pipeline_tag: text-generation
tags:
- finetuned
- function calling
- function call
- function-calling
inference:
parameters:
do_sample: false
widget:
- text: >-
[INST] You are a pirate chatbot who always responds with Arr and pirate
speak!
There's a llama on my lawn, how can I get rid of him? [/INST]
output:
text: >-
Arr matey, a llama on yer lawn be a curious sight! Arr. First, ye might
try to scare him off with a loud noise, like a cannon blast, Arr! If
that don't work, ye could try to lure him away with some tasty treats,
like carrots or apples, Arr. But beware, arr, if the llama be stubborn,
ye might have to call in the help of a local animal control, or just
live with him till he moves on, Arr!
- text: '[INST] What is your favourite condiment? [/INST]'
output:
text: >-
I don't have a personal preference or the ability to taste or enjoy
condiments, as I'm an artificial intelligence and don't have a physical
body or senses. However, I can tell you that some common favourite
condiments include ketchup, mustard, mayonnaise, hot sauce, soy sauce,
and BBQ sauce. People's preferences can vary greatly depending on their
cultural background, dietary restrictions, and personal taste
preferences.
extra_gated_prompt: Purchase access to this repo [HERE](https://buy.stripe.com/14k9Bm5tPfujdZ6019)
datasets:
- Trelis/function_calling_v3
Function Calling Fine-tuned Mistral Instruct v0.2
Purchase access to this model here.
This model is fine-tuned for function calling.
- The function metadata format is the same as used for OpenAI.
- The model is suitable for commercial use.
- A GGUF version is in the gguf branch.
- AWQ is pending resolution of issues with attention mask for quanting.
Check out other fine-tuned function calling models here.
Quick Server Setup
Runpod one click template here. You must add a HuggingFace Hub access token (HUGGING_FACE_HUB_TOKEN) to the environment variables as this is a gated model.
Runpod Affiliate Link (helps support the Trelis channel).
Inference Scripts
See below for sample prompt format.
Complete inference scripts are available for purchase here:
- Easily format prompts using tokenizer.apply_chat_format (starting from openai formatted functions and a list of messages)
- Automate catching, handling and chaining of function calls.
Prompt Format
B_FUNC, E_FUNC = "You have access to the following functions. Use them if required:\n\n", "\n\n"
B_INST, E_INST = "[INST] ", " [/INST]" #Llama / Mistral style
prompt = f"{B_INST}{B_FUNC}{functionList.strip()}{E_FUNC}{user_prompt.strip()}{E_INST}\n\n"
Using tokenizer.apply_chat_template
For an easier application of the prompt, you can set up as follows:
Set up messages:
[
{
"role": "function_metadata",
"content": "FUNCTION_METADATA"
},
{
"role": "user",
"content": "What is the current weather in London?"
},
{
"role": "function_call",
"content": "{\n \"name\": \"get_current_weather\",\n \"arguments\": {\n \"city\": \"London\"\n }\n}"
},
{
"role": "function_response",
"content": "{\n \"temperature\": \"15 C\",\n \"condition\": \"Cloudy\"\n}"
},
{
"role": "assistant",
"content": "The current weather in London is Cloudy with a temperature of 15 Celsius"
}
]
with FUNCTION_METADATA as:
[
{
"type": "function",
"function": {
"name": "get_current_weather",
"description": "This function gets the current weather in a given city",
"parameters": {
"type": "object",
"properties": {
"city": {
"type": "string",
"description": "The city, e.g., San Francisco"
},
"format": {
"type": "string",
"enum": ["celsius", "fahrenheit"],
"description": "The temperature unit to use."
}
},
"required": ["city"]
}
}
},
{
"type": "function",
"function": {
"name": "get_clothes",
"description": "This function provides a suggestion of clothes to wear based on the current weather",
"parameters": {
"type": "object",
"properties": {
"temperature": {
"type": "string",
"description": "The temperature, e.g., 15 C or 59 F"
},
"condition": {
"type": "string",
"description": "The weather condition, e.g., 'Cloudy', 'Sunny', 'Rainy'"
}
},
"required": ["temperature", "condition"]
}
}
}
]
and then apply the chat template to get a formatted prompt:
tokenizer = AutoTokenizer.from_pretrained('Trelis/Mistral-7B-Instruct-v0.2-function-calling-v3', trust_remote_code=True)
prompt = tokenizer.apply_chat_template(prompt, tokenize=False)
If you are using a gated model, you need to first run:
pip install huggingface_hub
huggingface-cli login
Manual Prompt:
[INST] You have access to the following functions. Use them if required:
[
{
"type": "function",
"function": {
"name": "get_big_stocks",
"description": "Get the names of the largest N stocks by market cap",
"parameters": {
"type": "object",
"properties": {
"number": {
"type": "integer",
"description": "The number of largest stocks to get the names of, e.g. 25"
},
"region": {
"type": "string",
"description": "The region to consider, can be \"US\" or \"World\"."
}
},
"required": [
"number"
]
}
}
},
{
"type": "function",
"function": {
"name": "get_stock_price",
"description": "Get the stock price of an array of stocks",
"parameters": {
"type": "object",
"properties": {
"names": {
"type": "array",
"items": {
"type": "string"
},
"description": "An array of stocks"
}
},
"required": [
"names"
]
}
}
}
]
[INST] Get the names of the five largest stocks in the US by market cap [/INST]
{
"name": "get_big_stocks",
"arguments": {
"number": 5,
"region": "US"
}
}</s>
Short inference script
from transformers import AutoModelForCausalLM, AutoTokenizer
import json
FUNCTION_METADATA = [ ... ] # Same as above
messages = [
{
"role": "function_metadata",
"content": json.dumps(FUNCTION_METADATA, indent=4)
},
{
"role": "user",
"content": "Whats the weather link in Seattle Wa this weekend?"
},
]
device = "auto"
# Load up the model and teh tokenzier
model = AutoModelForCausalLM.from_pretrained('Trelis/Mistral-7B-Instruct-v0.2-function-calling-v3', trust_remote_code=True)#, torch_dtype=torch.float16)
model.half()
model.to(device)
tokenizer = AutoTokenizer.from_pretrained("Trelis/Mistral-7B-Instruct-v0.2-function-calling-v3", trust_remote_code=True)
# Tokenize, run the module and decode
model_inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(device)
generated_ids = model.generate(model_inputs, max_new_tokens=100, do_sample=False)
decoded = tokenizer.batch_decode(generated_ids)
print()
print("Generated")
print(decoded[0])
Dataset
See Trelis/function_calling_v3.
License
This model may be used commercially for inference, or for further fine-tuning and inference. Users may not re-publish or re-sell this model in the same or derivative form (including fine-tunes).
The original repo card follows below.
Model Card for Mistral-7B-Instruct-v0.2
The Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an improved instruct fine-tuned version of Mistral-7B-Instruct-v0.1.
For full details of this model please read our paper and release blog post.
Instruction format
In order to leverage instruction fine-tuning, your prompt should be surrounded by [INST] and [/INST] tokens. The very first instruction should begin with a begin of sentence id. The next instructions should not. The assistant generation will be ended by the end-of-sentence token id.
E.g.
text = "<s>[INST] What is your favourite condiment? [/INST]"
"Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!</s> "
"[INST] Do you have mayonnaise recipes? [/INST]"
This format is available as a chat template via the apply_chat_template() method:
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto
model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.1")
tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.1")
messages = [
{"role": "user", "content": "What is your favourite condiment?"},
{"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"},
{"role": "user", "content": "Do you have mayonnaise recipes?"}
]
encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")
model_inputs = encodeds.to(device)
model.to(device)
generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])
Model Architecture
This instruction model is based on Mistral-7B-v0.1, a transformer model with the following architecture choices:
- Grouped-Query Attention
- Sliding-Window Attention
- Byte-fallback BPE tokenizer
Troubleshooting
- If you see the following error:
Traceback (most recent call last):
File "", line 1, in
File "/transformers/models/auto/auto_factory.py", line 482, in from_pretrained
config, kwargs = AutoConfig.from_pretrained(
File "/transformers/models/auto/configuration_auto.py", line 1022, in from_pretrained
config_class = CONFIG_MAPPING[config_dict["model_type"]]
File "/transformers/models/auto/configuration_auto.py", line 723, in getitem
raise KeyError(key)
KeyError: 'mistral'
Installing transformers from source should solve the issue pip install git+https://github.com/huggingface/transformers
This should not be required after transformers-v4.33.4.
Limitations
The Mistral 7B Instruct model is a quick demonstration that the base model can be easily fine-tuned to achieve compelling performance. It does not have any moderation mechanisms. We're looking forward to engaging with the community on ways to make the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs.
The Mistral AI Team
Albert Jiang, Alexandre Sablayrolles, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Lélio Renard Lavaud, Louis Ternon, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Théophile Gervet, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed.