Upload folder using huggingface_hub

README.md

@@ -0,0 +1,27 @@
+---
+base_model: llava-hf/llava-1.5-7b-hf
+language:
+- en
+library_name: transformers
+pipeline_tag: image-text-to-text
+license: llama2
+tags:
+- multimodal
+- llava
+- vision
+- unsloth
+- mlx
+---
+
+# shashikanth-a/llava-1.5-7b-hf-4bit
+This model was converted to MLX format from [`unsloth/llava-1.5-7b-hf`]() using mlx-vlm version **0.1.3**.
+Refer to the [original model card](https://huggingface.co/unsloth/llava-1.5-7b-hf) for more details on the model.
+## Use with mlx
+
+```bash
+pip install -U mlx-vlm
+```
+
+```bash
+python -m mlx_vlm.generate --model shashikanth-a/llava-1.5-7b-hf-4bit --max-tokens 100 --temp 0.0
+```

added_tokens.json

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

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% for message in messages %}{% if message['role'] != 'system' %}{{ message['role'].upper() + ': '}}{% endif %}{# Render all images first #}{% for content in message['content'] | selectattr('type', 'equalto', 'image') %}{{ '<image>\n' }}{% endfor %}{# Render all text next #}{% if message['role'] != 'assistant' %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{{ content['text'] + ' '}}{% endfor %}{% else %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{% generation %}{{ content['text'] + ' '}}{% endgeneration %}{% endfor %}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'ASSISTANT:' }}{% endif %}"
+}

config.json

@@ -0,0 +1,184 @@
+{
+    "architectures": [
+        "LlavaForConditionalGeneration"
+    ],
+    "ignore_index": -100,
+    "image_seq_length": 576,
+    "image_token_index": 32000,
+    "model_type": "llava",
+    "pad_token_id": 32001,
+    "projector_hidden_act": "gelu",
+    "quantization": {
+        "group_size": 64,
+        "bits": 4
+    },
+    "text_config": {
+        "_attn_implementation_autoset": false,
+        "_name_or_path": "lmsys/vicuna-7b-v1.5",
+        "add_cross_attention": false,
+        "architectures": [
+            "LlamaForCausalLM"
+        ],
+        "attention_bias": false,
+        "attention_dropout": 0.0,
+        "bad_words_ids": null,
+        "begin_suppress_tokens": null,
+        "bos_token_id": 1,
+        "chunk_size_feed_forward": 0,
+        "cross_attention_hidden_size": null,
+        "decoder_start_token_id": null,
+        "diversity_penalty": 0.0,
+        "do_sample": false,
+        "early_stopping": false,
+        "encoder_no_repeat_ngram_size": 0,
+        "eos_token_id": 2,
+        "exponential_decay_length_penalty": null,
+        "finetuning_task": null,
+        "forced_bos_token_id": null,
+        "forced_eos_token_id": null,
+        "head_dim": 128,
+        "hidden_act": "silu",
+        "hidden_size": 4096,
+        "id2label": {
+            "0": "LABEL_0",
+            "1": "LABEL_1"
+        },
+        "initializer_range": 0.02,
+        "intermediate_size": 11008,
+        "is_decoder": false,
+        "is_encoder_decoder": false,
+        "label2id": {
+            "LABEL_0": 0,
+            "LABEL_1": 1
+        },
+        "length_penalty": 1.0,
+        "max_length": 20,
+        "max_position_embeddings": 4096,
+        "min_length": 0,
+        "mlp_bias": false,
+        "model_type": "llama",
+        "no_repeat_ngram_size": 0,
+        "num_attention_heads": 32,
+        "num_beam_groups": 1,
+        "num_beams": 1,
+        "num_hidden_layers": 32,
+        "num_key_value_heads": 32,
+        "num_return_sequences": 1,
+        "output_attentions": false,
+        "output_hidden_states": false,
+        "output_scores": false,
+        "pad_token_id": 32001,
+        "prefix": null,
+        "pretraining_tp": 1,
+        "problem_type": null,
+        "pruned_heads": {},
+        "remove_invalid_values": false,
+        "repetition_penalty": 1.0,
+        "return_dict": true,
+        "return_dict_in_generate": false,
+        "rms_norm_eps": 1e-05,
+        "rope_scaling": null,
+        "rope_theta": 10000.0,
+        "sep_token_id": null,
+        "suppress_tokens": null,
+        "task_specific_params": null,
+        "temperature": 1.0,
+        "tf_legacy_loss": false,
+        "tie_encoder_decoder": false,
+        "tie_word_embeddings": false,
+        "tokenizer_class": null,
+        "top_k": 50,
+        "top_p": 1.0,
+        "torch_dtype": "float16",
+        "torchscript": false,
+        "typical_p": 1.0,
+        "use_bfloat16": false,
+        "use_cache": true,
+        "vocab_size": 32064
+    },
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.46.3",
+    "unsloth_fixed": true,
+    "vision_config": {
+        "_attn_implementation_autoset": false,
+        "_name_or_path": "",
+        "add_cross_attention": false,
+        "architectures": null,
+        "attention_dropout": 0.0,
+        "bad_words_ids": null,
+        "begin_suppress_tokens": null,
+        "bos_token_id": null,
+        "chunk_size_feed_forward": 0,
+        "cross_attention_hidden_size": null,
+        "decoder_start_token_id": null,
+        "diversity_penalty": 0.0,
+        "do_sample": false,
+        "early_stopping": false,
+        "encoder_no_repeat_ngram_size": 0,
+        "eos_token_id": null,
+        "exponential_decay_length_penalty": null,
+        "finetuning_task": null,
+        "forced_bos_token_id": null,
+        "forced_eos_token_id": null,
+        "hidden_act": "quick_gelu",
+        "hidden_size": 1024,
+        "id2label": {
+            "0": "LABEL_0",
+            "1": "LABEL_1"
+        },
+        "image_size": 336,
+        "initializer_factor": 1.0,
+        "initializer_range": 0.02,
+        "intermediate_size": 4096,
+        "is_decoder": false,
+        "is_encoder_decoder": false,
+        "label2id": {
+            "LABEL_0": 0,
+            "LABEL_1": 1
+        },
+        "layer_norm_eps": 1e-05,
+        "length_penalty": 1.0,
+        "max_length": 20,
+        "min_length": 0,
+        "model_type": "clip_vision_model",
+        "no_repeat_ngram_size": 0,
+        "num_attention_heads": 16,
+        "num_beam_groups": 1,
+        "num_beams": 1,
+        "num_channels": 3,
+        "num_hidden_layers": 24,
+        "num_return_sequences": 1,
+        "output_attentions": false,
+        "output_hidden_states": false,
+        "output_scores": false,
+        "pad_token_id": 32001,
+        "patch_size": 14,
+        "prefix": null,
+        "problem_type": null,
+        "projection_dim": 768,
+        "pruned_heads": {},
+        "remove_invalid_values": false,
+        "repetition_penalty": 1.0,
+        "return_dict": true,
+        "return_dict_in_generate": false,
+        "sep_token_id": null,
+        "suppress_tokens": null,
+        "task_specific_params": null,
+        "temperature": 1.0,
+        "tf_legacy_loss": false,
+        "tie_encoder_decoder": false,
+        "tie_word_embeddings": true,
+        "tokenizer_class": null,
+        "top_k": 50,
+        "top_p": 1.0,
+        "torch_dtype": null,
+        "torchscript": false,
+        "typical_p": 1.0,
+        "use_bfloat16": false,
+        "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:bdf0f404f419efb874d22b4cf233dc87e9b49602a8318ffc9bc65296e29f4aa9
+size 3975094479

preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "crop_size": {
+    "height": 336,
+    "width": 336
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "LlavaProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 336
+  }
+}

processor_config.json

@@ -0,0 +1,6 @@
+{
+  "image_token": "<image>",
+  "patch_size": 14,
+  "processor_class": "LlavaProcessor",
+  "vision_feature_select_strategy": "default"
+}

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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,61 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "processor_class": "LlavaProcessor",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}