Upload DFK Ministral-3-8B fine-tuned merged model (fp16)

.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

chat_template.jinja

@@ -0,0 +1,3 @@
+{{ bos_token }}{% set ns = namespace(system='', injected=false) %}{% for message in messages %}{% if message['role'] == 'system' %}{% set ns.system = message['content'] %}{% elif message['role'] == 'user' %}{% if ns.system and not ns.injected %}[INST] {{ ns.system }}
+
+{{ message['content'] }} [/INST] {% set ns.injected = true %}{% else %}[INST] {{ message['content'] }} [/INST] {% endif %}{% elif message['role'] == 'assistant' %}{{ message['content'] }}{{ eos_token }}{% endif %}{% endfor %}

config.json

@@ -0,0 +1,67 @@
+{
+  "architectures": [
+    "Mistral3ForConditionalGeneration"
+  ],
+  "dtype": "float16",
+  "image_token_index": 10,
+  "model_type": "mistral3",
+  "multimodal_projector_bias": false,
+  "projector_hidden_act": "gelu",
+  "spatial_merge_size": 2,
+  "text_config": {
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "dtype": "float16",
+    "eos_token_id": 2,
+    "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,
+    "pad_token_id": 11,
+    "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": false,
+    "use_cache": true,
+    "vocab_size": 131072
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.8.1",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "dtype": "float16",
+    "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 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 262144,
+  "pad_token_id": 11,
+  "transformers_version": "5.8.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d0f91ad4b7e3d4fb2748ff3ca6487687b633d288501762ce213a1e1428a2b6a
+size 17836123376

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:577575622324b2e099e2648be26bdeb5e5815ffe66d7004e9e3ddbf421db6bf1
+size 17078110

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "is_local": true,
+  "legacy": true,
+  "local_files_only": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "processor_class": "PixtralProcessor",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}