tomasmcm/nexusraven-13b 🔢📝 → 📝

▶️ 56 runs 📅 Nov 2023 ⚙️ Cog 0.8.6 🔗 GitHub 📄 Paper ⚖️ License

code-generation commercial-use cybersecurity function-calling langchain-integration open-source python

About

Source: Nexusflow/NexusRaven-13B ✦ Quant: TheBloke/NexusRaven-13B-AWQ ✦ Surpassing the state-of-the-art in open-source function calling LLMs

Example Output

Prompt:

:
OPTION:
def hello_world(n : int)

"""
Prints hello world to the user.

Args:
n (int) : Number of times to print hello world.
"""

OPTION:
def hello_universe(n : int)

"""
Prints hello universe to the user.

Args:
n (int) : Number of times to print hello universe.
"""

User Query: Question: Please print hello world 10 times.

Please pick a function from the above options that best answers the user query and fill in the appropriate arguments.

Output

.
Thought: The purpose of the def hello_world(n : int) is to print hello world n times.
Initial Answer: hello_world(10)
Reflection: The function hello_world takes in one argument, n, which is an integer. The user has asked to print hello world 10 times.

The call provided is hello_world(10).

The call does not need to be improved.

This call can be run:
Fixed Call: hello_world(10)
Fixed Function Name: hello_world
Fixed Function Args: {"n" : 10}

Done.

Performance Metrics

2.69s Prediction Time

2.69s Total Time

All Input Parameters

{
  "top_k": 50,
  "top_p": 0.95,
  "prompt": "<human>:\nOPTION:\n<func_start>def hello_world(n : int)<func_end>\n<docstring_start>\n\"\"\"\nPrints hello world to the user.\n\nArgs:\nn (int) : Number of times to print hello world.\n\"\"\"\n<docstring_end>\n\nOPTION:\n<func_start>def hello_universe(n : int)<func_end>\n<docstring_start>\n\"\"\"\nPrints hello universe to the user.\n\nArgs:\nn (int) : Number of times to print hello universe.\n\"\"\"\n<docstring_end>\n\nUser Query: Question: Please print hello world 10 times.\n\nPlease pick a function from the above options that best answers the user query and fill in the appropriate arguments.<human_end>",
  "temperature": 0.8,
  "max_new_tokens": 256,
  "presence_penalty": 1
}

Input Parameters

top_k Type: integerDefault: 50: The number of highest probability tokens to consider for generating the output. If > 0, only keep the top k tokens with highest probability (top-k filtering).
top_p Type: numberDefault: 0.95Range: 0.01 - 1: A probability threshold for generating the output. If < 1.0, only keep the top tokens with cumulative probability >= top_p (nucleus filtering). Nucleus filtering is described in Holtzman et al. (http://arxiv.org/abs/1904.09751).
prompt (required) Type: string: Text prompt to send to the model.
temperature Type: numberDefault: 0.8Range: 0.01 - 5: The value used to modulate the next token probabilities.
max_new_tokens Type: integerDefault: 128: The maximum number of tokens the model should generate as output.
presence_penalty Type: numberDefault: 1Range: 0.01 - 5: Presence penalty

Output Schema

Output

Type: string

Example Execution Logs

Processed prompts:   0%|          | 0/1 [00:00<?, ?it/s]
Processed prompts: 100%|██████████| 1/1 [00:02<00:00,  2.56s/it]
Processed prompts: 100%|██████████| 1/1 [00:02<00:00,  2.56s/it]
Generated 143 tokens in 2.564486503601074 seconds.

Version Details

Version ID: c5079fb725e3a93ea7c445df6d1429673b406e49cf2205d7d79327f9e189aba9
Version Created: November 4, 2023

Run on Replicate →