CodeLlama 34B Instruct Hf is an open-source language model by codellama. Features: 34b LLM, VRAM: 67.5GB, Context: 16K, License: llama2, Instruction-Based, Code Generating, LLM Explorer Score: 0.28, ELO: 1058, Arc: 40.8, HellaSwag: 35.7, MMLU: 39.7, GSM8K: 31, HumanEval: 50.8.
CodeLlama 34B Instruct Hf Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
CodeLlama 34B Instruct Hf Parameters and Internals
| Model Type | | text generation, code synthesis, instruction following |
|
| Use Cases |
| Areas: | |
| Applications: | | Code synthesis, Understanding tasks |
|
| Primary Use Cases: | | Code assistant, Code generation |
|
| Limitations: | | Use only in English, Potential production of inaccurate or objectionable responses |
|
|
| Supported Languages | | Programming Languages (Python), Human Languages (English) |
|
| Training Details |
| Methodology: | | Uses an optimized transformer architecture. Trained on similar data as Llama 2. |
|
| Training Time: | |
| Hardware Used: | |
| Model Architecture: | | Auto-regressive language model |
|
|
| Safety Evaluation |
| Methodologies: | | Safety evaluations include tests in English. |
|
| Ethical Considerations: | | Use in languages other than English may produce unpredictable results. |
|
|
| Responsible Ai Considerations |
| Accountability: | | Developers should perform safety testing tailored to specific applications. |
|
| Mitigation Strategies: | | Detailed in Responsible Use Guide. |
|
|
| Input Output |
| Input Format: | |
| Accepted Modalities: | |
| Output Format: | |
| Performance Tips: | | Ensure proper safety testing and tuning before deploying applications. |
|
|
Quantized Models of the CodeLlama 34B Instruct Hf
Best Alternatives to CodeLlama 34B Instruct Hf