add model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

GEMMA_LICENSE.md

@@ -0,0 +1 @@
+Gemma is provided under and subject to the Gemma Terms of Use found at ai.google.dev/gemma/terms.

LICENSE.md

@@ -0,0 +1,26 @@
+Copyright (c) 2024, Danilo Peixoto Ferreira. All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+* Redistributions of source code must retain the above copyright notice, this
+ list of conditions and the following disclaimer.
+
+* Redistributions in binary form must reproduce the above copyright notice,
+ this list of conditions and the following disclaimer in the documentation
+ and/or other materials provided with the distribution.
+
+* Neither the name of the copyright holder nor the names of its
+ contributors may be used to endorse or promote products derived from
+ this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

README.md

@@ -1,3 +1,162 @@
 ---
+pretty_name: Pandora 7B Chat
+base_model: google/gemma-7b
+datasets:
+- danilopeixoto/pandora-instruct
+- danilopeixoto/pandora-tool-calling
+- danilopeixoto/pandora-rlhf
+task_categories:
+- text-generation
+tags:
+- chat
+- dpo
+- fine-tuning
+- function-calling
+- instruct
+- rlhf
+- sft
+- tool-calling
 license: bsd-3-clause
 ---
+
+# Pandora 7B Chat
+
+Pandora 7B Chat is a Large Language Model (LLM) designed for chat applications.
+
+Pandora is fine-tuned with publicly available datasets, including a tool-calling dataset for agent-based tasks and a Reinforcement Learning from Human Feedback (RLHF) dataset with Direct Preference Optimization (DPO) training for preference alignment.
+
+The fine-tuning process incorporates Low-Rank Adaptation (LoRA) with the [MLX framework](https://ml-explore.github.io/mlx/build/html/index.html), optimized for Apple Silicon.
+
+The model is based on the [google/gemma-7b](https://huggingface.co/google/gemma-7b) model.
+
+![Pandora](assets/pandora.jpeg)
+
+## Datasets
+
+Datasets used for fine-tuning stages:
+
+- [danilopeixoto/pandora-instruct](https://huggingface.co/datasets/danilopeixoto/pandora-instruct)
+- [danilopeixoto/pandora-tool-calling](https://huggingface.co/datasets/danilopeixoto/pandora-tool-calling)
+- [danilopeixoto/pandora-rlhf](https://huggingface.co/datasets/danilopeixoto/pandora-rlhf)
+
+## Evaluation
+
+Evaluation on [MT-Bench](https://arxiv.org/abs/2306.05685) multi-turn benchmark:
+
+![Benchmark](assets/benchmark.svg)
+
+## Usage
+
+Install package dependencies:
+
+```shell
+pip install mlx-lm
+```
+
+Generate response:
+
+```python
+from mlx_lm import load, generate
+
+
+model, tokenizer = load('danilopeixoto/pandora-7b-chat')
+
+prompt = '''<|start|>system
+You are Pandora, a helpful AI assistant.
+<|end|>
+<|start|>user
+Hello!
+<|end|>
+<|start|>'''
+
+response = generate(model, tokenizer, prompt)
+print(response)
+```
+
+The model supports the following prompt templates:
+
+**Question-answering with system messages**
+
+```txt
+<|start|>system
+{system_message}
+<|end|>
+<|start|>user
+{user_message}
+<|end|>
+<|start|>assistant
+{assistant_message}
+<|end|>
+```
+
+**Tool calling**
+
+```txt
+<|start|>system
+{system_message}
+<|end|>
+<|start|>system:tools
+{system_tools_message}
+<|end|>
+<|start|>user
+{user_message}
+<|end|>
+<|start|>assistant:tool_calls
+{assistant_tool_calls_message}
+<|end|>
+<|start|>tool
+{tool_message}
+<|end|>
+<|start|>assistant
+{assistant_message}
+<|end|>
+```
+
+> **Note** The variables `system_tools_message`, `assistant_tool_calls_message`, and `tool_message` must contain valid YAML.
+
+An example of a tool-calling prompt:
+
+```python
+prompt = '''<|start|>system
+You are Pandora, a helpful AI assistant.
+<|end|>
+<|start|>system:tools
+- description: Get the current weather based on a given location.
+ name: get_current_weather
+ parameters:
+ type: object
+ properties:
+ location:
+ type: string
+ description: The location name.
+ required:
+ - location
+<|end|>
+<|start|>user
+What is the weather in Sydney, Australia?
+<|end|>
+<|start|>assistant:tool_calls
+- name: get_current_weather
+ arguments:
+ location: Sydney, Australia
+<|end|>
+<|start|>tool
+name: get_current_weather
+content: 72°F
+<|end|>
+<|start|>'''
+```
+
+## Examples
+
+**OpenGPTs**
+
+![OpenGPTs](assets/opengpts.png)
+
+## Copyright and license
+
+Copyright (c) 2024, Danilo Peixoto Ferreira. All rights reserved.
+
+Project developed under a [BSD-3-Clause license](LICENSE.md).
+
+Gemma is provided under and subject to the [Gemma Terms of Use license](GEMMA_LICENSE.md).

added_tokens.json

@@ -0,0 +1,4 @@
+{
+ "<|end|>": 256001,
+ "<|start|>": 256000
+}

config.json

@@ -0,0 +1,82 @@
+{
+ "vocab_size": 256002,
+ "max_position_embeddings": 8192,
+ "hidden_size": 3072,
+ "intermediate_size": 24576,
+ "num_hidden_layers": 28,
+ "num_attention_heads": 16,
+ "head_dim": 256,
+ "num_key_value_heads": 16,
+ "hidden_act": "gelu",
+ "initializer_range": 0.02,
+ "rms_norm_eps": 1e-06,
+ "use_cache": true,
+ "rope_theta": 10000.0,
+ "attention_bias": false,
+ "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": 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": [
+ "GemmaForCausalLM"
+ ],
+ "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": 2,
+ "pad_token_id": 0,
+ "eos_token_id": 256001,
+ "sep_token_id": null,
+ "decoder_start_token_id": null,
+ "task_specific_params": null,
+ "problem_type": null,
+ "_name_or_path": "models/pandora-7b-sfttool-2000it",
+ "transformers_version": "4.38.1",
+ "model_type": "gemma",
+ "rope_scaling": null
+}

model.0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad26db0dc8f8fa892b7aa2b2147438b0f7ee0e83d10556b193ac513f5a0b2424
+size 5297499010

model.1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c1f8c925ccf32b96295430ad46795a429fa042df1e0eafa772675a1d2d3f8be
+size 5234624520

model.2.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32fed2eb2c3785bdf4aee3dc6ae0ce48de0e6c8efb236cb80bf7f88fc2833088
+size 5284943325

model.3.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da342e27db0dd06c2865ee288191baea64f4cf1fe4d7a2cf04510bd7aaf44695
+size 1258336744

special_tokens_map.json

@@ -0,0 +1,38 @@
+{
+ "additional_special_tokens": [
+ "<bos>",
+ "<eos>",
+ "<unk>",
+ "<pad>",
+ "<|start|>",
+ "<|end|>"
+ ],
+ "bos_token": {
+ "content": "<bos>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<|end|>",
+ "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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd3bef86b3df2b29baafcd73c2888c50c98ea304935de941a5f69d47110e474e
+size 17477923

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

tokenizer_config.json

@@ -0,0 +1,73 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "added_tokens_decoder": {
+ "0": {
+ "content": "<pad>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "1": {
+ "content": "<eos>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "2": {
+ "content": "<bos>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "3": {
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "256000": {
+ "content": "<|start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "256001": {
+ "content": "<|end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "additional_special_tokens": [
+ "<bos>",
+ "<eos>",
+ "<unk>",
+ "<pad>",
+ "<|start|>",
+ "<|end|>"
+ ],
+ "bos_token": "<bos>",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<|end|>",
+ "legacy": null,
+ "model_max_length": 1000000000000000019884624838656,
+ "pad_token": "<pad>",
+ "sp_model_kwargs": {},
+ "spaces_between_special_tokens": false,
+ "tokenizer_class": "GemmaTokenizer",
+ "unk_token": "<unk>",
+ "use_default_system_prompt": false
+}