Upload Qwen2_5_VLForConditionalGeneration

README.md

@@ -0,0 +1,199 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]

config.json

@@ -0,0 +1,171 @@
+{
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2_5_vl",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pad_token_id": 151654,
+  "quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "format": "pack-quantized",
+        "input_activations": null,
+        "output_activations": null,
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": -1,
+          "num_bits": 4,
+          "observer": "mse",
+          "observer_kwargs": {},
+          "scale_dtype": null,
+          "strategy": "channel",
+          "symmetric": true,
+          "type": "int",
+          "zp_dtype": null
+        }
+      }
+    },
+    "format": "pack-quantized",
+    "global_compression_ratio": null,
+    "ignore": [
+      "lm_head"
+    ],
+    "kv_cache_scheme": null,
+    "quant_method": "compressed-tensors",
+    "quantization_status": "compressed",
+    "sparsity_config": {},
+    "transform_config": {},
+    "version": "0.13.0"
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "text_config": {
+    "_name_or_path": "Vanbitcase/ier_qwen2.5_fp",
+    "architectures": [
+      "Qwen2_5_VLForConditionalGeneration"
+    ],
+    "attention_dropout": 0.0,
+    "dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "hidden_act": "silu",
+    "hidden_size": 3584,
+    "image_token_id": 151655,
+    "initializer_range": 0.02,
+    "intermediate_size": 18944,
+    "layer_types": [
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 128000,
+    "max_window_layers": 28,
+    "model_type": "qwen2_5_vl_text",
+    "num_attention_heads": 28,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 4,
+    "pad_token_id": 151654,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "mrope_section": [
+        16,
+        24,
+        24
+      ],
+      "rope_type": "default",
+      "type": "default"
+    },
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "use_cache": true,
+    "use_sliding_window": false,
+    "video_token_id": 151656,
+    "vision_end_token_id": 151653,
+    "vision_start_token_id": 151652,
+    "vision_token_id": 151654,
+    "vocab_size": 152064
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.3",
+  "unsloth_fixed": true,
+  "unsloth_version": "2026.1.4",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vision_config": {
+    "depth": 32,
+    "dtype": "bfloat16",
+    "fullatt_block_indexes": [
+      7,
+      15,
+      23,
+      31
+    ],
+    "hidden_act": "silu",
+    "hidden_size": 1280,
+    "in_channels": 3,
+    "in_chans": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 3420,
+    "model_type": "qwen2_5_vl",
+    "num_heads": 16,
+    "out_hidden_size": 3584,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "spatial_patch_size": 14,
+    "temporal_patch_size": 2,
+    "tokens_per_second": 2,
+    "window_size": 112
+  },
+  "vision_token_id": 151654,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 151645,
+  "pad_token_id": 151654,
+  "transformers_version": "4.57.3"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38c0838afef72c14b5a7cabf1f9dd8c7fa8a5724db5064cde716dc073796d364
+size 4698506184

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c859795ad3a627a9b95bcb762e059d5b768a4a36fdd4affeff269d93fdecc67
+size 1089994880

recipe.yaml

@@ -0,0 +1,86 @@
+default_stage:
+  default_modifiers:
+    AWQModifier:
+      config_groups:
+        group_0:
+          targets: [Linear]
+          weights:
+            num_bits: 4
+            type: int
+            symmetric: true
+            group_size: -1
+            strategy: channel
+            block_structure: null
+            dynamic: false
+            actorder: null
+            scale_dtype: null
+            zp_dtype: null
+            observer: mse
+            observer_kwargs: {}
+          input_activations: null
+          output_activations: null
+          format: null
+      targets: [Linear]
+      ignore: [lm_head, model.embed_tokens, model.norm, visual.merger.mlp.0, visual.merger.mlp.2,
+        visual.patch_embed.proj, visual.blocks.0.attn.qkv, visual.blocks.0.attn.proj, visual.blocks.0.mlp.gate_proj,
+        visual.blocks.0.mlp.up_proj, visual.blocks.0.mlp.down_proj, visual.blocks.1.attn.qkv,
+        visual.blocks.1.attn.proj, visual.blocks.1.mlp.gate_proj, visual.blocks.1.mlp.up_proj,
+        visual.blocks.1.mlp.down_proj, visual.blocks.2.attn.qkv, visual.blocks.2.attn.proj,
+        visual.blocks.2.mlp.gate_proj, visual.blocks.2.mlp.up_proj, visual.blocks.2.mlp.down_proj,
+        visual.blocks.3.attn.qkv, visual.blocks.3.attn.proj, visual.blocks.3.mlp.gate_proj,
+        visual.blocks.3.mlp.up_proj, visual.blocks.3.mlp.down_proj, visual.blocks.4.attn.qkv,
+        visual.blocks.4.attn.proj, visual.blocks.4.mlp.gate_proj, visual.blocks.4.mlp.up_proj,
+        visual.blocks.4.mlp.down_proj, visual.blocks.5.attn.qkv, visual.blocks.5.attn.proj,
+        visual.blocks.5.mlp.gate_proj, visual.blocks.5.mlp.up_proj, visual.blocks.5.mlp.down_proj,
+        visual.blocks.6.attn.qkv, visual.blocks.6.attn.proj, visual.blocks.6.mlp.gate_proj,
+        visual.blocks.6.mlp.up_proj, visual.blocks.6.mlp.down_proj, visual.blocks.7.attn.qkv,
+        visual.blocks.7.attn.proj, visual.blocks.7.mlp.gate_proj, visual.blocks.7.mlp.up_proj,
+        visual.blocks.7.mlp.down_proj, visual.blocks.8.attn.qkv, visual.blocks.8.attn.proj,
+        visual.blocks.8.mlp.gate_proj, visual.blocks.8.mlp.up_proj, visual.blocks.8.mlp.down_proj,
+        visual.blocks.9.attn.qkv, visual.blocks.9.attn.proj, visual.blocks.9.mlp.gate_proj,
+        visual.blocks.9.mlp.up_proj, visual.blocks.9.mlp.down_proj, visual.blocks.10.attn.qkv,
+        visual.blocks.10.attn.proj, visual.blocks.10.mlp.gate_proj, visual.blocks.10.mlp.up_proj,
+        visual.blocks.10.mlp.down_proj, visual.blocks.11.attn.qkv, visual.blocks.11.attn.proj,
+        visual.blocks.11.mlp.gate_proj, visual.blocks.11.mlp.up_proj, visual.blocks.11.mlp.down_proj,
+        visual.blocks.12.attn.qkv, visual.blocks.12.attn.proj, visual.blocks.12.mlp.gate_proj,
+        visual.blocks.12.mlp.up_proj, visual.blocks.12.mlp.down_proj, visual.blocks.13.attn.qkv,
+        visual.blocks.13.attn.proj, visual.blocks.13.mlp.gate_proj, visual.blocks.13.mlp.up_proj,
+        visual.blocks.13.mlp.down_proj, visual.blocks.14.attn.qkv, visual.blocks.14.attn.proj,
+        visual.blocks.14.mlp.gate_proj, visual.blocks.14.mlp.up_proj, visual.blocks.14.mlp.down_proj,
+        visual.blocks.15.attn.qkv, visual.blocks.15.attn.proj, visual.blocks.15.mlp.gate_proj,
+        visual.blocks.15.mlp.up_proj, visual.blocks.15.mlp.down_proj, visual.blocks.16.attn.qkv,
+        visual.blocks.16.attn.proj, visual.blocks.16.mlp.gate_proj, visual.blocks.16.mlp.up_proj,
+        visual.blocks.16.mlp.down_proj, visual.blocks.17.attn.qkv, visual.blocks.17.attn.proj,
+        visual.blocks.17.mlp.gate_proj, visual.blocks.17.mlp.up_proj, visual.blocks.17.mlp.down_proj,
+        visual.blocks.18.attn.qkv, visual.blocks.18.attn.proj, visual.blocks.18.mlp.gate_proj,
+        visual.blocks.18.mlp.up_proj, visual.blocks.18.mlp.down_proj, visual.blocks.19.attn.qkv,
+        visual.blocks.19.attn.proj, visual.blocks.19.mlp.gate_proj, visual.blocks.19.mlp.up_proj,
+        visual.blocks.19.mlp.down_proj, visual.blocks.20.attn.qkv, visual.blocks.20.attn.proj,
+        visual.blocks.20.mlp.gate_proj, visual.blocks.20.mlp.up_proj, visual.blocks.20.mlp.down_proj,
+        visual.blocks.21.attn.qkv, visual.blocks.21.attn.proj, visual.blocks.21.mlp.gate_proj,
+        visual.blocks.21.mlp.up_proj, visual.blocks.21.mlp.down_proj, visual.blocks.22.attn.qkv,
+        visual.blocks.22.attn.proj, visual.blocks.22.mlp.gate_proj, visual.blocks.22.mlp.up_proj,
+        visual.blocks.22.mlp.down_proj, visual.blocks.23.attn.qkv, visual.blocks.23.attn.proj,
+        visual.blocks.23.mlp.gate_proj, visual.blocks.23.mlp.up_proj, visual.blocks.23.mlp.down_proj,
+        visual.blocks.24.attn.qkv, visual.blocks.24.attn.proj, visual.blocks.24.mlp.gate_proj,
+        visual.blocks.24.mlp.up_proj, visual.blocks.24.mlp.down_proj, visual.blocks.25.attn.qkv,
+        visual.blocks.25.attn.proj, visual.blocks.25.mlp.gate_proj, visual.blocks.25.mlp.up_proj,
+        visual.blocks.25.mlp.down_proj, visual.blocks.26.attn.qkv, visual.blocks.26.attn.proj,
+        visual.blocks.26.mlp.gate_proj, visual.blocks.26.mlp.up_proj, visual.blocks.26.mlp.down_proj,
+        visual.blocks.27.attn.qkv, visual.blocks.27.attn.proj, visual.blocks.27.mlp.gate_proj,
+        visual.blocks.27.mlp.up_proj, visual.blocks.27.mlp.down_proj, visual.blocks.28.attn.qkv,
+        visual.blocks.28.attn.proj, visual.blocks.28.mlp.gate_proj, visual.blocks.28.mlp.up_proj,
+        visual.blocks.28.mlp.down_proj, visual.blocks.29.attn.qkv, visual.blocks.29.attn.proj,
+        visual.blocks.29.mlp.gate_proj, visual.blocks.29.mlp.up_proj, visual.blocks.29.mlp.down_proj,
+        visual.blocks.30.attn.qkv, visual.blocks.30.attn.proj, visual.blocks.30.mlp.gate_proj,
+        visual.blocks.30.mlp.up_proj, visual.blocks.30.mlp.down_proj, visual.blocks.31.attn.qkv,
+        visual.blocks.31.attn.proj, visual.blocks.31.mlp.gate_proj, visual.blocks.31.mlp.up_proj,
+        visual.blocks.31.mlp.down_proj]
+      mappings:
+      - smooth_layer: re:model\.layers\.\d+\.input_layernorm
+        balance_layers: ['re:model\.layers\.\d+\.self_attn\.q_proj', 're:model\.layers\.\d+\.self_attn\.k_proj',
+          're:model\.layers\.\d+\.self_attn\.v_proj']
+      - smooth_layer: re:model\.layers\.\d+\.post_attention_layernorm
+        balance_layers: ['re:model\.layers\.\d+\.mlp\.gate_proj', 're:model\.layers\.\d+\.mlp\.up_proj']
+      duo_scaling: true
+      n_grid: 20