transformer stack. The 2B variant is text-only.
+
+Available configs:
+
+| Config | Model | Type |
+|---|---|---|
+| `27b-qlora.yaml` | Qwen3.5-27B | Dense VLM, text-only path |
+| `35b-a3b-moe-qlora.yaml` | Qwen3.5-35B-A3B | MoE, text-only path |
+| `122b-a10b-moe-qlora.yaml` | Qwen3.5-122B-A10B | MoE, text-only path |
+| `7b-lora-vision.yaml` | Qwen3.5-7B | Vision+text (multimodal) |
+
+## Getting started
+
+1. Install Axolotl following the [installation guide](https://docs.axolotl.ai/docs/installation.html).
+
+2. Install [Cut Cross Entropy](https://docs.axolotl.ai/docs/custom_integrations.html#cut-cross-entropy) to reduce training VRAM usage.
+
+3. Install FLA for sample packing support with the Gated DeltaNet linear attention layers:
+```bash
+pip3 uninstall -y causal-conv1d && pip3 install flash-linear-attention==0.4.1
+```
+> FLA is required when `sample_packing: true`. Without it, training raises a `RuntimeError` on packed sequences. Vision configs use `sample_packing: false` so FLA is optional there.
+
+4. Run a finetuning example:
+
+```bash
+# Dense 27B text-only (QLoRA, ~47 GiB VRAM with sample packing)
+axolotl train examples/qwen3.5/27b-qlora.yaml
+
+# MoE 35B-A3B text-only (QLoRA)
+axolotl train examples/qwen3.5/35b-a3b-moe-qlora.yaml
+
+# MoE 122B-A10B text-only (QLoRA)
+axolotl train examples/qwen3.5/122b-a10b-moe-qlora.yaml
+
+# 7B vision+text (LoRA, multimodal dataset)
+axolotl train examples/qwen3.5/7b-lora-vision.yaml
+```
+
+### TIPS
+
+- For inference, you can experiment with `temperature: 0.7`, `top_p: 0.8`, `top_k: 20`, and `min_p: 0`.
+- You can run a full finetuning by removing `adapter: qlora` and `load_in_4bit: true`. See [Multi-GPU](#optimization-guides) below.
+- Read more on loading 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).
+- For **multimodal** finetuning, set `processor_type: AutoProcessor`, `skip_prepare_dataset: true`, and `remove_unused_columns: false` as shown in `7b-lora-vision.yaml`.
+- The Gated DeltaNet linear attention layers (`linear_attn.*`) can optionally be added to `lora_target_modules` — they are commented out by default.
+
+## Optimization Guides
+
+- [Optimizations Guide](https://docs.axolotl.ai/docs/optimizations.html)
+
+## Related Resources
+
+- [Qwen3.5 Blog](https://qwenlm.github.io/blog/qwen3.5/)
+- [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)

src/axolotl/common/architectures.py

@@ -12,6 +12,7 @@
     "mixtral": "MixtralSparseMoeBlock",
     "qwen2_moe": "Qwen2MoeSparseMoeBlock",
     "qwen3_moe": "Qwen3MoeSparseMoeBlock",
+    "qwen3_5_moe": "Qwen3_5MoeSparseMoeBlock",
     "qwen3_vl_moe": "Qwen3VLMoeTextSparseMoeBlock",
     "deepseek_v2": "DeepseekV2MoE",
     "deepseek_v3": "DeepseekV3MoE",

src/axolotl/loaders/patch_manager.py

@@ -239,6 +239,31 @@ def _apply_model_specific_patches(self):
 
             patch_qwen3_next_modeling_packing()
 
+        if self.cfg.model_config_type == "qwen3_5" and self.cfg.sample_packing:
+            from axolotl.monkeypatch.models.qwen3_5.modeling import (
+                patch_qwen3_5_modeling_packing,
+            )
+
+            patch_qwen3_5_modeling_packing()
+
+        if self.cfg.model_config_type == "qwen3_5_moe" and self.cfg.sample_packing:
+            from axolotl.monkeypatch.models.qwen3_5.modeling import (
+                patch_qwen3_5_moe_modeling_packing,
+            )
+
+            patch_qwen3_5_moe_modeling_packing()
+
+        if (
+            self.cfg.model_config_type in ["qwen3_5", "qwen3_5_moe"]
+            and self.cfg.is_multimodal
+            and self.cfg.flash_attention
+        ):
+            from axolotl.monkeypatch.models.qwen3_5.modeling import (
+                patch_qwen3_5_vlm_flash_attention,
+            )
+
+            patch_qwen3_5_vlm_flash_attention()
+
         if self.cfg.model_config_type == "kimi_linear":
             from axolotl.monkeypatch.models.kimi_linear.patch_kimi_linear import (
                 patch_kimi_model,