Fireball 3.1 8B ORPO Benchmarks
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)
Fireball 3.1 8B ORPO Parameters and Internals
| LLM Name | Fireball 3.1 8B ORPO |
| Repository 🤗 | https://huggingface.co/EpistemeAI/Fireball-3.1-8B-ORPO |
| Model Creator | EpistemeAI |
| Base Model(s) | |
| Model Size | 8b |
| Required VRAM | 16.1 GB |
| Updated | 2024-09-19 |
| Maintainer | EpistemeAI |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 4bit |
| Model Architecture | Adapter |
| License | llama3.1 |
| Model Max Length | 131072 |
| Is Biased | none |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|finetune_right_pad_id|> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | v_proj|up_proj|gate_proj|o_proj|q_proj|down_proj|k_proj |
| LoRA Alpha | 16 |
| LoRA Dropout | 0 |
| R Param | 16 |
Best Alternatives to Fireball 3.1 8B ORPO
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ... 3 8B Instruct Bvr Finetune V3 | 8K / 16.1 GB | 8 | 0 |
| Llama3 C1 Full | 0K / 0.2 GB | 13 | 0 |
| Adapter Test | 0K / 0.1 GB | 6 | 0 |
| Vortex2 | 0K / 4.4 GB | 8 | 0 |
| FineLlama3.1 8B Instruct Lora | 0K / 0.2 GB | 0 | 1 |
| Llama 3 8B Claudstruct V3 | 0K / 0.1 GB | 35 | 0 |
| Llama3 8B Instruct Code | 0K / 0.2 GB | 1 | 1 |
| Llama 3 8B Instruct 80K QLoRA | 0K / 2.2 GB | 0 | 23 |
| Llama3 8b Sa V0.1 | 0K / 0 GB | 31 | 0 |
| Llama 3 8B Claudstruct V1 | 0K / 0.1 GB | 5 | 0 |
Rank the Fireball 3.1 8B 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? 36026 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803