Model Card on HF 🤗: https://huggingface.co/NousResearch/CodeLlama-7b-hf
CodeLlama 7B Hf Benchmarks
ARC: 39.85 vs 96.7 (so35)-58.8%
HellaSwag: 59.58 vs 95.3 (gpt4)-37.5%
MMLU: 30.47 vs 88.3 (so35)-65.5%
TruthfulQA: 38.62 vs 59 (gpt4)-34.5%
WinoGrande: 64.88 vs 87.5 (gpt4)-25.9%
GSM8K: 5.46 vs 96.4 (so35)-94.3%
LLME Score: 0.20975
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 7B Hf Parameters and Internals
| LLM Name | CodeLlama 7B Hf |
| Repository 🤗 | https://huggingface.co/NousResearch/CodeLlama-7b-hf |
| Model Size | 7b |
| Required VRAM | 13.5 GB |
| Updated | 2025-02-05 |
| 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 7B Hf
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Deepseek Coder 6.7B Instruct | 16K / 13.5 GB | 31321 | 374 |
| CodeLlama 7B Instruct Hf | 16K / 13.5 GB | 131801 | 224 |
| CodeLlama 7B Hf | 16K / 13.5 GB | 65816 | 344 |
| CodeLlama 7B Hf | 16K / 13.5 GB | 25150 | 79 |
| CodeLlama 7B Instruct Hf | 16K / 13.5 GB | 27572 | 37 |
| GetCode Slerp | 16K / 13.6 GB | 1229 | 1 |
| MathCoder2 CodeLlama 7B | 16K / 13.5 GB | 37 | 5 |
| Wizardllama 7B | 16K / 13.5 GB | 61 | 0 |
| CodeLlama 7B Python Hf | 16K / 13.5 GB | 5257 | 137 |
| Cdlm 7 Ko Nl2sql V1.0 | 16K / 13.5 GB | 2311 | 4 |
Note: green Score (e.g. "73.2") means that the model is better than NousResearch/CodeLlama-7b-hf .
Rank the CodeLlama 7B 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? 42577 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227