Upload folder using huggingface_hub

README.md

@@ -0,0 +1,19 @@
+---
+tags:
+- vision
+- image-text-to-text
+- mlx
+---
+
+# mlx-community/llava-v1.6-34b-8bit
+This model was converted to MLX format from [`llava-hf/llava-v1.6-34b-hf`]() using mlx-vlm version **0.0.9**.
+Refer to the [original model card](https://huggingface.co/llava-hf/llava-v1.6-34b-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-v1.6-34b-8bit --max-tokens 100 --temp 0.0
+```

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image>": 64000
+}

config.json

@@ -0,0 +1,72 @@
+{
+    "architectures": [
+        "LlavaNextForConditionalGeneration"
+    ],
+    "ignore_index": -100,
+    "image_grid_pinpoints": [
+        [
+            336,
+            672
+        ],
+        [
+            672,
+            336
+        ],
+        [
+            672,
+            672
+        ],
+        [
+            1008,
+            336
+        ],
+        [
+            336,
+            1008
+        ]
+    ],
+    "image_token_index": 64000,
+    "model_type": "llava_next",
+    "projector_hidden_act": "gelu",
+    "quantization": {
+        "group_size": 64,
+        "bits": 8
+    },
+    "text_config": {
+        "_name_or_path": "NousResearch/Nous-Hermes-2-Yi-34B",
+        "architectures": [
+            "LlamaForCausalLM"
+        ],
+        "eos_token_id": 7,
+        "hidden_size": 7168,
+        "intermediate_size": 20480,
+        "max_position_embeddings": 4096,
+        "model_type": "llama",
+        "num_attention_heads": 56,
+        "num_hidden_layers": 60,
+        "num_key_value_heads": 8,
+        "pad_token_id": 0,
+        "rms_norm_eps": 1e-05,
+        "rope_theta": 5000000.0,
+        "torch_dtype": "bfloat16",
+        "use_cache": false,
+        "vocab_size": 64064
+    },
+    "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": 64064
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:046f1e757aa35f197066906ca8e4c06ad4319ccf0f33575df9ba9fc578422113
+size 5241283928

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:426eb0ec578ad818724e0fc8784133e42c0dd1e7c892174c926d9d406e674348
+size 5334653148

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc4dd60f97ab4e5ce5973054f684807182abf8474bcb6a4a7226c8e825bd112d
+size 5334653176

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0302b226a94911d8491e881f538f16d93dff8dd4c44758e89e0d09824fb21fe8
+size 5334653166

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b51e69ed50ff9e02a6dfe2cbcff7f2ba28e834936f5fd8114ef39dcc7ed31a6
+size 5334653136

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b079a2291bc14fb4a924ecb97c74fd0b0990f50794110e6575ad689526ad053d
+size 5334653184

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98b4f117e8d2a4224deeb3d7c195bb2a7b1bab88989d353d2d2f701e4724fff5
+size 5011516184

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 +1,33 @@
+{
+  "additional_special_tokens": [
+    "<image>"
+  ],
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "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 sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
+size 1033105

tokenizer_config.json

@@ -0,0 +1,73 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "7": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64000": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<image>"
+  ],
+  "bos_token": "<|startoftext|>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<unk>",
+  "processor_class": "LlavaNextProcessor",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}