ydideh810/cosmo-speak 🔢✓📝 → 📝

▶️ 17 runs 📅 Jul 2024 ⚙️ Cog 0.8.6

About

A chat-bot that specialises in Space/Aeronautics knowledge.

Example Output

Prompt:

"How do Sun and Earth sensors boost spacecraft navigation and mission success?"

Output

Sun and Earth sensors play an important role in ensuring the accuracy of navigation systems and the success of spacecraft missions. Here’s how:
Accurate Navigation: Sun sensors are used to accurately determine the orientation of a spacecraft with respect to the sun. This information is critical for navigating through space, as it helps keep a spacecraft on course and avoid collisions with other objects in orbit. Sun sensors can also be used to determine the position of a spacecraft relative to its surroundings, which is essential for mission planning and execution.
Asteroid Probe Mission

Performance Metrics

13.05s Prediction Time

160.36s Total Time

All Input Parameters

{
  "debug": false,
  "top_k": 50,
  "top_p": 0.9,
  "prompt": "How do Sun and Earth sensors boost spacecraft navigation and mission success?",
  "temperature": 0.75,
  "max_new_tokens": 128,
  "min_new_tokens": -1
}

Input Parameters

seed Type: integer: Random seed. Leave blank to randomize the seed
debug Type: booleanDefault: false: provide debugging output in logs
top_k Type: integerDefault: 50Range: 0 - ∞: When decoding text, samples from the top k most likely tokens; lower to ignore less likely tokens
top_p Type: numberDefault: 0.9Range: 0 - 1: When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens
prompt (required) Type: string: Prompt to send to the model.
temperature Type: numberDefault: 0.75Range: 0.01 - 5: Adjusts randomness of outputs, greater than 1 is random and 0 is deterministic, 0.75 is a good starting value.
max_new_tokens Type: integerDefault: 128Range: 1 - ∞: Maximum number of tokens to generate. A word is generally 2-3 tokens
min_new_tokens Type: integerDefault: -1Range: -1 - ∞: Minimum number of tokens to generate. To disable, set to -1. A word is generally 2-3 tokens.
stop_sequences Type: string: A comma-separated list of sequences to stop generation at. For example, '<end>,<stop>' will stop generation at the first instance of 'end' or '<stop>'.
replicate_weights Type: string: Path to fine-tuned weights produced by a Replicate fine-tune job.

Output Schema

Output

Type: array • Items Type: string

Example Execution Logs

Your formatted prompt is:
How do Sun and Earth sensors boost spacecraft navigation and mission success?
previous weights were different, switching to https://replicate.delivery/pbxt/rSIuuP8T2eUOJarWa0ZDrY3orSuayx7xBIJjIUmqll9nJxmJA/training_output.zip
Downloading peft weights
using https://replicate.delivery/pbxt/rSIuuP8T2eUOJarWa0ZDrY3orSuayx7xBIJjIUmqll9nJxmJA/training_output.zip instead of https://replicate.delivery/pbxt/rSIuuP8T2eUOJarWa0ZDrY3orSuayx7xBIJjIUmqll9nJxmJA/training_output.zip
Downloaded training_output.zip as 10 824 kB chunks in 0.3842 with 0 retries
Downloaded peft weights in 0.384
Unzipped peft weights in 0.017
Initialized peft model in 0.008
Overall initialize_peft took 9.953
Exllama: False
INFO 07-30 20:11:53 async_llm_engine.py:371] Received request 0: prompt: 'How do Sun and Earth sensors boost spacecraft navigation and mission success?', sampling params: SamplingParams(n=1, best_of=1, presence_penalty=0.0, frequency_penalty=1.0, temperature=0.75, top_p=0.9, top_k=50, use_beam_search=False, length_penalty=1.0, early_stopping=False, stop=['</s>'], ignore_eos=False, max_tokens=128, logprobs=None, skip_special_tokens=True), prompt token ids: None.
INFO 07-30 20:11:53 llm_engine.py:631] Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 0.0 tokens/s, Running: 1 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 0.0%, CPU KV cache usage: 0.0%
INFO 07-30 20:11:56 async_llm_engine.py:111] Finished request 0.
hostname: model-hp-73001d654114dad81ec65da3b834e2f6-888dc6d68-m2gtq

Version Details

Version ID: fd8ed7161c14133273cfa8fdc60a10143a0107a7d4adeb495ba98f22257d965e
Version Created: July 30, 2024

Run on Replicate →