tomasmcm/evolved-seeker-1.3b 📝🔢 → 📝
About
Source: TokenBender/evolvedSeeker_1_3 ✦ Quant: TheBloke/evolvedSeeker_1_3-AWQ ✦ A fine-tuned version of deepseek-ai/deepseek-coder-1.3b-base on 50k instructions for 3 epochs
Example Output
Prompt:
"<|im_start|>system
You are a helpful coding assistant.<|im_end|>
<|im_start|>user
write a javascript program to reverse letters in each word in a sentence without reversing order of words in the sentence.<|im_end|>
<|im_start|>assistant"
Output
Here is a simple JavaScript program that achieves this:
function reverseWordsInSentence(sentence) {
return sentence.split(' ').map(word => word.split('').reverse().join('')).join(' ');
}
console.log(reverseWordsInSentence("Hello world")); // Outputs: "olleH dlrow"
This function works by first splitting the sentence into an array of words. Then, for each word, it splits the word into an array of characters, reverses that array, then joins it back together into a word. Finally, it joins all the words back together into a sentence.
Performance Metrics
4.89s
Prediction Time
4.91s
Total Time
All Input Parameters
{
"stop": "<|im_end|>",
"top_k": 40,
"top_p": 0.95,
"prompt": "<|im_start|>system\nYou are a helpful coding assistant.<|im_end|>\n<|im_start|>user\nwrite a javascript program to reverse letters in each word in a sentence without reversing order of words in the sentence.<|im_end|>\n<|im_start|>assistant",
"max_tokens": 512,
"temperature": 0.7,
"presence_penalty": 0,
"frequency_penalty": 0
}
Input Parameters
- stop
- List of strings that stop the generation when they are generated. The returned output will not contain the stop strings.
- top_k
- Integer that controls the number of top tokens to consider. Set to -1 to consider all tokens.
- top_p
- Float that controls the cumulative probability of the top tokens to consider. Must be in (0, 1]. Set to 1 to consider all tokens.
- prompt (required)
- Text prompt to send to the model.
- max_tokens
- Maximum number of tokens to generate per output sequence.
- temperature
- Float that controls the randomness of the sampling. Lower values make the model more deterministic, while higher values make the model more random. Zero means greedy sampling.
- presence_penalty
- Float that penalizes new tokens based on whether they appear in the generated text so far. Values > 0 encourage the model to use new tokens, while values < 0 encourage the model to repeat tokens.
- frequency_penalty
- Float that penalizes new tokens based on their frequency in the generated text so far. Values > 0 encourage the model to use new tokens, while values < 0 encourage the model to repeat tokens.
Output Schema
Output
Example Execution Logs
Processed prompts: 0%| | 0/1 [00:00<?, ?it/s] Processed prompts: 100%|██████████| 1/1 [00:04<00:00, 4.88s/it] Processed prompts: 100%|██████████| 1/1 [00:04<00:00, 4.88s/it] Generated 158 tokens in 4.881830453872681 seconds.
Version Details
- Version ID
04492f3607a921344a8173a727224dc1ea22518ea9d40b8231296afe29fb972a- Version Created
- November 28, 2023