nateraw/samsum-llama-2-13b 🔢✓📝 → 📝
About
Example Output
"
[INST] <
Use the Input to provide a summary of a conversation.
<
Input:
Nate: Remember when Marc used to be so carefree and fun?
Jenna: Oh definitely, he was always the life of the party.
Nate: Lately, it feels like he's a different person.
Jenna: In what way?
Nate: He's more serious now, always working and never has time for us.
Nate: I tried inviting him to hang out several times, but he's always too busy.
Jenna: Maybe he's just going through a phase?
Nate: I don't know, it's been months.
Nate: It's like he's lost his spark or something.
Jenna: I noticed that too. Last time I saw him, he seemed distant.
Nate: I just hope he's okay.
Jenna: Maybe we should talk to him, see if something's bothering him?
Nate: Yeah, I think that's a good idea. I miss the old Marc.
Summary:
"Output
Performance Metrics
All Input Parameters
{ "debug": false, "top_k": 50, "top_p": 0.95, "prompt": "[INST] <<SYS>>\nUse the Input to provide a summary of a conversation.\n<</SYS>>\n\nInput:\nNate: Remember when Marc used to be so carefree and fun?\nJenna: Oh definitely, he was always the life of the party.\nNate: Lately, it feels like he's a different person.\nJenna: In what way?\nNate: He's more serious now, always working and never has time for us.\nNate: I tried inviting him to hang out several times, but he's always too busy.\nJenna: Maybe he's just going through a phase?\nNate: I don't know, it's been months.\nNate: It's like he's lost his spark or something.\nJenna: I noticed that too. Last time I saw him, he seemed distant.\nNate: I just hope he's okay.\nJenna: Maybe we should talk to him, see if something's bothering him?\nNate: Yeah, I think that's a good idea. I miss the old Marc.\n\nSummary: ", "temperature": 0.75, "max_new_tokens": 256, "min_new_tokens": -1, "stop_sequences": "</s>" }
Input Parameters
- seed
- Random seed. Leave blank to randomize the seed
- debug
- provide debugging output in logs
- top_k
- When decoding text, samples from the top k most likely tokens; lower to ignore less likely tokens
- top_p
- When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens
- prompt (required)
- Prompt to send to the model.
- temperature
- Adjusts randomness of outputs, greater than 1 is random and 0 is deterministic, 0.75 is a good starting value.
- max_new_tokens
- Maximum number of tokens to generate. A word is generally 2-3 tokens
- min_new_tokens
- Minimum number of tokens to generate. To disable, set to -1. A word is generally 2-3 tokens.
- stop_sequences
- 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
- Path to fine-tuned weights produced by a Replicate fine-tune job.
Output Schema
Output
Example Execution Logs
Your formatted prompt is: [INST] <<SYS>> Use the Input to provide a summary of a conversation. <</SYS>> Input: Nate: Remember when Marc used to be so carefree and fun? Jenna: Oh definitely, he was always the life of the party. Nate: Lately, it feels like he's a different person. Jenna: In what way? Nate: He's more serious now, always working and never has time for us. Nate: I tried inviting him to hang out several times, but he's always too busy. Jenna: Maybe he's just going through a phase? Nate: I don't know, it's been months. Nate: It's like he's lost his spark or something. Jenna: I noticed that too. Last time I saw him, he seemed distant. Nate: I just hope he's okay. Jenna: Maybe we should talk to him, see if something's bothering him? Nate: Yeah, I think that's a good idea. I miss the old Marc. Summary:
Version Details
- Version ID
d7efe6128fb634f45488349595179a9a17cbfa60815466074d93b932c4837192
- Version Created
- September 1, 2023