Upload folder using huggingface_hub

README.md

@@ -7,15 +7,17 @@ tags:
 - multimodal
 - qwen
 - mlx
-pipeline_tag: image-text-to-text
 ---
 
 # mlx-community/nanoLLaVA
+This model was converted to MLX format from [`qnguyen3/nanoLLaVA`]() using mlx-vllm version **0.0.0**.
+Refer to the [original model card](https://huggingface.co/qnguyen3/nanoLLaVA) for more details on the model.
+## Use with mlx
 
-Thsi project is a WIP and will annouce soon follow me on X for updates [Prince Canuma](https://twitter.com/Prince_Canuma).
-
-This model was converted to MLX format from [`qnguyen3/nanoLLaVA`]() using mlx-vllm (WIP) version **0.0.0**.
-
-Model added by [Prince Canuma](https://twitter.com/Prince_Canuma).
+```bash
+pip install -U mlx-vlm
+```
 
-Refer to the [original model card](https://huggingface.co/qnguyen3/nanoLLaVA) for more details on the model.
+```bash
+python -m mlx_vlm.generate --model mlx-community/nanoLLaVA --max-tokens 100 --temp 0.0
+```

config.json

@@ -29,88 +29,6 @@
     "rms_norm_eps": 1e-06,
     "rope_theta": 1000000.0,
     "sliding_window": 4096,
-    "text_config": {
-        "vocab_size": 151936,
-        "max_position_embeddings": 32768,
-        "hidden_size": 1024,
-        "intermediate_size": 2816,
-        "num_hidden_layers": 24,
-        "num_attention_heads": 16,
-        "use_sliding_window": false,
-        "sliding_window": 4096,
-        "max_window_layers": 21,
-        "num_key_value_heads": 16,
-        "hidden_act": "silu",
-        "initializer_range": 0.02,
-        "rms_norm_eps": 1e-06,
-        "use_cache": false,
-        "rope_theta": 1000000.0,
-        "attention_dropout": 0.0,
-        "return_dict": true,
-        "output_hidden_states": false,
-        "output_attentions": false,
-        "torchscript": false,
-        "torch_dtype": "bfloat16",
-        "use_bfloat16": false,
-        "tf_legacy_loss": false,
-        "pruned_heads": {},
-        "tie_word_embeddings": false,
-        "chunk_size_feed_forward": 0,
-        "is_encoder_decoder": false,
-        "is_decoder": false,
-        "cross_attention_hidden_size": null,
-        "add_cross_attention": false,
-        "tie_encoder_decoder": false,
-        "max_length": 20,
-        "min_length": 0,
-        "do_sample": false,
-        "early_stopping": false,
-        "num_beams": 1,
-        "num_beam_groups": 1,
-        "diversity_penalty": 0.0,
-        "temperature": 1.0,
-        "top_k": 50,
-        "top_p": 1.0,
-        "typical_p": 1.0,
-        "repetition_penalty": 1.0,
-        "length_penalty": 1.0,
-        "no_repeat_ngram_size": 0,
-        "encoder_no_repeat_ngram_size": 0,
-        "bad_words_ids": null,
-        "num_return_sequences": 1,
-        "output_scores": false,
-        "return_dict_in_generate": false,
-        "forced_bos_token_id": null,
-        "forced_eos_token_id": null,
-        "remove_invalid_values": false,
-        "exponential_decay_length_penalty": null,
-        "suppress_tokens": null,
-        "begin_suppress_tokens": null,
-        "architectures": [
-            "Qwen2ForCausalLM"
-        ],
-        "finetuning_task": null,
-        "id2label": {
-            "0": "LABEL_0",
-            "1": "LABEL_1"
-        },
-        "label2id": {
-            "LABEL_0": 0,
-            "LABEL_1": 1
-        },
-        "tokenizer_class": null,
-        "prefix": null,
-        "bos_token_id": null,
-        "pad_token_id": null,
-        "eos_token_id": 151645,
-        "sep_token_id": null,
-        "decoder_start_token_id": null,
-        "task_specific_params": null,
-        "problem_type": null,
-        "_name_or_path": "vilm/Quyen-SE-v0.1",
-        "transformers_version": "4.39.3",
-        "model_type": "qwen2"
-    },
     "tie_word_embeddings": false,
     "tokenizer_model_max_length": 4096,
     "tokenizer_padding_side": "right",
@@ -120,78 +38,5 @@
     "use_cache": false,
     "use_mm_proj": true,
     "use_sliding_window": false,
-    "vision_config": {
-        "return_dict": true,
-        "output_hidden_states": false,
-        "output_attentions": false,
-        "torchscript": false,
-        "torch_dtype": null,
-        "use_bfloat16": false,
-        "tf_legacy_loss": false,
-        "pruned_heads": {},
-        "tie_word_embeddings": true,
-        "chunk_size_feed_forward": 0,
-        "is_encoder_decoder": false,
-        "is_decoder": false,
-        "cross_attention_hidden_size": null,
-        "add_cross_attention": false,
-        "tie_encoder_decoder": false,
-        "max_length": 20,
-        "min_length": 0,
-        "do_sample": false,
-        "early_stopping": false,
-        "num_beams": 1,
-        "num_beam_groups": 1,
-        "diversity_penalty": 0.0,
-        "temperature": 1.0,
-        "top_k": 50,
-        "top_p": 1.0,
-        "typical_p": 1.0,
-        "repetition_penalty": 1.0,
-        "length_penalty": 1.0,
-        "no_repeat_ngram_size": 0,
-        "encoder_no_repeat_ngram_size": 0,
-        "bad_words_ids": null,
-        "num_return_sequences": 1,
-        "output_scores": false,
-        "return_dict_in_generate": false,
-        "forced_bos_token_id": null,
-        "forced_eos_token_id": null,
-        "remove_invalid_values": false,
-        "exponential_decay_length_penalty": null,
-        "suppress_tokens": null,
-        "begin_suppress_tokens": null,
-        "architectures": null,
-        "finetuning_task": null,
-        "id2label": {
-            "0": "LABEL_0",
-            "1": "LABEL_1"
-        },
-        "label2id": {
-            "LABEL_0": 0,
-            "LABEL_1": 1
-        },
-        "tokenizer_class": null,
-        "prefix": null,
-        "bos_token_id": null,
-        "pad_token_id": null,
-        "eos_token_id": null,
-        "sep_token_id": null,
-        "decoder_start_token_id": null,
-        "task_specific_params": null,
-        "problem_type": null,
-        "_name_or_path": "",
-        "model_type": "siglip_vision_model",
-        "hidden_size": 1152,
-        "intermediate_size": 4304,
-        "num_hidden_layers": 27,
-        "num_attention_heads": 16,
-        "num_channels": 3,
-        "patch_size": 14,
-        "image_size": 384,
-        "attention_dropout": 0.0,
-        "layer_norm_eps": 1e-06,
-        "hidden_act": "gelu_pytorch_tanh"
-    },
     "vocab_size": 151936
 }