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

SYSTEM_PROMPT.txt

@@ -0,0 +1,3 @@
+First draft your thinking process (inner monologue) until you arrive at a response. Format your response using Markdown, and use LaTeX for any mathematical equations. Write both your thoughts and the response in the same language as the input.
+
+Your thinking process must follow the template below:[THINK]Your thoughts or/and draft, like working through an exercise on scratch paper. Be as casual and as long as you want until you are confident to generate the response. Use the same language as the input.[/THINK]Here, provide a self-contained response.

config.json

@@ -0,0 +1,61 @@
+{
+  "architectures": [
+    "Mistral3ForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "image_token_index": 10,
+  "model_type": "mistral3",
+  "multimodal_projector_bias": false,
+  "projector_hidden_act": "gelu",
+  "quantization_config": {
+    "autoround_version": "0.9.0",
+    "batch_size": 1,
+    "bits": 4,
+    "block_name_to_quantize": "model.language_model.layers",
+    "data_type": "int",
+    "dataset": "liuhaotian/llava_conv_58k",
+    "gradient_accumulate_steps": 8,
+    "group_size": 128,
+    "packing_format": "auto_round:auto_gptq",
+    "quant_method": "auto-round",
+    "scale_dtype": "None",
+    "seqlen": 512,
+    "sym": true
+  },
+  "spatial_merge_size": 2,
+  "text_config": {
+    "attention_dropout": 0.0,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 32768,
+    "max_position_embeddings": 131072,
+    "model_type": "mistral",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 40,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000000.0,
+    "sliding_window": null,
+    "use_cache": true,
+    "vocab_size": 131072
+  },
+  "transformers_version": "4.57.1",
+  "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_theta": 10000.0
+  },
+  "vision_feature_layer": -1
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_new_tokens": 131072,
+  "pad_token_id": 11,
+  "temperature": 0.7,
+  "top_p": 0.95,
+  "transformers_version": "4.57.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e0dd486b800237cb5594befaf1f12b22c70b7dff93def699b96bb124e596bc9
+size 4933281064

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6201b9c257a0f1b385437bb082f4dae95813a686a6a75db6e907ff4cdee71638
+size 4995921624

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61ee99fa3b823359bce563a6a32baf17d8c57097d30e8f8843889e6218028b80
+size 3840950744

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:487158e25eb90313f1f57a1894a260addf66dd6526984393fe8150abbe3c7a22
+size 1342177424

quantization_config.json

@@ -0,0 +1,15 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "sym": true,
+  "data_type": "int",
+  "seqlen": 512,
+  "batch_size": 1,
+  "scale_dtype": "None",
+  "gradient_accumulate_steps": 8,
+  "dataset": "liuhaotian/llava_conv_58k",
+  "autoround_version": "0.9.0",
+  "block_name_to_quantize": "model.language_model.layers",
+  "quant_method": "auto-round",
+  "packing_format": "auto_round:auto_gptq"
+}

tekken.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05e051a32ae9d6333459da0083d36507116334fc85378321cfb32dfff7187531
+size 19399765