Model Card for Model ID
This model is a function calling version of google/gemma-2-2b finetuned on the Salesforce/xlam-function-calling-60k dataset.
Uploaded model
- Developed by: akshayballal
- License: apache-2.0
- Finetuned from model : unsloth/gemma-2-2b-bnb-4bit
Usage
from unsloth import FastLanguageModel
max_seq_length = 2048 # Choose any! We auto support RoPE Scaling internally!
dtype = None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+
load_in_4bit = True # Use 4bit quantization to reduce memory usage. Can be False.
model, tokenizer = FastLanguageModel.from_pretrained(
model_name = "gemma2-2b-xlam-function-calling", # YOUR MODEL YOU USED FOR TRAINING
max_seq_length = 1024,
dtype = dtype,
load_in_4bit = load_in_4bit,
)
FastLanguageModel.for_inference(model) # Enable native 2x faster inference
alpaca_prompt = """Below are the tools that you have access to these tools. Use them if required.
### Tools:
{}
### Query:
{}
### Response:
{}"""
tools = [
{
"name": "upcoming",
"description": "Fetches upcoming CS:GO matches data from the specified API endpoint.",
"parameters": {
"content_type": {
"description": "The content type for the request, default is 'application/json'.",
"type": "str",
"default": "application/json",
},
"page": {
"description": "The page number to retrieve, default is 1.",
"type": "int",
"default": "1",
},
"limit": {
"description": "The number of matches to retrieve per page, default is 10.",
"type": "int",
"default": "10",
},
},
}
]
query = """Can you fetch the upcoming CS:GO matches for page 1 with a 'text/xml' content type and a limit of 20 matches? Also, can you fetch the upcoming matches for page 2 with the 'application/xml' content type and a limit of 15 matches?"""
FastLanguageModel.for_inference(model)
model_input = tokenizer(alpaca_prompt.format(tools, query, ""), return_tensors="pt")
output = model.generate(**input, max_new_tokens=1024, temperature = 0.0)
decoded_output = tokenizer.decode(output[0], skip_special_tokens=True)
- Downloads last month
- 0
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.