Video-Text-to-Text
Transformers
Safetensors
English
qwen3_5
image-text-to-text
video
multimodal
video-captioning
temporal-grounding
qwen
text-generation
VLM
gptq
4-bit precision
quantized
custom_code
Instructions to use prasannaJagadesh/marlin-2B-GPTQ-4BITS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use prasannaJagadesh/marlin-2B-GPTQ-4BITS with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("prasannaJagadesh/marlin-2B-GPTQ-4BITS", trust_remote_code=True) model = AutoModelForMultimodalLM.from_pretrained("prasannaJagadesh/marlin-2B-GPTQ-4BITS", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "Qwen3_5ForConditionalGeneration" | |
| ], | |
| "auto_map": { | |
| "AutoModelForCausalLM": "modeling_marlin.MarlinForConditionalGeneration" | |
| }, | |
| "dtype": "bfloat16", | |
| "eos_token_id": [ | |
| 248044, | |
| 248046 | |
| ], | |
| "hidden_size": 2048, | |
| "image_token_id": 248056, | |
| "model_type": "qwen3_5", | |
| "pad_token_id": 248044, | |
| "quantization_config": { | |
| "bits": 4, | |
| "checkpoint_format": "gptq", | |
| "desc_act": true, | |
| "format": "gptq", | |
| "group_size": 128, | |
| "lm_head": false, | |
| "meta": { | |
| "act_group_aware": false, | |
| "auto_forward_data_parallel": true, | |
| "damp_auto_increment": 0.01, | |
| "damp_percent": 0.05, | |
| "dense_vram_strategy": "exclusive", | |
| "dense_vram_strategy_devices": null, | |
| "fallback": { | |
| "smooth": null, | |
| "strategy": "rtn", | |
| "threshold": "0.5%" | |
| }, | |
| "foem": null, | |
| "gc_mode": "interval", | |
| "gptaq": null, | |
| "hessian": { | |
| "chunk_bytes": null, | |
| "chunk_size": null, | |
| "staging_dtype": "float32" | |
| }, | |
| "mock_quantization": false, | |
| "moe_vram_strategy": "exclusive", | |
| "moe_vram_strategy_devices": null, | |
| "mse": 0.0, | |
| "offload_to_disk": true, | |
| "offload_to_disk_path": "/data/nemostation/outputs/.quantize_tmp/gptqmodel_eus5n9zo", | |
| "pack_impl": "cpu", | |
| "quantizer": [ | |
| "gptqmodel:7.1.0" | |
| ], | |
| "static_groups": false, | |
| "true_sequential": true, | |
| "uri": "https://github.com/modelcloud/gptqmodel", | |
| "wait_for_submodule_finalizers": false | |
| }, | |
| "method": "gptq", | |
| "pack_dtype": "int32", | |
| "quant_method": "gptq", | |
| "sym": true | |
| }, | |
| "rope_parameters": { | |
| "rope_theta": 10000.0, | |
| "rope_type": "default" | |
| }, | |
| "text_config": { | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attn_output_gate": true, | |
| "bos_token_id": null, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 248044, | |
| "full_attention_interval": 4, | |
| "head_dim": 256, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 6144, | |
| "layer_types": [ | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention" | |
| ], | |
| "linear_conv_kernel_dim": 4, | |
| "linear_key_head_dim": 128, | |
| "linear_num_key_heads": 16, | |
| "linear_num_value_heads": 16, | |
| "linear_value_head_dim": 128, | |
| "mamba_ssm_dtype": "float32", | |
| "max_position_embeddings": 262144, | |
| "mlp_only_layers": [], | |
| "model_type": "qwen3_5_text", | |
| "mtp_num_hidden_layers": 1, | |
| "mtp_use_dedicated_embeddings": false, | |
| "num_attention_heads": 8, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 2, | |
| "pad_token_id": 248044, | |
| "partial_rotary_factor": 0.25, | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "mrope_interleaved": true, | |
| "mrope_section": [ | |
| 11, | |
| 11, | |
| 10 | |
| ], | |
| "partial_rotary_factor": 0.25, | |
| "rope_theta": 10000000, | |
| "rope_type": "default" | |
| }, | |
| "tie_word_embeddings": true, | |
| "use_cache": true, | |
| "vocab_size": 248320, | |
| "do_sample": true | |
| }, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "5.12.1", | |
| "use_cache": true, | |
| "video_token_id": 248057, | |
| "vision_config": { | |
| "deepstack_visual_indexes": [], | |
| "depth": 24, | |
| "dtype": "bfloat16", | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 1024, | |
| "in_channels": 3, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4096, | |
| "model_type": "qwen3_5_vision", | |
| "num_heads": 16, | |
| "num_position_embeddings": 2304, | |
| "out_hidden_size": 2048, | |
| "patch_size": 16, | |
| "spatial_merge_size": 2, | |
| "temporal_patch_size": 2 | |
| }, | |
| "vision_end_token_id": 248054, | |
| "vision_start_token_id": 248053, | |
| "do_sample": true | |
| } | |