tomasmcm/alma-7b 🔢📝 → 📝

▶️ 102 runs 📅 Nov 2023 ⚙️ Cog 0.8.6 🔗 GitHub 📄 Paper ⚖️ License
language-model llm machine-translation multilingual text-translation

About

Source: haoranxu/ALMA-7B ✦ Quant: TheBloke/ALMA-7B-AWQ ✦ ALMA (Advanced Language Model-based trAnslator) is an LLM-based translation model

Example Output

Prompt:

"Translate this from English to German:
English: Hi there, what's your name?
German: "

Output

‚Hey, was ist dein Name?

Performance Metrics

0.50s Prediction Time
213.36s Total Time
All Input Parameters 
{
  "top_k": 50,
  "top_p": 0.95,
  "prompt": "Translate this from English to German:\nEnglish: Hi there, what's your name?\nGerman: ",
  "temperature": 0.8,
  "max_new_tokens": 128,
  "presence_penalty": 1
}
Input Parameters
top_k Type: integerDefault: 50
The number of highest probability tokens to consider for generating the output. If > 0, only keep the top k tokens with highest probability (top-k filtering).
top_p Type: numberDefault: 0.95Range: 0.01 - 1
A probability threshold for generating the output. If < 1.0, only keep the top tokens with cumulative probability >= top_p (nucleus filtering). Nucleus filtering is described in Holtzman et al. (http://arxiv.org/abs/1904.09751).
prompt (required) Type: string
Text prompt to send to the model.
temperature Type: numberDefault: 0.8Range: 0.01 - 5
The value used to modulate the next token probabilities.
max_new_tokens Type: integerDefault: 128
The maximum number of tokens the model should generate as output.
presence_penalty Type: numberDefault: 1Range: 0.01 - 5
Presence penalty
Output Schema

Output

Type: string

Example Execution Logs 
Processed prompts:   0%|          | 0/1 [00:00<?, ?it/s]
Processed prompts: 100%|██████████| 1/1 [00:00<00:00,  2.07it/s]
Processed prompts: 100%|██████████| 1/1 [00:00<00:00,  2.07it/s]
Generated 11 tokens in 0.49060773849487305 seconds.
Version Details
Version ID
4e0b419245e5db8edc948dffe8d05d9327dce9ae6c9a764ea7b12e3c66f60b7c
Version Created
November 4, 2023
Run on Replicate →