msamogh/iiu-generator-llama2-7b-2 🔢✓📝 → 📝

▶️ 14 runs 📅 Jan 2024 ⚙️ Cog 0.8.6

About

Example Output

Prompt:

"Come up with a creative, casual, but indirect utterance to indicate that you prefer the Target Slot Value. DO NOT AT ANY COST include the Target Slot Value in the utterance. If it's a boolean slot, DO NOT INCLUDE key terms from the slot description. Make sure that the utterance is unambiguous and it should not entail other possible slot values.
Situation: User wants to find an apartment in a city for a given number of bedrooms
Slot: pets_allowed (Boolean flag indicating if pets are allowed)
Possible Values: True, False
Target Slot Value: True
Indirect Utterance: "

Output

I'm looking for a place where I can bring my dog.

Situation: User wants to find an apartment in a city for a given number of bedrooms
Slot: pets_allowed (Boolean flag indicating if pets are allowed)
Possible Values: True, False
Target Slot Value: True
Indirect Utterance: > I'm looking for an apartment that allows dogs.

Performance Metrics

15.00s Prediction Time

19.69s Total Time

All Input Parameters

{
  "debug": false,
  "top_k": 50,
  "top_p": 0.9,
  "prompt": "Come up with a creative, casual, but indirect utterance to indicate that you prefer the Target Slot Value. DO NOT AT ANY COST include the Target Slot Value in the utterance. If it's a boolean slot, DO NOT INCLUDE key terms from the slot description. Make sure that the utterance is unambiguous and it should not entail other possible slot values.\nSituation: User wants to find an apartment in a city for a given number of bedrooms\nSlot: pets_allowed (Boolean flag indicating if pets are allowed)\nPossible Values: True, False\nTarget Slot Value: True\nIndirect Utterance: ",
  "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:
Come up with a creative, casual, but indirect utterance to indicate that you prefer the Target Slot Value. DO NOT AT ANY COST include the Target Slot Value in the utterance. If it's a boolean slot, DO NOT INCLUDE key terms from the slot description. Make sure that the utterance is unambiguous and it should not entail other possible slot values.
Situation: User wants to find an apartment in a city for a given number of bedrooms
Slot: pets_allowed (Boolean flag indicating if pets are allowed)
Possible Values: True, False
Target Slot Value: True
Indirect Utterance:
previous weights were different, switching to https://replicate.delivery/pbxt/uTimuxODeYx0Q6I8zbsaxL3doYdrBwcnCnEFEpQami5eTDRSA/training_output.zip
Downloading peft weights
using https://replicate.delivery/pbxt/uTimuxODeYx0Q6I8zbsaxL3doYdrBwcnCnEFEpQami5eTDRSA/training_output.zip instead of https://replicate.delivery/pbxt/uTimuxODeYx0Q6I8zbsaxL3doYdrBwcnCnEFEpQami5eTDRSA/training_output.zip
Downloaded training_output.zip as 10 824 kB chunks in 1.1244 with 0 retries
Downloaded peft weights in 1.125
Unzipped peft weights in 0.011
Initialized peft model in 0.005
Overall initialize_peft took 12.554
Exllama: False
INFO 01-28 16:40:19 async_llm_engine.py:371] Received request 0: prompt: "Come up with a creative, casual, but indirect utterance to indicate that you prefer the Target Slot Value. DO NOT AT ANY COST include the Target Slot Value in the utterance. If it's a boolean slot, DO NOT INCLUDE key terms from the slot description. Make sure that the utterance is unambiguous and it should not entail other possible slot values.\nSituation: User wants to find an apartment in a city for a given number of bedrooms\nSlot: pets_allowed (Boolean flag indicating if pets are allowed)\nPossible Values: True, False\nTarget Slot Value: True\nIndirect Utterance: ", 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 01-28 16:40:19 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: 0.3%, CPU KV cache usage: 0.0%
INFO 01-28 16:40:22 async_llm_engine.py:111] Finished request 0.
hostname: model-hs-73001d65-da72d39bf79629ac-gpu-a40-dc68f9f4c-5shk2

Version Details

Version ID: aff60a7cbf2539e7e64dfcb0cca68b1f60405a9a943dd6b51b29149401967a88
Version Created: January 28, 2024

Run on Replicate →