mav23 / llama-3-firefunction-v2-GGUF

huggingface.co
Total runs: 126
24-hour runs: 0
7-day runs: -31
30-day runs: 79
Model's Last Updated: November 12 2024

Introduction of llama-3-firefunction-v2-GGUF

Model Details of llama-3-firefunction-v2-GGUF

FireFunction V2: Fireworks Function Calling Model

Try on Fireworks | API Docs | Demo App | Discord

firefunction

FireFunction is a state-of-the-art function calling model with a commercially viable license. View detailed info in our announcement blog . Key info and highlights:

Comparison with other models:

  • Competitive with GPT-4o at function-calling, scoring 0.81 vs 0.80 on a medley of public evaluations
  • Trained on Llama 3 and retains Llama 3’s conversation and instruction-following capabilities, scoring 0.84 vs Llama 3’s 0.89 on MT bench
  • Significant quality improvements over FireFunction v1 across the broad range of metrics

General info:

🐾 Successor of the FireFunction model

🔆 Support of parallel function calling (unlike FireFunction v1) and good instruction following

💡 Hosted on the Fireworks platform at < 10% of the cost of GPT 4o and 2x the speed

Intended Use and Limitations
Supported usecases

The model was tuned to perfom well on a range of usecases including:

  • general instruction following
  • multi-turn chat mixing vanilla messages with function calls
  • single- and parallel function calling
  • up to 20 function specs supported at once
  • structured information extraction

The model has an 8k context window, like Llama 3

Out-of-Scope Use

The model was not optimized for the following use cases:

  • 100+ function specs
  • nested function calling
Metrics
Benchmark Firefunction v1 Firefunction v2 Llama 3 70b Instruct Gpt-4o
Gorilla simple 0.91 0.94 0.925 0.88
Gorilla multiple_function 0.92 0.91 0.86 0.91
Gorilla parallel_function 0 0.9 0.86 0.89
Gorilla parallel_multiple_function 0 0.8 0.615 0.72
Nexus parallel 0.38 0.53 0.3 0.47
Mtbench 0.73 0.84 0.89 0.93
Average 0.49 0.82 0.74 0.8
Example Usage

See documentation for more detail.

from transformers import AutoModelForCausalLM, AutoTokenizer
import json
from datetime import datetime

device = "cuda" # the device to load the model onto

model = AutoModelForCausalLM.from_pretrained("fireworks-ai/firefunction-v2", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("fireworks-ai/firefunction-v2")

function_spec = [
    {
        "name": "get_stock_price",
        "description": "Get the current stock price",
        "parameters": {
            "type": "object",
            "properties": {
                "symbol": {
                    "type": "string",
                    "description": "The stock symbol, e.g. AAPL, GOOG"
                }
            },
            "required": [
                "symbol"
            ]
        }
    },
    {
        "name": "check_word_anagram",
        "description": "Check if two words are anagrams of each other",
        "parameters": {
            "type": "object",
            "properties": {
                "word1": {
                    "type": "string",
                    "description": "The first word"
                },
                "word2": {
                    "type": "string",
                    "description": "The second word"
                }
            },
            "required": [
                "word1",
                "word2"
            ]
        }
    }
]
functions = json.dumps(function_spec, indent=4)

messages = [
    {'role': 'system', 'content': 'You are a helpful assistant with access to functions. Use them if required.'},
    {'role': 'user', 'content': 'Hi, can you tell me the current stock price of google and netflix?'}
]

now = datetime.now().strftime('%Y-%m-%d %H:%M:%S')

model_inputs = tokenizer.apply_chat_template(messages, functions=functions, datetime=now, return_tensors="pt").to(model.device)

generated_ids = model.generate(model_inputs, max_new_tokens=128)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])
Resources

Runs of mav23 llama-3-firefunction-v2-GGUF on huggingface.co

126
Total runs
0
24-hour runs
-2
3-day runs
-31
7-day runs
79
30-day runs

More Information About llama-3-firefunction-v2-GGUF huggingface.co Model

More llama-3-firefunction-v2-GGUF license Visit here:

https://choosealicense.com/licenses/llama3

llama-3-firefunction-v2-GGUF huggingface.co

llama-3-firefunction-v2-GGUF huggingface.co is an AI model on huggingface.co that provides llama-3-firefunction-v2-GGUF's model effect (), which can be used instantly with this mav23 llama-3-firefunction-v2-GGUF model. huggingface.co supports a free trial of the llama-3-firefunction-v2-GGUF model, and also provides paid use of the llama-3-firefunction-v2-GGUF. Support call llama-3-firefunction-v2-GGUF model through api, including Node.js, Python, http.

llama-3-firefunction-v2-GGUF huggingface.co Url

https://huggingface.co/mav23/llama-3-firefunction-v2-GGUF

mav23 llama-3-firefunction-v2-GGUF online free

llama-3-firefunction-v2-GGUF huggingface.co is an online trial and call api platform, which integrates llama-3-firefunction-v2-GGUF's modeling effects, including api services, and provides a free online trial of llama-3-firefunction-v2-GGUF, you can try llama-3-firefunction-v2-GGUF online for free by clicking the link below.

mav23 llama-3-firefunction-v2-GGUF online free url in huggingface.co:

https://huggingface.co/mav23/llama-3-firefunction-v2-GGUF

llama-3-firefunction-v2-GGUF install

llama-3-firefunction-v2-GGUF is an open source model from GitHub that offers a free installation service, and any user can find llama-3-firefunction-v2-GGUF on GitHub to install. At the same time, huggingface.co provides the effect of llama-3-firefunction-v2-GGUF install, users can directly use llama-3-firefunction-v2-GGUF installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

llama-3-firefunction-v2-GGUF install url in huggingface.co:

https://huggingface.co/mav23/llama-3-firefunction-v2-GGUF

Url of llama-3-firefunction-v2-GGUF

llama-3-firefunction-v2-GGUF huggingface.co Url

Provider of llama-3-firefunction-v2-GGUF huggingface.co

mav23
ORGANIZATIONS

Other API from mav23

huggingface.co

Total runs: 1.2K
Run Growth: 509
Growth Rate: 41.42%
Updated:October 31 2024
huggingface.co

Total runs: 861
Run Growth: 546
Growth Rate: 63.41%
Updated:November 30 2024
huggingface.co

Total runs: 585
Run Growth: 570
Growth Rate: 97.44%
Updated:November 21 2024
huggingface.co

Total runs: 213
Run Growth: 149
Growth Rate: 69.95%
Updated:November 19 2024
huggingface.co

Total runs: 159
Run Growth: 127
Growth Rate: 79.87%
Updated:October 28 2024
huggingface.co

Total runs: 148
Run Growth: 25
Growth Rate: 16.89%
Updated:December 04 2024
huggingface.co

Total runs: 133
Run Growth: 36
Growth Rate: 27.07%
Updated:December 04 2024
huggingface.co

Total runs: 115
Run Growth: 18
Growth Rate: 15.65%
Updated:November 30 2024
huggingface.co

Total runs: 114
Run Growth: -3.5K
Growth Rate: -3107.02%
Updated:October 13 2024