Downloads · 30 days
25
3% of all-time downloads
tinyllama_PY-CODER-4bit-lora_4k-v12
Ramikan-BR/tinyllama_PY-CODER-4bit-lora_4k-v12
tinyllama_PY-CODER-4bit-lora_4k-v12 is a text generation model from Ramikan-BR. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
- Developed by: Ramikan-BR - License: apache-2.0 - Finetuned from model : Ramikan-BR/tinyllamaPY-CODER-4bit-lora4k-v11
All-time downloads
973
Public
Parameters
1.1B
4.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin2.2 GB · 50%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- llama
- Access
- Public
- Created
- May 16, 2024
- Updated
- May 27, 2024
- SHA
- 79c5410c
Try a prompt
Base models
Model card
From the Hugging Face model README
Avaliação de Modelo
Benchmarks
| Task | Model | Metric | Value |
|---|---|---|---|
| Winogrande | Ramikan-BR/tinyllama_PY-CODER-4bit-lora_4k-v12 | acc | 26.58% |
| TruthfulQA | Ramikan-BR/tinyllama_PY-CODER-4bit-lora_4k-v12 | mc2 | 40.77% |
| Hellaswag | Ramikan-BR/tinyllama_PY-CODER-4bit-lora_4k-v12 | acc | 35.16% |
| GSM8K | Ramikan-BR/tinyllama_PY-CODER-4bit-lora_4k-v12 | acc | 0.00% |
| ARC Challenge | Ramikan-BR/tinyllama_PY-CODER-4bit-lora_4k-v12 | acc | 24.32% |
Uploaded model
- Developed by: Ramikan-BR
- License: apache-2.0
- Finetuned from model : Ramikan-BR/tinyllama_PY-CODER-4bit-lora_4k-v11
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- License
- apache-2.0
- Languages
- en
- Created
- May 16, 2024
- Updated
- May 27, 2024