Model Card on HF 🤗: https://huggingface.co/OpenBuddy/openbuddy-openllama-13b-v7-fp16
Openbuddy Openllama 13B V7 Fp16 Benchmarks
ARC: 47.61 vs 96.7 (so35)-50.8%
HellaSwag: 72.24 vs 95.3 (gpt4)-24.2%
MMLU: 47.74 vs 88.3 (so35)-45.9%
TruthfulQA: 48.73 vs 59 (gpt4)-17.4%
WinoGrande: 69.69 vs 87.5 (gpt4)-20.4%
GSM8K: 9.86 vs 96.4 (so35)-89.8%
LLME Score: 0.14019
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)
Openbuddy Openllama 13B V7 Fp16 Parameters and Internals
| LLM Name | Openbuddy Openllama 13B V7 Fp16 |
| Repository 🤗 | https://huggingface.co/OpenBuddy/openbuddy-openllama-13b-v7-fp16 |
| Model Size | 13b |
| Required VRAM | 26.2 GB |
| Updated | 2025-09-23 |
| Maintainer | OpenBuddy |
| Model Type | llama |
| Model Files | |
| Quantization Type | fp16 |
| Model Architecture | LlamaForCausalLM |
| License | apache-2.0 |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.30.2 |
| Tokenizer Class | LlamaTokenizer |
| Beginning of Sentence Token | <s> |
| End of Sentence Token | </s> |
| Unk Token | <unk> |
| Vocabulary Size | 38656 |
| Torch Data Type | float16 |
Best Alternatives to Openbuddy Openllama 13B V7 Fp16
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llama13b 32K Illumeet Finetune | 32K / 26 GB | 9 | 0 |
| ...Maid V3 13B 32K 6.0bpw H6 EXL2 | 32K / 10 GB | 7 | 1 |
| ...Maid V3 13B 32K 8.0bpw H8 EXL2 | 32K / 13.2 GB | 7 | 1 |
| WhiteRabbitNeo 13B V1 | 16K / 26 GB | 2649 | 429 |
| CodeLlama 13B Python Fp16 | 16K / 26 GB | 2833 | 25 |
| CodeLlama 13B Instruct Fp16 | 16K / 26 GB | 2847 | 28 |
| ...Llama 13B Instruct Hf 4bit MLX | 16K / 7.8 GB | 1196 | 2 |
| CodeLlama 13B Fp16 | 16K / 26 GB | 7 | 66 |
| Airophin 13B Pntk 16K Fp16 | 16K / 26 GB | 1737 | 4 |
| Codellama 13B Bnb 4bit | 16K / 7.2 GB | 20 | 5 |
Note: green Score (e.g. "73.2") means that the model is better than OpenBuddy/openbuddy-openllama-13b-v7-fp16 .
Rank the Openbuddy Openllama 13B V7 Fp16 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? 51536 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124