Llama 2 13B Chat Hf is an open-source language model by meta-llama. Features: 13b LLM, VRAM: 26GB, Context: 4K, License: llama2, LLM Explorer Score: 0.34, ELO: 1078, Arc: 59, HellaSwag: 81.9, MMLU: 54.6, GSM8K: 15.2.
Llama 2 13B Chat Hf Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 2 13B Chat Hf Parameters and Internals
| Model Type | |
| Use Cases |
| Areas: | |
| Primary Use Cases: | | assistant-like chat, natural language generation tasks |
|
| Limitations: | | Use in languages other than English, Violations of laws or regulations |
|
| Considerations: | | Follow specific formatting for inputs |
|
|
| Additional Notes | | The fine-tuning data includes publicly available instruction datasets and human-annotated examples. |
|
| Training Details |
| Data Sources: | | publicly available datasets |
|
| Data Volume: | |
| Methodology: | | Supervised Fine-tuning and Reinforcement Learning with Human Feedback |
|
| Hardware Used: | | Meta's Research Super Cluster, third-party cloud compute |
|
| Model Architecture: | | auto-regressive language model with optimized transformer architecture |
|
|
| Input Output |
| Input Format: | |
| Accepted Modalities: | |
| Output Format: | |
|
| Release Notes |
| Version: | |
| Date: | |
| Notes: | | Llama 2 models ranging from 7 billion to 70 billion parameters released, optimized for dialogue and alignment with human preferences. |
|
|
|
Quantized Models of the Llama 2 13B Chat Hf
Best Alternatives to Llama 2 13B Chat Hf