add: qwen 3.5 (#3442)

* add: qwen 3.5

* test for qwen , patch

* lint

* qwen3 fix on main

* Apply suggestions from code review

Co-authored-by: NanoCode012 <kevinvong@rocketmail.com>

* moe config

* config moe

* configs and chore

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

Co-authored-by: NanoCode012 <kevinvong@rocketmail.com>

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

Co-authored-by: NanoCode012 <kevinvong@rocketmail.com>

* chore for qwen + vlm patch

* chore lint

* qwen lint

* 3_5_moe

* Update examples/qwen3.5/README.md

---------

Co-authored-by: NanoCode012 <kevinvong@rocketmail.com>

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: