Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tekken.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,267 @@
+{
+  "architectures": [
+    "Mistral3ForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "image_token_index": 10,
+  "model_type": "mistral3",
+  "multimodal_projector_bias": false,
+  "projector_hidden_act": "gelu",
+  "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": 32,
+          "num_bits": 8,
+          "observer": "mse",
+          "observer_kwargs": {},
+          "strategy": "group",
+          "symmetric": true,
+          "type": "int"
+        }
+      }
+    },
+    "format": "pack-quantized",
+    "global_compression_ratio": null,
+    "ignore": [
+      "model.vision_tower.transformer.layers.0.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.0.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.0.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.0.attention.k_proj",
+      "model.vision_tower.transformer.layers.0.attention.v_proj",
+      "model.vision_tower.transformer.layers.0.attention.q_proj",
+      "model.vision_tower.transformer.layers.0.attention.o_proj",
+      "model.vision_tower.transformer.layers.1.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.1.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.1.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.1.attention.k_proj",
+      "model.vision_tower.transformer.layers.1.attention.v_proj",
+      "model.vision_tower.transformer.layers.1.attention.q_proj",
+      "model.vision_tower.transformer.layers.1.attention.o_proj",
+      "model.vision_tower.transformer.layers.2.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.2.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.2.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.2.attention.k_proj",
+      "model.vision_tower.transformer.layers.2.attention.v_proj",
+      "model.vision_tower.transformer.layers.2.attention.q_proj",
+      "model.vision_tower.transformer.layers.2.attention.o_proj",
+      "model.vision_tower.transformer.layers.3.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.3.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.3.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.3.attention.k_proj",
+      "model.vision_tower.transformer.layers.3.attention.v_proj",
+      "model.vision_tower.transformer.layers.3.attention.q_proj",
+      "model.vision_tower.transformer.layers.3.attention.o_proj",
+      "model.vision_tower.transformer.layers.4.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.4.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.4.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.4.attention.k_proj",
+      "model.vision_tower.transformer.layers.4.attention.v_proj",
+      "model.vision_tower.transformer.layers.4.attention.q_proj",
+      "model.vision_tower.transformer.layers.4.attention.o_proj",
+      "model.vision_tower.transformer.layers.5.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.5.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.5.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.5.attention.k_proj",
+      "model.vision_tower.transformer.layers.5.attention.v_proj",
+      "model.vision_tower.transformer.layers.5.attention.q_proj",
+      "model.vision_tower.transformer.layers.5.attention.o_proj",
+      "model.vision_tower.transformer.layers.6.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.6.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.6.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.6.attention.k_proj",
+      "model.vision_tower.transformer.layers.6.attention.v_proj",
+      "model.vision_tower.transformer.layers.6.attention.q_proj",
+      "model.vision_tower.transformer.layers.6.attention.o_proj",
+      "model.vision_tower.transformer.layers.7.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.7.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.7.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.7.attention.k_proj",
+      "model.vision_tower.transformer.layers.7.attention.v_proj",
+      "model.vision_tower.transformer.layers.7.attention.q_proj",
+      "model.vision_tower.transformer.layers.7.attention.o_proj",
+      "model.vision_tower.transformer.layers.8.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.8.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.8.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.8.attention.k_proj",
+      "model.vision_tower.transformer.layers.8.attention.v_proj",
+      "model.vision_tower.transformer.layers.8.attention.q_proj",
+      "model.vision_tower.transformer.layers.8.attention.o_proj",
+      "model.vision_tower.transformer.layers.9.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.9.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.9.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.9.attention.k_proj",
+      "model.vision_tower.transformer.layers.9.attention.v_proj",
+      "model.vision_tower.transformer.layers.9.attention.q_proj",
+      "model.vision_tower.transformer.layers.9.attention.o_proj",
+      "model.vision_tower.transformer.layers.10.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.10.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.10.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.10.attention.k_proj",
+      "model.vision_tower.transformer.layers.10.attention.v_proj",
+      "model.vision_tower.transformer.layers.10.attention.q_proj",
+      "model.vision_tower.transformer.layers.10.attention.o_proj",
+      "model.vision_tower.transformer.layers.11.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.11.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.11.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.11.attention.k_proj",
+      "model.vision_tower.transformer.layers.11.attention.v_proj",
+      "model.vision_tower.transformer.layers.11.attention.q_proj",
+      "model.vision_tower.transformer.layers.11.attention.o_proj",
+      "model.vision_tower.transformer.layers.12.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.12.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.12.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.12.attention.k_proj",
+      "model.vision_tower.transformer.layers.12.attention.v_proj",
+      "model.vision_tower.transformer.layers.12.attention.q_proj",
+      "model.vision_tower.transformer.layers.12.attention.o_proj",
+      "model.vision_tower.transformer.layers.13.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.13.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.13.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.13.attention.k_proj",
+      "model.vision_tower.transformer.layers.13.attention.v_proj",
+      "model.vision_tower.transformer.layers.13.attention.q_proj",
+      "model.vision_tower.transformer.layers.13.attention.o_proj",
+      "model.vision_tower.transformer.layers.14.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.14.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.14.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.14.attention.k_proj",
+      "model.vision_tower.transformer.layers.14.attention.v_proj",
+      "model.vision_tower.transformer.layers.14.attention.q_proj",
+      "model.vision_tower.transformer.layers.14.attention.o_proj",
+      "model.vision_tower.transformer.layers.15.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.15.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.15.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.15.attention.k_proj",
+      "model.vision_tower.transformer.layers.15.attention.v_proj",
+      "model.vision_tower.transformer.layers.15.attention.q_proj",
+      "model.vision_tower.transformer.layers.15.attention.o_proj",
+      "model.vision_tower.transformer.layers.16.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.16.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.16.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.16.attention.k_proj",
+      "model.vision_tower.transformer.layers.16.attention.v_proj",
+      "model.vision_tower.transformer.layers.16.attention.q_proj",
+      "model.vision_tower.transformer.layers.16.attention.o_proj",
+      "model.vision_tower.transformer.layers.17.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.17.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.17.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.17.attention.k_proj",
+      "model.vision_tower.transformer.layers.17.attention.v_proj",
+      "model.vision_tower.transformer.layers.17.attention.q_proj",
+      "model.vision_tower.transformer.layers.17.attention.o_proj",
+      "model.vision_tower.transformer.layers.18.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.18.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.18.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.18.attention.k_proj",
+      "model.vision_tower.transformer.layers.18.attention.v_proj",
+      "model.vision_tower.transformer.layers.18.attention.q_proj",
+      "model.vision_tower.transformer.layers.18.attention.o_proj",
+      "model.vision_tower.transformer.layers.19.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.19.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.19.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.19.attention.k_proj",
+      "model.vision_tower.transformer.layers.19.attention.v_proj",
+      "model.vision_tower.transformer.layers.19.attention.q_proj",
+      "model.vision_tower.transformer.layers.19.attention.o_proj",
+      "model.vision_tower.transformer.layers.20.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.20.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.20.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.20.attention.k_proj",
+      "model.vision_tower.transformer.layers.20.attention.v_proj",
+      "model.vision_tower.transformer.layers.20.attention.q_proj",
+      "model.vision_tower.transformer.layers.20.attention.o_proj",
+      "model.vision_tower.transformer.layers.21.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.21.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.21.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.21.attention.k_proj",
+      "model.vision_tower.transformer.layers.21.attention.v_proj",
+      "model.vision_tower.transformer.layers.21.attention.q_proj",
+      "model.vision_tower.transformer.layers.21.attention.o_proj",
+      "model.vision_tower.transformer.layers.22.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.22.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.22.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.22.attention.k_proj",
+      "model.vision_tower.transformer.layers.22.attention.v_proj",
+      "model.vision_tower.transformer.layers.22.attention.q_proj",
+      "model.vision_tower.transformer.layers.22.attention.o_proj",
+      "model.vision_tower.transformer.layers.23.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.23.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.23.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.23.attention.k_proj",
+      "model.vision_tower.transformer.layers.23.attention.v_proj",
+      "model.vision_tower.transformer.layers.23.attention.q_proj",
+      "model.vision_tower.transformer.layers.23.attention.o_proj",
+      "model.multi_modal_projector.patch_merger.merging_layer",
+      "model.multi_modal_projector.linear_1",
+      "model.multi_modal_projector.linear_2",
+      "lm_head"
+    ],
+    "kv_cache_scheme": null,
+    "quant_method": "compressed-tensors",
+    "quantization_status": "compressed",
+    "sparsity_config": {},
+    "transform_config": {},
+    "version": "0.12.3.a20251114"
+  },
+  "spatial_merge_size": 2,
+  "text_config": {
+    "attention_dropout": 0.0,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 14336,
+    "max_position_embeddings": 262144,
+    "model_type": "ministral3",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 34,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_parameters": {
+      "beta_fast": 32.0,
+      "beta_slow": 1.0,
+      "factor": 16.0,
+      "llama_4_scaling_beta": 0.1,
+      "mscale": 1.0,
+      "mscale_all_dim": 1.0,
+      "original_max_position_embeddings": 16384,
+      "rope_theta": 1000000.0,
+      "rope_type": "yarn",
+      "type": "yarn"
+    },
+    "sliding_window": null,
+    "use_cache": true,
+    "vocab_size": 131072
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.0.0.dev0",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "head_dim": 64,
+    "hidden_act": "silu",
+    "hidden_size": 1024,
+    "image_size": 1540,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "model_type": "pixtral",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "rope_parameters": {
+      "rope_theta": 10000.0,
+      "rope_type": "default"
+    }
+  },
+  "vision_feature_layer": -1
+}

consolidated.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67fd1dc49a55026d0a112f2789302e36e9451b2f22e7afb83c372eeb3163226e
+size 10884111496

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 262144,
+  "pad_token_id": 11,
+  "transformers_version": "5.0.0.dev0"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fccbe9df7f2ec99e86eb116264b087fc830be747836be418277da637f8653439
+size 4990939968

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:624893221d76af2219996e94924047444bac1684825d0c81f066d59c959f8acf
+size 4996096976

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:089e3c33f5a5a4cc514f810d473046bc385968d30bff420686fecdb0e6383df8
+size 897091824

params.json

@@ -0,0 +1,57 @@
+{
+  "head_dim": 128,
+  "vocab_size": 131072,
+  "sliding_window": null,
+  "vision_encoder": {
+    "hidden_size": 1024,
+    "intermediate_size": 4096,
+    "num_hidden_layers": 24,
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "patch_size": 14,
+    "image_size": 1540,
+    "attention_dropout": 0.0,
+    "hidden_act": "silu",
+    "head_dim": 64,
+    "initializer_range": 0.02,
+    "rope_parameters": {
+      "rope_theta": 10000.0,
+      "rope_type": "default"
+    },
+    "return_dict": true,
+    "output_hidden_states": false,
+    "dtype": "float16",
+    "tie_word_embeddings": true,
+    "chunk_size_feed_forward": 0,
+    "is_encoder_decoder": false,
+    "is_decoder": false,
+    "cross_attention_hidden_size": null,
+    "add_cross_attention": false,
+    "tie_encoder_decoder": false,
+    "architectures": null,
+    "finetuning_task": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "task_specific_params": null,
+    "problem_type": null,
+    "tokenizer_class": null,
+    "prefix": null,
+    "bos_token_id": null,
+    "pad_token_id": null,
+    "eos_token_id": null,
+    "sep_token_id": null,
+    "decoder_start_token_id": null,
+    "_pre_quantization_dtype": "torch.float16",
+    "output_attentions": false,
+    "adapter_bias": false,
+    "spatial_merge_size": 2,
+    "image_token_id": 10,
+    "max_image_size": 1540
+  }
+}

recipe.yaml

@@ -0,0 +1,37 @@
+default_stage:
+  default_modifiers:
+    AWQModifier:
+      config_groups:
+        group_0:
+          targets: [Linear]
+          weights:
+            num_bits: 8
+            type: int
+            symmetric: true
+            group_size: 32
+            strategy: group
+            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: ['re:.*embed_tokens', 're:.*input_layernorm', 're:.*post_attention_layernorm',
+        're:.*norm', 're:.*lm_head', 're:.*multi_modal_projector.*', 're:.*vision_tower.*']
+      mappings:
+      - smooth_layer: re:.*input_layernorm$
+        balance_layers: ['re:.*q_proj$', 're:.*k_proj$', 're:.*v_proj$']
+      - smooth_layer: re:.*v_proj$
+        balance_layers: ['re:.*o_proj$']
+      - smooth_layer: re:.*post_attention_layernorm$
+        balance_layers: ['re:.*gate_proj$', 're:.*up_proj$']
+      - smooth_layer: re:.*up_proj$
+        balance_layers: ['re:.*down_proj$']
+      offload_device: !!python/object/apply:torch.device [cpu]
+      duo_scaling: true
+      n_grid: 20

tekken.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e29d19ea32eb7e26e6c0572d57cb7f9eca0f4420e0e0fe6ae1cf3be94da1c0d6
+size 16753777