Upload folder using huggingface_hub

README.md

@@ -1,32 +1,34 @@
-# Planned.AI (planned day) Personalized Trip Planner Model in Tunisia - 4-bit Quantized
+---
+license: gemma
+library_name: transformers
+tags:
+- mlx
+widget:
+- messages:
+  - role: user
+    content: How does the brain work?
+inference:
+  parameters:
+    max_new_tokens: 200
+extra_gated_heading: Access Gemma on Hugging Face
+extra_gated_prompt: To access Gemma on Hugging Face, you’re required to review and
+  agree to Google’s usage license. To do this, please ensure you’re logged-in to Hugging
+  Face and click below. Requests are processed immediately.
+extra_gated_button_content: Acknowledge license
+---
+
+# SadokBarbouche/planned.AI-gemma-2b-it-quantized
+This model was converted to MLX format from [`google/gemma-1.1-2b-it`]().
+Refer to the [original model card](https://huggingface.co/google/gemma-1.1-2b-it) for more details on the model.
+## Use with mlx
 
-## Overview
-This repository contains a personalized trip planner tool based on a quantized version of the base model from the MLX library. The tool generates tailored trip itineraries for users based on their preferences and specified destinations. The model leverages a dataset of scraped places from across Tunisia to provide comprehensive and personalized recommendations.
-
-## Model Description
-The personalized trip planner utilizes a quantized version of the base model from the MLX library. The model has been trained on a dataset comprising various attractions, landmarks, and destinations from Tunisia. By incorporating user preferences and destination inputs, the model generates personalized trip plans that cater to individual interests and requirements.
-
-## Usage
-To utilize the Personalized Trip Planner tool, follow these steps:
-
-1. Install the MLX library:
 ```bash
 pip install mlx-lm
 ```
 
-2. Load the base model and tokenizer:
 ```python
-from mlx_lm import load
+from mlx_lm import load, generate
 
-# Load the quantized base model
 model, tokenizer = load("SadokBarbouche/planned.AI-gemma-2b-it-quantized")
+response = generate(model, tokenizer, prompt="hello", verbose=True)
 ```
-
-## Data Preparation
-The model training data comprises scraped information about various attractions and landmarks from Tunisia. The dataset was carefully curated to encompass a diverse range of destinations, ensuring the model's ability to generate comprehensive trip plans.
-
-## Evaluation
-The performance of the personalized trip planner tool was evaluated based on its ability to generate relevant, coherent, and personalized trip plans tailored to user preferences and specified destinations. Evaluation results demonstrate the effectiveness of the base model in providing valuable recommendations for travelers.
-
-## Acknowledgements
-We would like to express our gratitude to the contributors of the `google-maps-scraper` tool on GitHub, as well as the developers of the MLX library for their support in model integration and usage.

config.json

@@ -1,85 +1,86 @@
 {
-    "add_cross_attention": false,
-    "architectures": [
-        "GemmaForCausalLM"
-    ],
+    "vocab_size": 256000,
+    "max_position_embeddings": 8192,
+    "hidden_size": 2048,
+    "intermediate_size": 16384,
+    "num_hidden_layers": 18,
+    "num_attention_heads": 8,
+    "head_dim": 256,
+    "num_key_value_heads": 1,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_activation": "gelu_pytorch_tanh",
+    "initializer_range": 0.02,
+    "rms_norm_eps": 1e-06,
+    "use_cache": true,
+    "rope_theta": 10000.0,
     "attention_bias": false,
     "attention_dropout": 0.0,
-    "bad_words_ids": null,
-    "begin_suppress_tokens": null,
-    "bos_token_id": 2,
+    "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": true,
     "chunk_size_feed_forward": 0,
+    "is_encoder_decoder": false,
+    "is_decoder": false,
     "cross_attention_hidden_size": null,
-    "decoder_start_token_id": null,
-    "diversity_penalty": 0.0,
+    "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,
-    "eos_token_id": 1,
-    "exponential_decay_length_penalty": null,
-    "finetuning_task": null,
+    "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,
-    "head_dim": 256,
-    "hidden_act": "gelu",
-    "hidden_size": 2048,
+    "remove_invalid_values": false,
+    "exponential_decay_length_penalty": null,
+    "suppress_tokens": null,
+    "begin_suppress_tokens": null,
+    "architectures": [
+        "GemmaForCausalLM"
+    ],
+    "finetuning_task": null,
     "id2label": {
         "0": "LABEL_0",
         "1": "LABEL_1"
     },
-    "initializer_range": 0.02,
-    "intermediate_size": 16384,
-    "is_decoder": false,
-    "is_encoder_decoder": false,
     "label2id": {
         "LABEL_0": 0,
         "LABEL_1": 1
     },
-    "length_penalty": 1.0,
-    "max_length": 20,
-    "max_position_embeddings": 8192,
-    "min_length": 0,
-    "model_type": "gemma",
-    "no_repeat_ngram_size": 0,
-    "num_attention_heads": 8,
-    "num_beam_groups": 1,
-    "num_beams": 1,
-    "num_hidden_layers": 18,
-    "num_key_value_heads": 1,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": 0,
+    "tokenizer_class": null,
     "prefix": null,
+    "bos_token_id": 2,
+    "pad_token_id": 0,
+    "eos_token_id": 1,
+    "sep_token_id": null,
+    "decoder_start_token_id": null,
+    "task_specific_params": null,
     "problem_type": null,
-    "pruned_heads": {},
+    "_name_or_path": "/root/.cache/huggingface/hub/models--google--gemma-1.1-2b-it/snapshots/bf4924f313df5166dee1467161e886e55f2eb4d4",
+    "transformers_version": "4.39.3",
+    "model_type": "gemma",
     "quantization": {
         "group_size": 64,
         "bits": 4
-    },
-    "remove_invalid_values": false,
-    "repetition_penalty": 1.0,
-    "return_dict": true,
-    "return_dict_in_generate": false,
-    "rms_norm_eps": 1e-06,
-    "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": true,
-    "tokenizer_class": null,
-    "top_k": 50,
-    "top_p": 1.0,
-    "torch_dtype": "float16",
-    "torchscript": false,
-    "transformers_version": "4.38.2",
-    "typical_p": 1.0,
-    "use_bfloat16": false,
-    "use_cache": true,
-    "vocab_size": 256000
+    }
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c479437d917adc183d91e75516db16805bb64a7d2cba00b11c6e989ecafb536a
-size 2163541275
+oid sha256:778be7f9278a91ec3bbd3d554fafc1994bc3f85a95f548fa37dd77409d45ecec
+size 2163541283

special_tokens_map.json

@@ -18,7 +18,7 @@
     "single_word": false
   },
   "pad_token": {
-    "content": "<eos>",
+    "content": "<pad>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f30f819ff5b0f4cef2c8a6aafbeb20a13e7dd14409ece0f1e11e1d84bcfd281b
-size 17518937
+oid sha256:c15eb04bc5ad609fb26533e8525302c5640a945e5f67f65b7c849900acda7d99
+size 17518497

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "add_bos_token": true,
-  "add_eos_token": true,
+  "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<pad>",
@@ -1748,7 +1748,7 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<eos>",
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<eos>",
+  "pad_token": "<pad>",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "GemmaTokenizer",