MaziyarPanahi/calme-2.4-rys-78b
This model is a fine-tuned version of the dnhkng/RYS-XLarge
, pushing the boundaries of natural language understanding and generation even further. My goal was to create a versatile and robust model that excels across a wide range of benchmarks and real-world applications.
Use Cases
This model is suitable for a wide range of applications, including but not limited to:
- Advanced question-answering systems
- Intelligent chatbots and virtual assistants
- Content generation and summarization
- Code generation and analysis
- Complex problem-solving and decision support
⚡ Quantized GGUF
Here are GGUF models thanks to @mradermacher:
- https://huggingface.co/mradermacher/calme-2.4-rys-78b-GGUF
- https://huggingface.co/mradermacher/calme-2.4-rys-78b-i1-GGUF
🏆 Open LLM Leaderboard Evaluation Results
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 50.26 |
IFEval (0-Shot) | 80.11 |
BBH (3-Shot) | 62.16 |
MATH Lvl 5 (4-Shot) | 37.69 |
GPQA (0-shot) | 20.36 |
MuSR (0-shot) | 34.57 |
MMLU-PRO (5-shot) | 66.69 |
Prompt Template
This model uses ChatML
prompt template:
<|im_start|>system
{System}
<|im_end|>
<|im_start|>user
{User}
<|im_end|>
<|im_start|>assistant
{Assistant}
How to use
# Use a pipeline as a high-level helper
from transformers import pipeline
messages = [
{"role": "user", "content": "Who are you?"},
]
pipe = pipeline("text-generation", model="MaziyarPanahi/calme-2.4-rys-78b")
pipe(messages)
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("MaziyarPanahi/calme-2.4-rys-78b")
model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/calme-2.4-rys-78b")
Ethical Considerations
As with any large language model, users should be aware of potential biases and limitations. We recommend implementing appropriate safeguards and human oversight when deploying this model in production environments.
- Downloads last month
- 944
Inference API (serverless) is not available, repository is disabled.
Model tree for MaziyarPanahi/calme-2.4-rys-78b
Datasets used to train MaziyarPanahi/calme-2.4-rys-78b
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard80.110
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard62.160
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard37.690
- acc_norm on GPQA (0-shot)Open LLM Leaderboard20.360
- acc_norm on MuSR (0-shot)Open LLM Leaderboard34.570
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard66.690