Upload folder using huggingface_hub

README.md

@@ -0,0 +1,20 @@
+---
+license: apache-2.0
+tags:
+- vision
+- image-text-to-text
+- mlx
+---
+
+# mlx-community/llava-v1.6-mistral-7b-4bit
+This model was converted to MLX format from [`llava-hf/llava-v1.6-mistral-7b-hf`]() using mlx-vlm version **0.0.9**.
+Refer to the [original model card](https://huggingface.co/llava-hf/llava-v1.6-mistral-7b-hf) for more details on the model.
+## Use with mlx
+
+```bash
+pip install -U mlx-vlm
+```
+
+```bash
+python -m mlx_vlm.generate --model mlx-community/llava-v1.6-mistral-7b-4bit --max-tokens 100 --temp 0.0
+```

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<image>": 32000,
+  "<pad>": 32001
+}

config.json

@@ -0,0 +1,67 @@
+{
+    "architectures": [
+        "LlavaNextForConditionalGeneration"
+    ],
+    "ignore_index": -100,
+    "image_grid_pinpoints": [
+        [
+            336,
+            672
+        ],
+        [
+            672,
+            336
+        ],
+        [
+            672,
+            672
+        ],
+        [
+            1008,
+            336
+        ],
+        [
+            336,
+            1008
+        ]
+    ],
+    "image_token_index": 32000,
+    "model_type": "llava_next",
+    "projector_hidden_act": "gelu",
+    "quantization": {
+        "group_size": 64,
+        "bits": 4
+    },
+    "text_config": {
+        "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+        "architectures": [
+            "MistralForCausalLM"
+        ],
+        "intermediate_size": 14336,
+        "max_position_embeddings": 32768,
+        "model_type": "mistral",
+        "num_key_value_heads": 8,
+        "rms_norm_eps": 1e-05,
+        "rope_theta": 1000000.0,
+        "sliding_window": null,
+        "torch_dtype": "bfloat16",
+        "vocab_size": 32064
+    },
+    "torch_dtype": "float16",
+    "transformers_version": "4.39.0.dev0",
+    "use_image_newline_parameter": true,
+    "vision_config": {
+        "hidden_size": 1024,
+        "image_size": 336,
+        "intermediate_size": 4096,
+        "model_type": "clip_vision_model",
+        "num_attention_heads": 16,
+        "num_hidden_layers": 24,
+        "patch_size": 14,
+        "projection_dim": 768,
+        "vocab_size": 32000
+    },
+    "vision_feature_layer": -2,
+    "vision_feature_select_strategy": "default",
+    "vocab_size": 32064
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c067c64c4cc2ab04af36a9c0a2cb528efc89ed0828a4a5df1332522ef5d3f62
+size 4258218323

preprocessor_config.json

@@ -0,0 +1,52 @@
+{
+  "aspect_ratio_setting": "anyres",
+  "crop_size": {
+    "height": 336,
+    "width": 336
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_grid_pinpoints": [
+    [
+      336,
+      672
+    ],
+    [
+      672,
+      336
+    ],
+    [
+      672,
+      672
+    ],
+    [
+      1008,
+      336
+    ],
+    [
+      336,
+      1008
+    ]
+  ],
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "LlavaNextImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "LlavaNextProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 336
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,63 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "max_length": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
+  "processor_class": "LlavaNextProcessor",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}