Base model:adapter:meta-llama/... Base model:meta-llama/llama-3.... Conversational Dataset:bjoernp/ultrachat de Dataset:leolm/german poems Dataset:leolm/german songs Dataset:leolm/openschnabeltier Dataset:mayflowergmbh/airoboro... Dataset:mayflowergmbh/alpaca-g... Dataset:mayflowergmbh/booksum ... Dataset:mayflowergmbh/dolly-15... Dataset:mayflowergmbh/dolphin ... Dataset:mayflowergmbh/evol-ins... Dataset:mayflowergmbh/intel or... Dataset:mayflowergmbh/oasst de Dataset:mayflowergmbh/openschn... Dataset:mayflowergmbh/ultra-ch... De En Instruct Llama Llama-factory Lora Peft Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/Nekochu/Llama-3.1-8B-German-ORPO
Llama 3.1 8B German ORPO Benchmarks
MMLU Pro: 26.59
GPQA: 8.84
MUSR: 16.86
BBH: 29.42
IFEval: 46.11 vs 88 (so35)-47.6%
MATH Lvl 5: 11.71
LLME Score: 0.27902
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)
Llama 3.1 8B German ORPO Parameters and Internals
| LLM Name | Llama 3.1 8B German ORPO |
| Repository 🤗 | https://huggingface.co/Nekochu/Llama-3.1-8B-German-ORPO |
| Model Name | Llama-3.1 8B German ORPO |
| Model Creator | Nekochu |
| Base Model(s) | |
| Model Size | 8b |
| Required VRAM | 16.1 GB |
| Updated | 2025-02-22 |
| Maintainer | Nekochu |
| Model Type | llama3.1 |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | de en |
| Model Architecture | LlamaForCausalLM |
| License | llama3.1 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.43.3 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|eot_id|> |
| Vocabulary Size | 128256 |
| LoRA Model | Yes |
| Torch Data Type | bfloat16 |
Best Alternatives to Llama 3.1 8B German ORPO
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...a 3 8B Instruct Gradient 1048K | 1024K / 16.1 GB | 3927 | 680 |
| Mpasila Viking 8B | 1024K / 16.1 GB | 84 | 0 |
| Hel V2 8B DARK FICTION | 1024K / 16.1 GB | 22 | 0 |
| 16 | 1024K / 16.1 GB | 169 | 0 |
| ...di95 LewdStorytellerMix 8B 64K | 1024K / 16.1 GB | 69 | 2 |
| Because Im Bored Nsfw1 | 1024K / 16.1 GB | 36 | 1 |
| 12 | 1024K / 16.1 GB | 60 | 0 |
| MrRoboto ProLong 8B V4b | 1024K / 16.1 GB | 107 | 0 |
| MrRoboto ProLong 8B V1a | 1024K / 16.1 GB | 108 | 0 |
| MrRoboto ProLong 8B V2a | 1024K / 16.1 GB | 102 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than Nekochu/Llama-3.1-8B-German-ORPO .
Rank the Llama 3.1 8B German ORPO 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? 43470 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227