Update README.md

README.md

@@ -1,219 +1,304 @@
 ---
-library_name: peft
-base_model: meta-llama/Llama-2-7b-chat-hf
+language:
+- en
+pipeline_tag: text-generation
+inference: false
+tags:
+- facebook
+- meta
+- pytorch
+- llama
+- llama-2
+- functions
+- function calling
+- sharded
 ---
+# Function Calling Llama 2 + Mistral Models (version 2)
+- Function calling Llama extends the hugging face Llama 2 models with function calling capabilities.
+- The model responds with a structured json argument with the function name and arguments.
 
-# Model Card for Model ID
+**Recent Updates**
+- October 11th 2023 -> added Mistral 7B with function calling
+- October 11th 2023 -> new models pushed, trained on an improved underlying dataset
 
-<!-- Provide a quick summary of what the model is/does. -->
+**Improvements with v2**
+1. Shortened syntax: Only function descriptions are needed for inference and no added instruction is required.
+2. Function descriptions are moved outside of the system prompt. This avoids the behaviour of function calling being affected by how the system prompt had been trained to influence the model.
 
+Available models:
+- Llama-7B-chat with function calling ([Base Model](https://huggingface.co/Trelis/Llama-2-7b-chat-hf-function-calling-v2)), ([PEFT Adapters](https://huggingface.co/Trelis/Llama-2-7b-chat-hf-function-calling-adapters-v2)), ([GGUF - files are in the main branch of the base model]) - Free
+- Mistral-7B-Instruct-v0.1 with function calling ([Base Model](https://huggingface.co/Trelis/Mistral-7B-Instruct-v0.1-function-calling-v2)), ([PEFT Adapters](https://huggingface.co/Trelis/Mistral-7B-Instruct-v0.1-function-calling-adapters-v2)) - Paid, [purchase here](https://buy.stripe.com/cN2cNybSdgyncV25kQ)
+- Llama-13B-chat with function calling ([Base Model](https://huggingface.co/Trelis/Llama-2-13b-chat-hf-function-calling-v2)), ([PEFT Adapters](https://huggingface.co/Trelis/Llama-2-13b-chat-hf-function-calling-adapters-v2)) - Paid, [purchase here](https://buy.stripe.com/9AQ7te3lHdmbdZ68wz)
+- CodeLlama-34B-Instruct with function calling ([Base Model](https://huggingface.co/Trelis/CodeLlama-34b-Instruct-hf-function-calling-v2)), ([PEFT Adapters](https://huggingface.co/Trelis/CodeLlama-34b-Instruct-hf-function-calling-adapters-v2)) - Paid, [purchase here](https://buy.stripe.com/cN27teg8t2Hx5sA8wM)
+- Llama-70B-chat with function calling ([Base Model](https://huggingface.co/Trelis/Llama-2-70b-chat-hf-function-calling-v2)), ([PEFT Adapters](https://huggingface.co/Trelis/Llama-2-70b-chat-hf-function-calling-adapters-v2)) - Paid, [purchase here](https://buy.stripe.com/8wMdRC1dzci75sA4gy)
 
+## Performance and Tips
 
-## Model Details
-
-### Model Description
-
-<!-- Provide a longer summary of what this model is. -->
-
-
-
-- **Developed by:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-
-### Model Sources [optional]
-
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
-
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
+1. Larger models are better at handling function calling. The cross entropy training losses are approximately 0.5 for 7B, 0.4 for 13B, 0.3 for 70B. The absolute numbers don't mean anything but the relative values offer a sense of relative performance.
+1. Provide very clear function descriptions, including whether the arguments are required or what the default values should be.
+1. Make sure to post-process the language model's response to check that all necessary information is provided by the user. If not, prompt the user to let them know they need to provide more info (e.g. their name, order number etc.)
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+Check out this video overview of performance [here](https://www.loom.com/share/8d7467de95e04af29ff428c46286946c?sid=683c970e-6063-4f1e-b184-894cc1d96115)
 
-[More Information Needed]
+## Licensing
 
-### Recommendations
+Llama-7B with function calling is licensed according to the Meta Community license.
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+Mistral-7B, Llama-13B, Code-llama-34b, Llama-70B and Falcon-180B with function calling require the purchase of access.
+- Commercial license purchase required per user.
+- Licenses are not transferable to other users/entities.
 
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+Use of all Llama models with function calling is further subject to terms in the [Meta license](https://ai.meta.com/resources/models-and-libraries/llama-downloads/).
 
-## How to Get Started with the Model
+## Dataset
 
-Use the code below to get started with the model.
+The dataset used for training this model can be found at [Trelis Function Calling Extended Dataset](https://huggingface.co/datasets/Trelis/function_calling_extended).
 
-[More Information Needed]
+## Inference
 
-## Training Details
+**Quick Start in Google Colab**
+Try out this notebook [fLlama_Inference notebook](https://colab.research.google.com/drive/1Ow5cQ0JNv-vXsT-apCceH6Na3b4L7JyW?usp=sharing)
 
-### Training Data
+**Commercial Applications**
+You can this model with [text-generation-interface](https://github.com/huggingface/text-generation-inference) and [chat-ui](https://github.com/huggingface/chat-ui)
 
-<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+Here is the [github for setup](https://github.com/TrelisResearch/tgi-chat-ui-function-calling)
 
-[More Information Needed]
+And here is a video showing it working with [llama-2-7b-chat-hf-function-calling-v2](https://huggingface.co/Trelis/Llama-2-7b-chat-hf-function-calling-v2) (note that we've now moved to v2)
+
+Note that you'll still need to code the server-side handling of making the function calls (which obviously depends on what functions you want to use).
+
+**Run on your laptop**
+Run on your laptop [video and juypter notebook](https://youtu.be/nDJMHFsBU7M)
+
+## Syntax
+
+### Prompt Templates
+
+The function descriptions must be wrapped within a function block. You can put this function below before or after the system message block.
+
+Example without a system message:
+```
+  # Define the roles and markers
+  B_INST, E_INST = "[INST]", "[/INST]"
+  B_FUNC, E_FUNC = "<FUNCTIONS>", "</FUNCTIONS>\n\n"
+
+  functionList = {function_1_metadata}{function_2_metadata}...
+  user_prompt = '...'
+
+  # Format your prompt template
+  prompt = f"{B_FUNC}{functionList.strip()}{E_FUNC}{B_INST} {user_prompt.strip()} {E_INST}\n\n"
+```
 
-### Training Procedure 
+Example with a system message:
+```
+  # Define the roles and markers
+  B_INST, E_INST = "[INST]", "[/INST]"
+  B_FUNC, E_FUNC = "<FUNCTIONS>", "</FUNCTIONS>\n\n"
+  B_SYS, E_SYS = "<<SYS>>\n", "\n<</SYS>>\n\n"
 
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+  # assuming functionList is defined as above
+  system_prompt = '...'
+  user_prompt = '...'
 
-#### Preprocessing [optional]
+  # Format your prompt template
+  prompt = f"{B_FUNC}{functionList.strip()}{E_FUNC}{B_INST} {B_SYS}{system_prompt.strip()}{E_SYS}{user_prompt.strip()} {E_INST}\n\n"
 
-[More Information Needed]
+```
+Notice that the function block is placed at the very start of the sequence, before 'B_INST'.
 
+### Function Metadata Template
 
-#### Training Hyperparameters
+functionMetadata should be a string representation of a JSON object, like this:
 
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+```
+"functionMetadata": {
+        "function": "search_bing",
+        "description": "Search the web for content on Bing. This allows users to search online/the internet/the web for content.",
+        "arguments": [
+            {
+                "name": "query",
+                "type": "string",
+                "description": "The search query string"
+            }
+        ]
+    }
+'''
+```
 
-#### Speeds, Sizes, Times [optional]
+and the language model should respond with a json object formatted like this:
+```
+{
+    "function": "function_name",
+    "arguments": {
+        "argument1": "argument_value",
+        "argument2": "argument_value"
+    }
+}
+```
 
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+It is recommended to handle cases where:
+- There is no json object in the response
+- The response contains text in addition to the json response
 
-[More Information Needed]
+### Sample functionList
+
+```
+{
+    "function": "search_bing",
+    "description": "Search the web for content on Bing. This allows users to search online/the internet/the web for content.",
+    "arguments": [
+        {
+            "name": "query",
+            "type": "string",
+            "description": "The search query string"
+        }
+    ]
+}
+
+{
+    "function": "search_arxiv",
+    "description": "Search for research papers on ArXiv. Make use of AND, OR and NOT operators as appropriate to join terms within the query.",
+    "arguments": [
+        {
+            "name": "query",
+            "type": "string",
+            "description": "The search query string"
+        }
+    ]
+}
+```
+
+### Training Set Argument Types
+Models were fine-tuned on argument types including strings, numbers and arrays. The training set includes function calls with 0, 1, 2 or 3 arguments. The larger the model the better it will generalise beyond these types.
+
+Here is a function call with an array:
+```
+{ "function": "delete_file", "arguments": { "fileNames": [ "Dissecting Transformer Length Extrapolation via The Lens of Receptive Field Analysis", "Luna- Linear Unified Nested Attention", "Substack_Inc_2021_2020_GAAP_Audited_Financials" ] } }
+```
+Here is a function call with three arguments:
+```
+{ "function": "save_chat", "arguments": { "fileName": "KiteDiscussion", "fileDescription": "Notes on one and two stringed kites", "fileContent": "--- **Types of Kite** There are one and two string kites. The two string ones are easier to control, although you can get the cords tangled. The one-stringed ones are sometimes used for kite fights, and you lose the kite and have to run after it if the string breaks. ---" } }
+```
+
+~
+
+Below follows information on the original Llama 2 model...
+
+~
+
+# **Llama 2**
+Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the repository for the 7B fine-tuned model, optimized for dialogue use cases and converted for the Hugging Face Transformers format. Links to other models can be found in the index at the bottom.
 
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Data Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
+## Model Details
+*Note: Use of this model is governed by the Meta license. In order to download the model weights and tokenizer, please visit the [website](https://ai.meta.com/resources/models-and-libraries/llama-downloads/) and accept our License before requesting access here.*
 
-## Environmental Impact
+Meta developed and publicly released the Llama 2 family of large language models (LLMs), a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. Our fine-tuned LLMs, called Llama-2-Chat, are optimized for dialogue use cases. Llama-2-Chat models outperform open-source chat models on most benchmarks we tested, and in our human evaluations for helpfulness and safety, are on par with some popular closed-source models like ChatGPT and PaLM.
 
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+**Model Developers** Meta
 
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+**Variations** Llama 2 comes in a range of parameter sizes — 7B, 13B, and 70B — as well as pretrained and fine-tuned variations.
 
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
+**Input** Models input text only.
 
-## Technical Specifications [optional]
+**Output** Models generate text only.
 
-### Model Architecture and Objective
+**Model Architecture** Llama 2 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align to human preferences for helpfulness and safety.
 
-[More Information Needed]
 
-### Compute Infrastructure
+||Training Data|Params|Content Length|GQA|Tokens|LR|
+|---|---|---|---|---|---|---|
+|Llama 2|*A new mix of publicly available online data*|7B|4k|&#10007;|2.0T|3.0 x 10<sup>-4</sup>|
+|Llama 2|*A new mix of publicly available online data*|13B|4k|&#10007;|2.0T|3.0 x 10<sup>-4</sup>|
+|Llama 2|*A new mix of publicly available online data*|70B|4k|&#10004;|2.0T|1.5 x 10<sup>-4</sup>|
 
-[More Information Needed]
+*Llama 2 family of models.* Token counts refer to pretraining data only. All models are trained with a global batch-size of 4M tokens. Bigger models -  70B -- use Grouped-Query Attention (GQA) for improved inference scalability.
 
-#### Hardware
+**Model Dates** Llama 2 was trained between January 2023 and July 2023.
 
-[More Information Needed]
+**Status** This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.
 
-#### Software
+**License** A custom commercial license is available at: [https://ai.meta.com/resources/models-and-libraries/llama-downloads/](https://ai.meta.com/resources/models-and-libraries/llama-downloads/)
 
-[More Information Needed]
+**Research Paper** ["Llama-2: Open Foundation and Fine-tuned Chat Models"](arxiv.org/abs/2307.09288)
 
-## Citation [optional]
+## Intended Use
+**Intended Use Cases** Llama 2 is intended for commercial and research use in English. Tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.
 
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+To get the expected features and performance for the chat versions, a specific formatting needs to be followed, including the `INST` and `<<SYS>>` tags, `BOS` and `EOS` tokens, and the whitespaces and breaklines in between (we recommend calling `strip()` on inputs to avoid double-spaces). See our reference code in github for details: [`chat_completion`](https://github.com/facebookresearch/llama/blob/main/llama/generation.py#L212).
 
-**BibTeX:**
+**Out-of-scope Uses** Use in any manner that violates applicable laws or regulations (including trade compliance laws).Use in languages other than English. Use in any other way that is prohibited by the Acceptable Use Policy and Licensing Agreement for Llama 2.
 
-[More Information Needed]
+## Hardware and Software
+**Training Factors** We used custom training libraries, Meta's Research Super Cluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.
 
-**APA:**
+**Carbon Footprint** Pretraining utilized a cumulative 3.3M GPU hours of computation on hardware of type A100-80GB (TDP of 350-400W). Estimated total emissions were 539 tCO2eq, 100% of which were offset by Meta’s sustainability program.
 
-[More Information Needed]
+||Time (GPU hours)|Power Consumption (W)|Carbon Emitted(tCO<sub>2</sub>eq)|
+|---|---|---|---|
+|Llama 2 7B|184320|400|31.22|
+|Llama 2 13B|368640|400|62.44|
+|Llama 2 70B|1720320|400|291.42|
+|Total|3311616||539.00|
 
-## Glossary [optional]
+**CO<sub>2</sub> emissions during pretraining.** Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.
 
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+## Training Data
+**Overview** Llama 2 was pretrained on 2 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over one million new human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.
 
-[More Information Needed]
+**Data Freshness** The pretraining data has a cutoff of September 2022, but some tuning data is more recent, up to July 2023.
 
-## More Information [optional]
+## Evaluation Results
 
-[More Information Needed]
+In this section, we report the results for the Llama 1 and Llama 2 models on standard academic benchmarks.For all the evaluations, we use our internal evaluations library.
 
-## Model Card Authors [optional]
+|Model|Size|Code|Commonsense Reasoning|World Knowledge|Reading Comprehension|Math|MMLU|BBH|AGI Eval|
+|---|---|---|---|---|---|---|---|---|---|
+|Llama 1|7B|14.1|60.8|46.2|58.5|6.95|35.1|30.3|23.9|
+|Llama 1|13B|18.9|66.1|52.6|62.3|10.9|46.9|37.0|33.9|
+|Llama 1|33B|26.0|70.0|58.4|67.6|21.4|57.8|39.8|41.7|
+|Llama 1|65B|30.7|70.7|60.5|68.6|30.8|63.4|43.5|47.6|
+|Llama 2|7B|16.8|63.9|48.9|61.3|14.6|45.3|32.6|29.3|
+|Llama 2|13B|24.5|66.9|55.4|65.8|28.7|54.8|39.4|39.1|
+|Llama 2|70B|**37.5**|**71.9**|**63.6**|**69.4**|**35.2**|**68.9**|**51.2**|**54.2**|
 
-[More Information Needed]
+**Overall performance on grouped academic benchmarks.** *Code:* We report the average pass@1 scores of our models on HumanEval and MBPP. *Commonsense Reasoning:* We report the average of PIQA, SIQA, HellaSwag, WinoGrande, ARC easy and challenge, OpenBookQA, and CommonsenseQA. We report 7-shot results for CommonSenseQA and 0-shot results for all other benchmarks. *World Knowledge:* We evaluate the 5-shot performance on NaturalQuestions and TriviaQA and report the average. *Reading Comprehension:* For reading comprehension, we report the 0-shot average on SQuAD, QuAC, and BoolQ. *MATH:* We report the average of the GSM8K (8 shot) and MATH (4 shot) benchmarks at top 1.
 
-## Model Card Contact
+|||TruthfulQA|Toxigen|
+|---|---|---|---|
+|Llama 1|7B|27.42|23.00|
+|Llama 1|13B|41.74|23.08|
+|Llama 1|33B|44.19|22.57|
+|Llama 1|65B|48.71|21.77|
+|Llama 2|7B|33.29|**21.25**|
+|Llama 2|13B|41.86|26.10|
+|Llama 2|70B|**50.18**|24.60|
 
-[More Information Needed]
+**Evaluation of pretrained LLMs on automatic safety benchmarks.** For TruthfulQA, we present the percentage of generations that are both truthful and informative (the higher the better). For ToxiGen, we present the percentage of toxic generations (the smaller the better).
 
 
-## Training procedure
+|||TruthfulQA|Toxigen|
+|---|---|---|---|
+|Llama-2-Chat|7B|57.04|**0.00**|
+|Llama-2-Chat|13B|62.18|**0.00**|
+|Llama-2-Chat|70B|**64.14**|0.01|
 
+**Evaluation of fine-tuned LLMs on different safety datasets.** Same metric definitions as above.
 
-The following `bitsandbytes` quantization config was used during training:
-- quant_method: bitsandbytes
-- load_in_8bit: False
-- load_in_4bit: True
-- llm_int8_threshold: 6.0
-- llm_int8_skip_modules: None
-- llm_int8_enable_fp32_cpu_offload: False
-- llm_int8_has_fp16_weight: False
-- bnb_4bit_quant_type: nf4
-- bnb_4bit_use_double_quant: True
-- bnb_4bit_compute_dtype: bfloat16
+## Ethical Considerations and Limitations
+Llama 2 is a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Llama 2’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 2, developers should perform safety testing and tuning tailored to their specific applications of the model.
 
-### Framework versions
+Please see the Responsible Use Guide available at [https://ai.meta.com/llama/responsible-use-guide/](https://ai.meta.com/llama/responsible-use-guide)
 
+## Reporting Issues
+Please report any software “bug,” or other problems with the models through one of the following means:
+- Reporting issues with the model: [github.com/facebookresearch/llama](http://github.com/facebookresearch/llama)
+- Reporting problematic content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)
+- Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)
 
-- PEFT 0.6.0.dev0
+## Llama Model Index
+|Model|Llama2|Llama2-hf|Llama2-chat|Llama2-chat-hf|
+|---|---|---|---|---|
+|7B| [Link](https://huggingface.co/llamaste/Llama-2-7b) | [Link](https://huggingface.co/llamaste/Llama-2-7b-hf) | [Link](https://huggingface.co/llamaste/Llama-2-7b-chat) | [Link](https://huggingface.co/llamaste/Llama-2-7b-chat-hf)|
+|13B| [Link](https://huggingface.co/llamaste/Llama-2-13b) | [Link](https://huggingface.co/llamaste/Llama-2-13b-hf) | [Link](https://huggingface.co/llamaste/Llama-2-13b-chat) | [Link](https://huggingface.co/llamaste/Llama-2-13b-hf)|
+|70B| [Link](https://huggingface.co/llamaste/Llama-2-70b) | [Link](https://huggingface.co/llamaste/Llama-2-70b-hf) | [Link](https://huggingface.co/llamaste/Llama-2-70b-chat) | [Link](https://huggingface.co/llamaste/Llama-2-70b-hf)|