Arxiv:1910.09700 Autotrain compatible Endpoints compatible Finetuned Llama Lora Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/GENIAC-Team-Ozaki/lora-sft-finetuned-stage4-iter86000
Lora Sft Finetuned Stage4 Iter86000 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)
Lora Sft Finetuned Stage4 Iter86000 Parameters and Internals
| LLM Name | Lora Sft Finetuned Stage4 Iter86000 |
| Repository 🤗 | https://huggingface.co/GENIAC-Team-Ozaki/lora-sft-finetuned-stage4-iter86000 |
| Model Size | 11.5b |
| Required VRAM | 23.2 GB |
| Updated | 2025-09-23 |
| Maintainer | GENIAC-Team-Ozaki |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.40.0 |
| Tokenizer Class | T5Tokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 50816 |
| LoRA Model | Yes |
| Torch Data Type | bfloat16 |
Best Alternatives to Lora Sft Finetuned Stage4 Iter86000
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Midm 2.0 Base Instruct | 32K / 23.1 GB | 109699 | 125 |
| Llama 3 Monika Ddlc 11.5B V1 | 8K / 23 GB | 6 | 3 |
| Llama 3 11.5B V2 | 8K / 23 GB | 36 | 41 |
| Llama 3 11.5B Instruct V2 | 8K / 23 GB | 7 | 6 |
| Llama 3 11.5B V0.1 | 8K / 23 GB | 5 | 1 |
| Mermaid 11.5B | 4K / 23.2 GB | 4 | 1 |
| ...ena Finetuned Stage2 Iter40000 | 2K / 23.2 GB | 7 | 0 |
| L3 11.5B DuS MoonRoot Bnb 4bit | 8K / 7.5 GB | 5 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than GENIAC-Team-Ozaki/lora-sft-finetuned-stage4-iter86000 .
Rank the Lora Sft Finetuned Stage4 Iter86000 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? 51544 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124