together 0.2.4__tar.gz → 0.2.5__tar.gz

{together-0.2.4 → together-0.2.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: together
-Version: 0.2.4
+Version: 0.2.5
 Summary: Python client for Together's Cloud Platform!
 Project-URL: Homepage, https://github.com/togethercomputer/together
 Project-URL: Bug Tracker, https://github.com/togethercomputer/together/issues
@@ -211,16 +211,18 @@ Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Operating System :: POSIX :: Linux
 Classifier: Programming Language :: Python :: 3
 Requires-Python: >=3.6
-Requires-Dist: requests
+Requires-Dist: requests==2.31.0
 Requires-Dist: sseclient-py==1.7.2
-Requires-Dist: tqdm
-Requires-Dist: typer
+Requires-Dist: tqdm==4.66.1
+Requires-Dist: typer==0.9.0
 Provides-Extra: quality
 Requires-Dist: black~=23.1; extra == 'quality'
 Requires-Dist: mypy>=1.3.0; extra == 'quality'
 Requires-Dist: ruff<=0.0.259,>=0.0.241; extra == 'quality'
 Requires-Dist: types-requests>=2.31.0.1; extra == 'quality'
 Requires-Dist: types-tqdm>=4.65.0.0; extra == 'quality'
+Provides-Extra: tokenize
+Requires-Dist: transformers>=4.33.2; extra == 'tokenize'
 Description-Content-Type: text/markdown
 
 The [Together Python Library](https://pypi.org/project/together/) is the official Python client for Together's API platform, providing a convenient way for interacting with the Together APIs and enables easy integration of the inference API with your applications.
@@ -390,37 +392,36 @@ Refer to the [Files docs](https://docs.together.ai/docs/python-files) on the cor
 
 Files uploaded for training, fine-tuning and validation must be in [jsonlines](https://jsonlines.org/) format.
 
-We included an example dataset that comes with `together` to help you get a feel for the data format. Let's look at the first 5 lines of this 100 line dataset:
+In the example below we provide a link for you to download a jsonl file locally that serves as an example of the correct file formatting. In your terminal or commandline, navigate to the folder you want to download the file, paste the command below and hit enter.
 
-```python
-together.jokes_list[:5]
+```console
+curl https://huggingface.co/datasets/clam004/antihallucination_dataset/resolve/main/antihallucination.jsonl -o antihallucination.jsonl
 ```
 
-```
-[{'text': '<human>: Why is this joke funny? Q: What does a computer do when it is tired? A: It crashes!\nRosey: Did your computer ever stop working (freeze) or turn itself off when you wanted to use it? If it did, you can say your computer crashed. Computer crashes are frustrating because you cannot get your work done, and sometimes you lose the work you finished most recently, unless you saved it. Thankfully, they do not happen too often.'},
- {'text': "<human>: I'm going to give you a joke. After I give you the joke, please explain it: Q: Where can you go to practice math on New Year’s Eve? A: Times Square!\nRosey: To get better at math, people often people often practice addition (+) or subtraction (-) problems; then they work on multiplication (x) and division (÷), and all the way through calculus and beyond. Practicing multiplication is also known as practicing your times tables. You can say what is seven times nine (7 x 9), or you can can say what is seven multiplied by nine. They mean the same thing, times or multiplied by."},
- {'text': '<human>: Explain this joke: Q: When does it rain money? A: When there is change in the weather!\nRosey: “The rain in Spain falls mainly on the plain,” according to the song from My Fair Lady. In Peru, they just wish it would rain! But nowhere does it rain money. Rain is water that falls from the sky as part of the evaporation/water cycle. When it is sunny outside, and then the weather changes to cloudy or rainy, we say that there is a change in the weather.'},
- {'text': '<human>: Q: What happens when winter arrives? A: Autumn leaves! Why is this joke funny?\nRosey: In the northern hemisphere winter officially starts on December 21 (winter solstice, astronomical winter), but for many places in the north, it is already cold. Did you know that there is more than one way to mark the start of winter? Meteorologists, people who study the weather, talk about meteorological winter which starts on December 1. When talking about seasons, winter comes after fall; fall is also known as autumn.'},
- {'text': '<human>: Q: Where do roses sleep? A: In a flower bed! Why is this joke funny?\nRosey: According to many surveys, roses are one of the most popular flowers. Although they have thorns, some people say that they are not that hard to grow.'}]
-```
+This will download the dataset to a file called `antihallucination.jsonl`. Below are two examples of lines you will find in this `.jsonl` file. 
 
-Use the `together.Files.save_jsonl` function to save this python list of dictionaries into a jsonl file locally that has the correct formatting where each line is a json with single "text" field:
-
-```python
-together.Files.save_jsonl(together.jokes_list, "jokes.jsonl")
+```Text JSONL
+{"text": "<truth>Wilhelm Windelband (May 11, 1848 - October 22, 1915) was a German philosopher of the Baden School. Windelband is now mainly remembered for the terms \"nomothetic\" and \"idiographic\", which he introduced. These have currency in psychology and other areas, though not necessarily in line with his original meanings. Windelband was a Neo-Kantian who protested other Neo-Kantians of his time and maintained that \"to understand Kant rightly means to go beyond him\". Against his positivist contemporaries, Windelband argued that philosophy should engage in humanistic dialogue with the natural sciences rather than uncritically appropriating its methodologies. His interests in psychology and cultural sciences represented an opposition to psychologism and historicism schools by a critical philosophic system. Windelband relied in his effort to reach beyond Kant on such philosophers as Georg Wilhelm Friedrich Hegel, Johann Friedrich Herbart, and Hermann Lotze. Closely associated with Windelband was Heinrich Rickert. Windelband's disciples were not only noted philosophers, but sociologists like Max Weber and theologians like Ernst Troeltsch and Albert Schweitzer.<generated>Wilhelm Windelband (15 March 1848 – 18 September 1915) was a German philosopher of the late 19th and early 20th centuries. He is now remembered mainly for the terms \"nomothetic\" and \"idiographic,\" which he introduced. He also wrote on history, psychology, the philosophy of religion, values, and other topics. He was a neo-Kantian who protested other neo-Kantians of his time and maintained a critical position towards psychologism. Windelband is known as one of the founders of the \"Baden School\" of neo-Kantianism. He was a student of Kuno Fischer and Franz Brentano. His students included Edmund Husserl, Adolf Reinach, Carl Stumpf, and Richard von Mises.<eval>Wilhelm Windelband (15 March 1848 – 18 September 1915) was a German philosopher of the late 19th and early 20th centuries.<minor_inaccurate>He is now remembered mainly for the terms \"nomothetic\" and \"idiographic,\" which he introduced.<accurate>He also wrote on history, psychology, the philosophy of religion, values, and other topics.<accurate>He was a neo-Kantian who protested other neo-Kantians of his time and maintained a critical position towards psychologism.<accurate>Windelband is known as one of the founders of the \"Baden School\" of neo-Kantianism.<accurate>He was a student of Kuno Fischer and Franz Brentano.<major_inaccurate>His students included Edmund Husserl, Adolf Reinach, Carl Stumpf, and Richard von Mises.<major_inaccurate><stop>"}
+{"text": "<truth>Admiral of the Fleet Matthew Aylmer, 1st Baron Aylmer (ca. 1650 - 18 August 1720) was a Royal Navy officer. He was one of the captains who sent a letter to Prince William of Orange, who had just landed at Torbay, assuring the Prince of the captains' support; the Prince's response ultimately led to the Royal Navy switching allegiance to the Prince and the Glorious Revolution of November 1688. Aylmer saw action at the Battle of Bantry Bay in May 1689, at the Battle of Beachy Head in July 1690, and again at the Battle of Barfleur in May 1692 during the Nine Years' War. Aylmer became Commander-in-Chief of the Navy on 12 November 1709. However, when Aylmer met a French squadron and convoy, he was only able to capture one merchantman and the 56-gun \"Superbe\": the new Harley ministry used this failure as an excuse to remove him as Commander-in-Chief and did so a few months later. Following the accession of George I and the appointment of the Townshend ministry, Aylmer was reappointed Commander-in-Chief on 5 November 1714. He was also appointed Governor of Greenwich Hospital: in this post he founded the Royal Hospital School for the sons of seamen.<generated>Matthew Aylmer, 1st Baron Aylmer (1708–1794) was an Irish soldier and colonial administrator. He was born in Dublin, the son of a barrister, and was educated at Trinity College, Dublin. He joined the British Army in 1727 and served in the War of the Austrian Succession and the Seven Years' War. He was promoted to lieutenant-general in 1772 and was appointed Governor of Gibraltar in 1775. He was made a baron in 1782 and was appointed Commander-in-Chief of the British forces in North America in 1783. He was recalled in 1790 and died in London in 1794. He was buried in Westminster Abbey.<eval>Matthew Aylmer, 1st Baron Aylmer (1708–1794) was an Irish soldier and colonial administrator.<minor_inaccurate>He was born in Dublin, the son of a barrister, and was educated at Trinity College, Dublin.<minor_inaccurate>He joined the British Army in 1727 and served in the War of the Austrian Succession and the Seven Years' War.<minor_inaccurate>He was promoted to lieutenant-general in 1772 and was appointed Governor of Gibraltar in 1775.<major_inaccurate>He was made a baron in 1782 and was appointed Commander-in-Chief of the British forces in North America in 1783.<major_inaccurate>He was recalled in 1790 and died in London in 1794.<major_inaccurate>He was buried in Westminster Abbey.<major_inaccurate><stop>"}
 ```
 
+This dataset teaches your model a special task using special sequences not found elsewhere. It teaches your model how to check another model's generated text against a ground truth and annotate the generated text for hallucinations. We made up special sequences `<truth>`, `<generated>`, `<eval>` and `<stop>` in order to do this. Read more about how to come up with your own special sequences [here](https://docs.together.ai/docs/fine-tuning-task-specific-sequences).   
+
 Use `together.Files.check` to check if your jsonl file has the correct format. Also take a look at it with the editor of your choice. 
 
 ```python
-resp = together.Files.check(file="jokes.jsonl")
+resp = together.Files.check(file="antihallucination.jsonl")
 print(resp)
 ```
 
 If the file format is correct, the `is_check_passed` field will be True
 
 ```
-{'is_check_passed': True, 'model_special_tokens': 'we are not yet checking end of sentence tokens for this model', 'file_present': 'File found', 'file_size': 'File size 0.0 GB', 'num_samples': 100, 'num_samples_w_eos_token': 0}
+{'is_check_passed': True,
+ 'model_special_tokens': 'we are not yet checking end of sentence tokens for this model',
+ 'file_present': 'File found',
+ 'file_size': 'File size 0.001 GB',
+ 'num_samples': 238}
 ```
 
 To check if your data contains `model_special_tokens` (we are still expanding this to include more models and tokens) use:
@@ -450,7 +451,6 @@ print(resp)
                    'resulted in only 10 samples. Our minimum is 100 samples. ',
     'model_special_tokens': 'we are not yet checking end of sentence tokens '
                             'for this model',
-    'num_samples_w_eos_token': 0,
     'text_field': 'No "text" field was found on line 7 of the the input '
                   'file.Expected format: {"text":"my sample string"}.see '
                   'https://docs.together.ai/docs/fine-tuning for more '
@@ -468,13 +468,21 @@ The checker will look at the jsonl file to see if:
 In the `resp`, we will report the first line where the formatting error occurs, print the line, and the data format documentation on our website. Next lets upload a good file:
 
 ```python
-together.Files.upload(file="jokes.jsonl")
+resp = together.Files.upload(file="antihallucination.jsonl")
+file_id = resp["id"]
 ```
 
 You will get back the file `id` of the file you just uploaded
 
 ```
-{'filename': 'jokes.jsonl','id': 'file-d0d318cb-b7d9-493a-bd70-1cfe089d3815','object': 'file'}
+{'filename': 'antihallucination.jsonl',
+ 'id': 'file-33ecca00-17ea-4968-ada2-9f82ef2f4cb8',
+ 'object': 'file',
+ 'report_dict': {'is_check_passed': True,
+  'model_special_tokens': 'we are not yet checking end of sentence tokens for this model',
+  'file_present': 'File found',
+  'file_size': 'File size 0.001 GB',
+  'num_samples': 238}}
 ```
 
 You will get back the file `id` of the file you just uploaded, but if you forget it, you can get the `id`'s of all the files you have uploaded using `together.Files.list()`. You'll need these `id`'s that start with `file-960be810-4d....` in order to start a fine-tuning job
@@ -509,7 +517,7 @@ Run and manage your fine-tuning jobs, enabling you to tune all model layers, con
 
 Refer to the [Fine-tuning docs](https://docs.together.ai/docs/python-fine-tuning) on how to get started.
 
-Now that you have a valid file uploaded to together, you can finetune any of the models listed [here](https://docs.together.ai/docs/models-fine-tuning) or here `together.finetune_model_names` using `together.Finetune.create`
+Now that you have a valid file uploaded to together, you can finetune any of the models listed [here](https://docs.together.ai/docs/models-fine-tuning) using `together.Finetune.create`
 
 ```python
 resp = together.Finetune.create(
@@ -527,6 +535,25 @@ fine_tune_id = resp['id']
 print(resp)
 ```
 
+Unless you set `confirm_inputs=False` in `together.Finetune.create`, or `--quiet` in the CLI, there will be a confirmation step to make sure you are aware of any defaults or arguments that needed to be reset from their original inputs for this specific finetune job. Type `y` then `Enter` to submit the job, or anything else to abort. 
+
+```
+10-02-2023 11:14:27 - together.finetune - WARNING - Batch size must be 144 for togethercomputer/llama-2-70b-chat model. Setting batch size to 144 (finetune.py:114)
+Note: Some hyperparameters may have been adjusted with their minimum/maximum values for a given model.
+
+Job creation details:
+{   'batch_size': 144,
+    'learning_rate': 1e-05,
+    'model': 'togethercomputer/llama-2-70b-chat',
+    'n_checkpoints': 1,
+    'n_epochs': 4,
+    'suffix': None,
+    'training_file': 'file-33ecca00-17ea-4968-ada2-9f82ef2f4cb8',
+    'wandb_key': 'xxxx'}
+
+Do you want to submit the job? [y/N]
+```
+
 The response `resp` has alot of information for you that you can retrieve later with `together.Finetune.retrieve` using the `fine_tune_id` for this job. You can find this `fine_tune_id` in `resp['id']` and use it to check in on how your finetune job is doing. 
 
 ```python
@@ -565,6 +592,69 @@ together.Models.ready("carlton/ft-dd93c727-f35e-41c2-a370-7d55b54128fa-2023-08-1
 {'ready': 'model is ready for start, status code:1'}
 ```
 
+### Using a Downloaded Model
+
+The model will download as a `tar.zst` file
+
+```python
+together.Finetune.download(
+    fine_tune_id="ft-eb167402-98ed-4ac5-b6f5-8140c4ba146e",
+    output = "my-model/model.tar.zst"
+)
+```
+
+To uncompress this filetype on Mac you need to install zstd. 
+
+```
+brew install zstd
+cd my-model
+zstd -d model.tar.zst
+tar -xvf model.tar
+cd ..
+```
+
+Within the folder that you uncompress the file, you will find a set of files like this:  
+`ls my-model`
+
+```
+tokenizer_config.json
+special_tokens_map.json
+pytorch_model.bin
+generation_config.json
+tokenizer.json
+config.json
+```
+
+Use the folder path that contains these `.bin` and `.json` files to load your model
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+tokenizer = AutoTokenizer.from_pretrained("./my-model")
+
+model = AutoModelForCausalLM.from_pretrained(
+  "./my-model", 
+  trust_remote_code=True, 
+).to(device)
+
+input_context = "Space Robots are"
+input_ids = tokenizer.encode(input_context, return_tensors="pt")
+output = model.generate(input_ids.to(device), max_length=128, temperature=0.7).cpu()
+output_text = tokenizer.decode(output[0], skip_special_tokens=True)
+print(output_text)
+```
+
+```
+Space Robots are a great way to get your kids interested in science. After all, they are the future!
+```
+
+## Colab Tutorial
+
+Follow along in our Colab (Google Colaboratory) Notebook Tutorial [Example Finetuning Project](https://colab.research.google.com/drive/11DwtftycpDSgp3Z1vnV-Cy68zvkGZL4K?usp=sharing).
+
 ## Chat
 
 The `chat` command is a CLI-based chat application that can be used for back-and-forth conversations with models in a pre-defined format.

{together-0.2.4 → together-0.2.5}/README.md

@@ -165,37 +165,36 @@ Refer to the [Files docs](https://docs.together.ai/docs/python-files) on the cor
 
 Files uploaded for training, fine-tuning and validation must be in [jsonlines](https://jsonlines.org/) format.
 
-We included an example dataset that comes with `together` to help you get a feel for the data format. Let's look at the first 5 lines of this 100 line dataset:
+In the example below we provide a link for you to download a jsonl file locally that serves as an example of the correct file formatting. In your terminal or commandline, navigate to the folder you want to download the file, paste the command below and hit enter.
 
-```python
-together.jokes_list[:5]
+```console
+curl https://huggingface.co/datasets/clam004/antihallucination_dataset/resolve/main/antihallucination.jsonl -o antihallucination.jsonl
 ```
 
-```
-[{'text': '<human>: Why is this joke funny? Q: What does a computer do when it is tired? A: It crashes!\nRosey: Did your computer ever stop working (freeze) or turn itself off when you wanted to use it? If it did, you can say your computer crashed. Computer crashes are frustrating because you cannot get your work done, and sometimes you lose the work you finished most recently, unless you saved it. Thankfully, they do not happen too often.'},
- {'text': "<human>: I'm going to give you a joke. After I give you the joke, please explain it: Q: Where can you go to practice math on New Year’s Eve? A: Times Square!\nRosey: To get better at math, people often people often practice addition (+) or subtraction (-) problems; then they work on multiplication (x) and division (÷), and all the way through calculus and beyond. Practicing multiplication is also known as practicing your times tables. You can say what is seven times nine (7 x 9), or you can can say what is seven multiplied by nine. They mean the same thing, times or multiplied by."},
- {'text': '<human>: Explain this joke: Q: When does it rain money? A: When there is change in the weather!\nRosey: “The rain in Spain falls mainly on the plain,” according to the song from My Fair Lady. In Peru, they just wish it would rain! But nowhere does it rain money. Rain is water that falls from the sky as part of the evaporation/water cycle. When it is sunny outside, and then the weather changes to cloudy or rainy, we say that there is a change in the weather.'},
- {'text': '<human>: Q: What happens when winter arrives? A: Autumn leaves! Why is this joke funny?\nRosey: In the northern hemisphere winter officially starts on December 21 (winter solstice, astronomical winter), but for many places in the north, it is already cold. Did you know that there is more than one way to mark the start of winter? Meteorologists, people who study the weather, talk about meteorological winter which starts on December 1. When talking about seasons, winter comes after fall; fall is also known as autumn.'},
- {'text': '<human>: Q: Where do roses sleep? A: In a flower bed! Why is this joke funny?\nRosey: According to many surveys, roses are one of the most popular flowers. Although they have thorns, some people say that they are not that hard to grow.'}]
-```
+This will download the dataset to a file called `antihallucination.jsonl`. Below are two examples of lines you will find in this `.jsonl` file. 
 
-Use the `together.Files.save_jsonl` function to save this python list of dictionaries into a jsonl file locally that has the correct formatting where each line is a json with single "text" field:
-
-```python
-together.Files.save_jsonl(together.jokes_list, "jokes.jsonl")
+```Text JSONL
+{"text": "<truth>Wilhelm Windelband (May 11, 1848 - October 22, 1915) was a German philosopher of the Baden School. Windelband is now mainly remembered for the terms \"nomothetic\" and \"idiographic\", which he introduced. These have currency in psychology and other areas, though not necessarily in line with his original meanings. Windelband was a Neo-Kantian who protested other Neo-Kantians of his time and maintained that \"to understand Kant rightly means to go beyond him\". Against his positivist contemporaries, Windelband argued that philosophy should engage in humanistic dialogue with the natural sciences rather than uncritically appropriating its methodologies. His interests in psychology and cultural sciences represented an opposition to psychologism and historicism schools by a critical philosophic system. Windelband relied in his effort to reach beyond Kant on such philosophers as Georg Wilhelm Friedrich Hegel, Johann Friedrich Herbart, and Hermann Lotze. Closely associated with Windelband was Heinrich Rickert. Windelband's disciples were not only noted philosophers, but sociologists like Max Weber and theologians like Ernst Troeltsch and Albert Schweitzer.<generated>Wilhelm Windelband (15 March 1848 – 18 September 1915) was a German philosopher of the late 19th and early 20th centuries. He is now remembered mainly for the terms \"nomothetic\" and \"idiographic,\" which he introduced. He also wrote on history, psychology, the philosophy of religion, values, and other topics. He was a neo-Kantian who protested other neo-Kantians of his time and maintained a critical position towards psychologism. Windelband is known as one of the founders of the \"Baden School\" of neo-Kantianism. He was a student of Kuno Fischer and Franz Brentano. His students included Edmund Husserl, Adolf Reinach, Carl Stumpf, and Richard von Mises.<eval>Wilhelm Windelband (15 March 1848 – 18 September 1915) was a German philosopher of the late 19th and early 20th centuries.<minor_inaccurate>He is now remembered mainly for the terms \"nomothetic\" and \"idiographic,\" which he introduced.<accurate>He also wrote on history, psychology, the philosophy of religion, values, and other topics.<accurate>He was a neo-Kantian who protested other neo-Kantians of his time and maintained a critical position towards psychologism.<accurate>Windelband is known as one of the founders of the \"Baden School\" of neo-Kantianism.<accurate>He was a student of Kuno Fischer and Franz Brentano.<major_inaccurate>His students included Edmund Husserl, Adolf Reinach, Carl Stumpf, and Richard von Mises.<major_inaccurate><stop>"}
+{"text": "<truth>Admiral of the Fleet Matthew Aylmer, 1st Baron Aylmer (ca. 1650 - 18 August 1720) was a Royal Navy officer. He was one of the captains who sent a letter to Prince William of Orange, who had just landed at Torbay, assuring the Prince of the captains' support; the Prince's response ultimately led to the Royal Navy switching allegiance to the Prince and the Glorious Revolution of November 1688. Aylmer saw action at the Battle of Bantry Bay in May 1689, at the Battle of Beachy Head in July 1690, and again at the Battle of Barfleur in May 1692 during the Nine Years' War. Aylmer became Commander-in-Chief of the Navy on 12 November 1709. However, when Aylmer met a French squadron and convoy, he was only able to capture one merchantman and the 56-gun \"Superbe\": the new Harley ministry used this failure as an excuse to remove him as Commander-in-Chief and did so a few months later. Following the accession of George I and the appointment of the Townshend ministry, Aylmer was reappointed Commander-in-Chief on 5 November 1714. He was also appointed Governor of Greenwich Hospital: in this post he founded the Royal Hospital School for the sons of seamen.<generated>Matthew Aylmer, 1st Baron Aylmer (1708–1794) was an Irish soldier and colonial administrator. He was born in Dublin, the son of a barrister, and was educated at Trinity College, Dublin. He joined the British Army in 1727 and served in the War of the Austrian Succession and the Seven Years' War. He was promoted to lieutenant-general in 1772 and was appointed Governor of Gibraltar in 1775. He was made a baron in 1782 and was appointed Commander-in-Chief of the British forces in North America in 1783. He was recalled in 1790 and died in London in 1794. He was buried in Westminster Abbey.<eval>Matthew Aylmer, 1st Baron Aylmer (1708–1794) was an Irish soldier and colonial administrator.<minor_inaccurate>He was born in Dublin, the son of a barrister, and was educated at Trinity College, Dublin.<minor_inaccurate>He joined the British Army in 1727 and served in the War of the Austrian Succession and the Seven Years' War.<minor_inaccurate>He was promoted to lieutenant-general in 1772 and was appointed Governor of Gibraltar in 1775.<major_inaccurate>He was made a baron in 1782 and was appointed Commander-in-Chief of the British forces in North America in 1783.<major_inaccurate>He was recalled in 1790 and died in London in 1794.<major_inaccurate>He was buried in Westminster Abbey.<major_inaccurate><stop>"}
 ```
 
+This dataset teaches your model a special task using special sequences not found elsewhere. It teaches your model how to check another model's generated text against a ground truth and annotate the generated text for hallucinations. We made up special sequences `<truth>`, `<generated>`, `<eval>` and `<stop>` in order to do this. Read more about how to come up with your own special sequences [here](https://docs.together.ai/docs/fine-tuning-task-specific-sequences).   
+
 Use `together.Files.check` to check if your jsonl file has the correct format. Also take a look at it with the editor of your choice. 
 
 ```python
-resp = together.Files.check(file="jokes.jsonl")
+resp = together.Files.check(file="antihallucination.jsonl")
 print(resp)
 ```
 
 If the file format is correct, the `is_check_passed` field will be True
 
 ```
-{'is_check_passed': True, 'model_special_tokens': 'we are not yet checking end of sentence tokens for this model', 'file_present': 'File found', 'file_size': 'File size 0.0 GB', 'num_samples': 100, 'num_samples_w_eos_token': 0}
+{'is_check_passed': True,
+ 'model_special_tokens': 'we are not yet checking end of sentence tokens for this model',
+ 'file_present': 'File found',
+ 'file_size': 'File size 0.001 GB',
+ 'num_samples': 238}
 ```
 
 To check if your data contains `model_special_tokens` (we are still expanding this to include more models and tokens) use:
@@ -225,7 +224,6 @@ print(resp)
                    'resulted in only 10 samples. Our minimum is 100 samples. ',
     'model_special_tokens': 'we are not yet checking end of sentence tokens '
                             'for this model',
-    'num_samples_w_eos_token': 0,
     'text_field': 'No "text" field was found on line 7 of the the input '
                   'file.Expected format: {"text":"my sample string"}.see '
                   'https://docs.together.ai/docs/fine-tuning for more '
@@ -243,13 +241,21 @@ The checker will look at the jsonl file to see if:
 In the `resp`, we will report the first line where the formatting error occurs, print the line, and the data format documentation on our website. Next lets upload a good file:
 
 ```python
-together.Files.upload(file="jokes.jsonl")
+resp = together.Files.upload(file="antihallucination.jsonl")
+file_id = resp["id"]
 ```
 
 You will get back the file `id` of the file you just uploaded
 
 ```
-{'filename': 'jokes.jsonl','id': 'file-d0d318cb-b7d9-493a-bd70-1cfe089d3815','object': 'file'}
+{'filename': 'antihallucination.jsonl',
+ 'id': 'file-33ecca00-17ea-4968-ada2-9f82ef2f4cb8',
+ 'object': 'file',
+ 'report_dict': {'is_check_passed': True,
+  'model_special_tokens': 'we are not yet checking end of sentence tokens for this model',
+  'file_present': 'File found',
+  'file_size': 'File size 0.001 GB',
+  'num_samples': 238}}
 ```
 
 You will get back the file `id` of the file you just uploaded, but if you forget it, you can get the `id`'s of all the files you have uploaded using `together.Files.list()`. You'll need these `id`'s that start with `file-960be810-4d....` in order to start a fine-tuning job
@@ -284,7 +290,7 @@ Run and manage your fine-tuning jobs, enabling you to tune all model layers, con
 
 Refer to the [Fine-tuning docs](https://docs.together.ai/docs/python-fine-tuning) on how to get started.
 
-Now that you have a valid file uploaded to together, you can finetune any of the models listed [here](https://docs.together.ai/docs/models-fine-tuning) or here `together.finetune_model_names` using `together.Finetune.create`
+Now that you have a valid file uploaded to together, you can finetune any of the models listed [here](https://docs.together.ai/docs/models-fine-tuning) using `together.Finetune.create`
 
 ```python
 resp = together.Finetune.create(
@@ -302,6 +308,25 @@ fine_tune_id = resp['id']
 print(resp)
 ```
 
+Unless you set `confirm_inputs=False` in `together.Finetune.create`, or `--quiet` in the CLI, there will be a confirmation step to make sure you are aware of any defaults or arguments that needed to be reset from their original inputs for this specific finetune job. Type `y` then `Enter` to submit the job, or anything else to abort. 
+
+```
+10-02-2023 11:14:27 - together.finetune - WARNING - Batch size must be 144 for togethercomputer/llama-2-70b-chat model. Setting batch size to 144 (finetune.py:114)
+Note: Some hyperparameters may have been adjusted with their minimum/maximum values for a given model.
+
+Job creation details:
+{   'batch_size': 144,
+    'learning_rate': 1e-05,
+    'model': 'togethercomputer/llama-2-70b-chat',
+    'n_checkpoints': 1,
+    'n_epochs': 4,
+    'suffix': None,
+    'training_file': 'file-33ecca00-17ea-4968-ada2-9f82ef2f4cb8',
+    'wandb_key': 'xxxx'}
+
+Do you want to submit the job? [y/N]
+```
+
 The response `resp` has alot of information for you that you can retrieve later with `together.Finetune.retrieve` using the `fine_tune_id` for this job. You can find this `fine_tune_id` in `resp['id']` and use it to check in on how your finetune job is doing. 
 
 ```python
@@ -340,6 +365,69 @@ together.Models.ready("carlton/ft-dd93c727-f35e-41c2-a370-7d55b54128fa-2023-08-1
 {'ready': 'model is ready for start, status code:1'}
 ```
 
+### Using a Downloaded Model
+
+The model will download as a `tar.zst` file
+
+```python
+together.Finetune.download(
+    fine_tune_id="ft-eb167402-98ed-4ac5-b6f5-8140c4ba146e",
+    output = "my-model/model.tar.zst"
+)
+```
+
+To uncompress this filetype on Mac you need to install zstd. 
+
+```
+brew install zstd
+cd my-model
+zstd -d model.tar.zst
+tar -xvf model.tar
+cd ..
+```
+
+Within the folder that you uncompress the file, you will find a set of files like this:  
+`ls my-model`
+
+```
+tokenizer_config.json
+special_tokens_map.json
+pytorch_model.bin
+generation_config.json
+tokenizer.json
+config.json
+```
+
+Use the folder path that contains these `.bin` and `.json` files to load your model
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+tokenizer = AutoTokenizer.from_pretrained("./my-model")
+
+model = AutoModelForCausalLM.from_pretrained(
+  "./my-model", 
+  trust_remote_code=True, 
+).to(device)
+
+input_context = "Space Robots are"
+input_ids = tokenizer.encode(input_context, return_tensors="pt")
+output = model.generate(input_ids.to(device), max_length=128, temperature=0.7).cpu()
+output_text = tokenizer.decode(output[0], skip_special_tokens=True)
+print(output_text)
+```
+
+```
+Space Robots are a great way to get your kids interested in science. After all, they are the future!
+```
+
+## Colab Tutorial
+
+Follow along in our Colab (Google Colaboratory) Notebook Tutorial [Example Finetuning Project](https://colab.research.google.com/drive/11DwtftycpDSgp3Z1vnV-Cy68zvkGZL4K?usp=sharing).
+
 ## Chat
 
 The `chat` command is a CLI-based chat application that can be used for back-and-forth conversations with models in a pre-defined format.