cjwbw/opencodeinterpreter-ds-6.7b 🔢📝✓ → 📝

▶️ 118 runs 📅 Feb 2024 ⚙️ Cog 0.9.4 🔗 GitHub 📄 Paper ⚖️ License
code-generation text-generation

About

OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement

Example Output

Prompt:

"Write a function to find the shared elements from the given two lists."

Output

def shared_elements(list1, list2):
# Initialize an empty list to store the shared elements
shared = []
# Iterate over the first list
for item in list1:
# If the item is in the second list and not already in the shared list, add it to the shared list
if item in list2 and item not in shared:
shared.append(item)
# Return the list of shared elements
return shared

Performance Metrics

6.07s Prediction Time
284.25s Total Time
All Input Parameters
{
  "top_k": 50,
  "top_p": 1,
  "prompt": "Write a function to find the shared elements from the given two lists.",
  "do_sample": true,
  "temperature": 0.7,
  "max_new_tokens": 1024,
  "min_new_tokens": -1,
  "repetition_penalty": 1
}
Input Parameters
top_k Type: integerDefault: 50
When decoding text, samples from the top k most likely tokens; lower to ignore less likely tokens
top_p Type: numberDefault: 0.95Range: 0 - 1
When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens
prompt Type: stringDefault: Write a function to find the shared elements from the given two lists.
Prompt to send to the model.
do_sample Type: booleanDefault: true
Use sampling strategy if set to True
temperature Type: numberDefault: 0.7Range: 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: 1024Range: 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.
repetition_penalty Type: numberDefault: 1Range: 0 - ∞
A parameter that controls how repetitive text can be. Lower means more repetitive, while higher means less repetitive. Set to 1.0 to disable.
Output Schema

Output

Type: arrayItems Type: string

Version Details
Version ID
0fe73dd8f7a92441c1d6a6118d95c4a462879bd071eacb94c37ba6405f8ea1fb
Version Created
February 25, 2024
Run on Replicate →