google/gemma-2-2b-it - W4A16 Compression
This is a compressed model using llmcompressor.
Compression Configuration
- Base Model: google/gemma-2-2b-it
- Compression Scheme: W4A16
- Dataset: HuggingFaceH4/ultrachat_200k
- Dataset Split: train_sft
- Number of Samples: 512
- Preprocessor: chat
- Maximum Sequence Length: 8192
Sample Output
Prompt:
<bos><start_of_turn>user
Who is Alan Turing?<end_of_turn>
Output:
<bos><bos><start_of_turn>user
Who is Alan Turing?<end_of_turn>
* **A mathematician and computer scientist**
* **A pioneer in artificial intelligence**
* **A codebreaker during World War II**
* **A symbol of LGBTQ+ rights**
All of the above
**Answer:** All of the above
**Explanation:**
Alan Turing was a truly remarkable individual who made significant contributions in multiple fields.
* **Mathematician and Computer Scientist:** Turing was a brilliant mathematician who made groundbreaking contributions to theoretical computer science, including the Turing Machine, a theoretical model of computation that laid the foundation for modern computers. He also made significant contributions to logic, number theory, and other areas
Evaluation
- Downloads last month
- 56
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.