Model Card on HF 🤗: https://huggingface.co/NousResearch/CodeLlama-13b-hf
CodeLlama 13B Hf Benchmarks
ARC: 40.87 vs 96.7 (so35)-57.7%
HellaSwag: 63.35 vs 95.3 (gpt4)-33.5%
MMLU: 32.81 vs 88.3 (so35)-62.8%
TruthfulQA: 43.79 vs 59 (gpt4)-25.8%
WinoGrande: 67.17 vs 87.5 (gpt4)-23.2%
GSM8K: 12.13 vs 96.4 (so35)-87.4%
LLME Score: 0.203
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
CodeLlama 13B Hf Parameters and Internals
| LLM Name | CodeLlama 13B Hf |
| Repository 🤗 | https://huggingface.co/NousResearch/CodeLlama-13b-hf |
| Model Size | 13b |
| Required VRAM | 26 GB |
| Updated | 2024-12-21 |
| Maintainer | NousResearch |
| Model Type | llama |
| Model Files | |
| Generates Code | Yes |
| Model Architecture | LlamaForCausalLM |
| Context Length | 16384 |
| Model Max Length | 16384 |
| Transformers Version | 4.32.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Beginning of Sentence Token | <s> |
| End of Sentence Token | </s> |
| Unk Token | <unk> |
| Vocabulary Size | 32016 |
| Torch Data Type | float16 |
Best Alternatives to CodeLlama 13B Hf
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| CodeLlama 13B MORepair | 16K / 26 GB | 2650 | 2 |
| NexusRaven V2 13B | 16K / 26 GB | 3919 | 465 |
| CodeLlama 13B Instruct Hf | 16K / 26 GB | 16223 | 144 |
| CodeLlama 13B Hf | 16K / 26 GB | 13805 | 101 |
| CodeLlama 13B Instruct Hf | 16K / 26 GB | 993 | 18 |
| ...ma 13B Hf Truncated Embeddings | 16K / 52.3 GB | 17 | 0 |
| Tora Code 13B V1.0 | 16K / 26 GB | 1204 | 14 |
| CodeLlama 13B Python Hf | 16K / 26 GB | 1502 | 48 |
| Codellama 13B Oasst Sft V10 | 16K / 25.9 GB | 1941 | 66 |
| CodeLlama 13B Hf | 16K / 26 GB | 243 | 12 |
Note: green Score (e.g. "73.2") means that the model is better than NousResearch/CodeLlama-13b-hf .
Rank the CodeLlama 13B Hf Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 40066 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217