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/qwen3.5/7b-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