Warrior-v2-Qwen3.5-4B

yotisstudios/Warrior-v2-Qwen3.5-4B

Warrior-v2-Qwen3.5-4B is a image-text-to-text model from yotisstudios. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers.

This model was trained with Merlina. Credentials are not included — Merlina will use your own HFTOKEN and WANDBAPIKEY from .env or the form.

Downloads · 30 days

14% of all-time downloads

All-time downloads

Public

Parameters

4.5B

9.1 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors9.1 GB · 100%

At a glance

Task: Image-Text-to-Text
Library: transformers
Model type: qwen3_5
Access: Public
Created: Aug 15, 2026
Updated: Aug 15, 2026
SHA: 7e39d016

Try a prompt

Base models

Lazarus-Ai/ReAligned-Qwen3.5-4B

Datasets

yotisstudios/Warrior-SFT-v2

Model card

From the Hugging Face model README

Warrior-v2-Qwen3.5-4B

Training Configuration

Parameter	Value
Training Mode	SFT
Base Model	`Lazarus-Ai/ReAligned-Qwen3.5-4B`
Learning Rate	0.0002
Epochs	2
Batch Size	1
Gradient Accumulation	16
Effective Batch Size	16
Max Sequence Length	8192
Optimizer	paged_adamw_8bit
LR Scheduler	cosine
Warmup Ratio	0.05
Weight Decay	0.01
Max Grad Norm	0.3
Seed	42
LoRA Rank (r)	64
LoRA Alpha	128
LoRA Dropout	0.05
Target Modules	up_proj, down_proj, gate_proj, k_proj, q_proj, v_proj, o_proj
Quantization	4-bit (NF4)
GPU	NVIDIA GB10

Reproduce this training run

This model was trained with Merlina. Credentials are not included — Merlina will use your own HF_TOKEN and WANDB_API_KEY from .env or the form.

Paste this code into Merlina's Load Configuration → From Code to rebuild the exact training setup:

merlina-config-v1:H4sIAB3PgGoC_61VTY_jNgz9K4HOScbxZgczuU0L9NKZw3a36KEoBMambTWSpdVHstnF_PeSspVk0BYLFL3RFE09Pj5S34Q0GKGFCGL3TYxgUOzEb-C9sn51rFcfTji-W79fbX8QS9FiaLxyUdmRoj55UKMa-0Vjx071yQMfLMIAHttF561ZwOIFvVYjrCIHk9vYFvWackXog9j9_sdShGZAQ9cLM8XexTnxakosSog8og_57s2yBF99ol7X60q8LsUeAsp8EXmf4Sv4FFZP6u4XfNKqJxRvq7IpuhTld2pPlFNbTzijT7gUbEsvdvfb2QbtBjrd1A-zo_XWUW6xq9bVey7Y9xgZV9LIpYvkpPP2TybWnsZi9xCx2IdifC7GsRh2Moi_OaOMVgY44kRqRhAhHGQ8O67rx6dfPz49y-cX-lcjeCZYUssw46uqeinGZCQ62wyErmYaYzPIoL5iJrz30Coco4SmSSbp3G0ZIjoK39wTDvgiNY59HMTuYfNYTx5CaVy8HGyqepshoy7IIEXLgpi7njtH7tBF8u6RlVmtCYCGPf0UjLVxoLiMm-kyJkcQxSzjgJGVHGzyDV6tctmQ-p5-7oAOl8JTuVK15D_bqEKIqVU23BUNfPzpE-mA9ee0orQTRv6OHsFkEB3ogDce-YY2IrYiRULbKqYLCH-GM0sfjxfP_w2VMv8HoJ31BjKBk1WwRHvAkSI95cQR9ppQUhMOt5m5j7LFiE28OeRpeS0dn2fs-zNJk0-DTdOCIUBP4i7ApuFrsU1UZ5PlO1-ffUiCZFH3Z7pmll4z2IDctYghzvWSdEhR4UzyNUWis-46pbVEcpz_RZRUTUCkTmxnifNkyJEAct53S3ECb2i28z4s0z91ehqWal1P-2S7V5eS-PsEY7u_FORSGHioh3T10dbrpz0k90icoCQeLLQly9BxOFWkjrfckJupD4619FZB3NAvzhLXfZ-6yx_8IT8nGCcJ5H31YSt_li-8cg6ILsfLzm3ur9oaUteRNC5zOIE6oeqHSNJo4Fyo117yUufN5YvIGhvojRA3q4YimoOzaowXLfFqy3NxWT20C-lJMqzOksmRZlpJz5o5yQcmmUcQjORtsmEIjzeOOjsei4uSKp0fGVxVD9lJIxitlx556R0x33yV_eU8NEDFO_BEdaRR-XvErAySVPyH00zQvJNX1frN3Y1WjqbKYxispnZvePdBjKNUxmk0xBbM7_K8T_ODpXrGMfFGaWjeG9K60ldpZGHmRQ7-Cor2e1Syd-l2nnLi178A96M-AzMIAAA=

<details> <summary>Prefer JSON? The same config, expanded</summary>

Save this to data/configs/<name>.json, or import it via the Load Configuration dialog.

{
  "_metadata": {
    "name": "Warrior-v2-Qwen3.5-4B",
    "description": "Training configuration shared from a Merlina-trained model.",
    "tags": [],
    "schema": "merlina/training-config",
    "schema_version": 1,
    "merlina_version": "2.2.0"
  },
  "base_model": "Lazarus-Ai/ReAligned-Qwen3.5-4B",
  "output_name": "Warrior-v2-Qwen3.5-4B",
  "use_lora": true,
  "lora_r": 64,
  "lora_alpha": 128,
  "lora_dropout": 0.05,
  "target_modules": [
    "up_proj",
    "down_proj",
    "gate_proj",
    "k_proj",
    "q_proj",
    "v_proj",
    "o_proj"
  ],
  "modules_to_save": [],
  "lora_task_type": "CAUSAL_LM",
  "learning_rate": 0.0002,
  "num_epochs": 2,
  "batch_size": 1,
  "gradient_accumulation_steps": 16,
  "max_length": 8192,
  "max_prompt_length": 1024,
  "model_type": "auto",
  "training_mode": "sft",
  "beta": 0.1,
  "label_smoothing": 0.0,
  "gamma": 0.5,
  "dataset": {
    "source": {
      "source_type": "huggingface",
      "repo_id": "yotisstudios/Warrior-SFT-v2",
      "split": "train",
      "streaming": false,
      "streaming_batch_size": 10000
    },
    "additional_sources": [],
    "eval_source": {
      "source_type": "huggingface",
      "repo_id": "yotisstudios/Warrior-SFT-v2",
      "split": "val",
      "streaming": false,
      "streaming_batch_size": 10000
    },
    "format": {
      "format_type": "tokenizer",
      "enable_thinking": false,
      "auto_detect_thinking": true
    },
    "model_name": "Lazarus-Ai/ReAligned-Qwen3.5-4B",
    "convert_messages_format": true,
    "deduplicate": false,
    "dedupe_strategy": "prompt_chosen",
    "test_size": 0.01,
    "system_prompt_mode": "fill_empty",
    "training_mode": "sft"
  },
  "seed": 42,
  "max_grad_norm": 0.3,
  "warmup_ratio": 0.05,
  "eval_steps": 0.2,
  "use_4bit": true,
  "use_wandb": false,
  "push_to_hub": false,
  "merge_lora_before_upload": true,
  "hf_hub_private": false,
  "hf_namespace": "yotisstudios",
  "export_gguf": false,
  "gguf_quant_types": [
    "Q4_K_M"
  ],
  "keep_gguf_fp16": false,
  "shuffle_dataset": true,
  "weight_decay": 0.01,
  "lr_scheduler_type": "cosine",
  "gradient_checkpointing": true,
  "logging_steps": 1,
  "optimizer_type": "paged_adamw_8bit",
  "adam_beta1": 0.9,
  "adam_beta2": 0.999,
  "adam_epsilon": 1e-08,
  "adafactor_relative_step": false,
  "adafactor_scale_parameter": false,
  "adafactor_warmup_init": false,
  "adafactor_decay_rate": -0.8,
  "adafactor_clip_threshold": 1.0,
  "attn_implementation": "auto",
  "use_liger": true,
  "torch_compile": false,
  "eval_on_start": false,
  "multi_gpu_strategy": "auto"
}

</details>

Trained with Merlina

Merlina on GitHub

Task: Image-Text-to-Text
Library: transformers
Type: qwen3_5
Created: Aug 15, 2026
Updated: Aug 15, 2026