Upload model trained with Unsloth

Upload model trained with Unsloth 2x faster

README.md

@@ -6,6 +6,7 @@ tags:
 - unsloth
 - mistral3
 - trl
+- sft
 license: apache-2.0
 language:
 - en

config.json

@@ -0,0 +1,161 @@
+{
+  "architectures": [
+    "Mistral3ForConditionalGeneration"
+  ],
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "image_token_index": 10,
+  "model_type": "mistral3",
+  "multimodal_projector_bias": false,
+  "pad_token_id": 11,
+  "projector_hidden_act": "gelu",
+  "quantization_config": {
+    "include_input_output_embeddings": true,
+    "modules_to_not_convert": [],
+    "quant_method": "torchao",
+    "quant_type": {
+      "default": {
+        "_data": {
+          "module_fqn_to_config": {
+            "_default": {
+              "_data": {
+                "act_mapping_type": {
+                  "_data": "ASYMMETRIC",
+                  "_type": "MappingType"
+                },
+                "intx_choose_qparams_algorithm": {
+                  "_data": "AFFINE",
+                  "_type": "IntxChooseQParamsAlgorithm"
+                },
+                "intx_packing_format": {
+                  "_data": "UNPACKED_TO_INT8",
+                  "_type": "IntxPackingFormat"
+                },
+                "layout": {
+                  "_data": {},
+                  "_type": "QDQLayout",
+                  "_version": 1
+                },
+                "weight_dtype": {
+                  "_data": "int4",
+                  "_type": "torch.dtype"
+                },
+                "weight_granularity": {
+                  "_data": {
+                    "group_size": 32
+                  },
+                  "_type": "PerGroup",
+                  "_version": 1
+                },
+                "weight_mapping_type": {
+                  "_data": "SYMMETRIC",
+                  "_type": "MappingType"
+                },
+                "weight_scale_dtype": null
+              },
+              "_type": "Int8DynamicActivationIntxWeightConfig",
+              "_version": 2
+            },
+            "model.language_model.embed_tokens": {
+              "_data": {
+                "granularity": {
+                  "_data": {
+                    "axis": 0
+                  },
+                  "_type": "PerAxis",
+                  "_version": 1
+                },
+                "intx_choose_qparams_algorithm": {
+                  "_data": "AFFINE",
+                  "_type": "IntxChooseQParamsAlgorithm"
+                },
+                "intx_packing_format": {
+                  "_data": "UNPACKED_TO_INT8",
+                  "_type": "IntxPackingFormat"
+                },
+                "layout": {
+                  "_data": {},
+                  "_type": "QDQLayout",
+                  "_version": 1
+                },
+                "mapping_type": {
+                  "_data": "SYMMETRIC",
+                  "_type": "MappingType"
+                },
+                "scale_dtype": null,
+                "weight_dtype": {
+                  "_data": "int8",
+                  "_type": "torch.dtype"
+                }
+              },
+              "_type": "IntxWeightOnlyConfig",
+              "_version": 2
+            }
+          }
+        },
+        "_type": "ModuleFqnToConfig",
+        "_version": 1
+      }
+    },
+    "quant_type_kwargs": {},
+    "untie_embedding_weights": false
+  },
+  "spatial_merge_size": 2,
+  "text_config": {
+    "attention_dropout": 0.0,
+    "dtype": "bfloat16",
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 3072,
+    "initializer_range": 0.02,
+    "intermediate_size": 9216,
+    "max_position_embeddings": 262144,
+    "model_type": "ministral3",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 26,
+    "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,
+    "tie_word_embeddings": true,
+    "use_cache": true,
+    "vocab_size": 131072
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.0.0.dev0",
+  "unsloth_fixed": true,
+  "unsloth_version": "2025.11.6",
+  "use_cache": false,
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "dtype": "bfloat16",
+    "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
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "max_length": 262144,
+  "pad_token_id": 11,
+  "transformers_version": "5.0.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c722db6ea52767d6cf86bd06eda3f195409245b8f23b992fe8d377d85413a29
+size 4614146316