Llama3.1 8B Instruct Convfinqa RFT Sc K10 Lora R16a32 Lr1e 4 Ep3 Ratio0.2 is an open-source language model by Jongbin-kr. Features: 8b LLM, VRAM: 0.2GB, License: llama3.1, Instruction-Based.
| LLM Name | Llama3.1 8B Instruct Convfinqa RFT Sc K10 Lora R16a32 Lr1e 4 Ep3 Ratio0.2 |
| Repository π€ | https://huggingface.co/Jongbin-kr/llama3.1-8b-instruct_convfinqa_RFT-sc_k10_lora-r16a32_lr1e-4_ep3_ratio0.2 |
| Base Model(s) | |
| Model Size | 8b |
| Required VRAM | 0.2 GB |
| Updated | 2026-11-22 |
| Maintainer | Jongbin-kr |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | Adapter |
| License | llama3.1 |
| Model Max Length | 131072 |
| Is Biased | none |
| Tokenizer Class | TokenizersBackend |
| Padding Token | <|finetune_right_pad_id|> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | up_proj|o_proj|q_proj|down_proj|v_proj|k_proj|gate_proj |
| LoRA Alpha | 32 |
| LoRA Dropout | 0.05 |
| R Param | 16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ... 3 8B Instruct Bvr Finetune V3 | 8K / 16.1 GB | 10 | 0 |
| Visual Jev 8B Answer Sft | 0K / 0.2 GB | 44 | 1 |
| K Oss 8 Mini Instruct Beta | 0K / 0.2 GB | 50 | 1 |
| ...Max H3 Prompt Rewriter LoRA 8B | 0K / 2.8 GB | 137 | 26 |
| Velora V1 | 0K / 0 GB | 26 | 1 |
| Llama3 8B Persian Lora | 0K / 0.2 GB | 22 | 1 |
| Genlocalnews Llama3.1 8B Lora | 0K / 0.2 GB | 21 | 1 |
| ....1 8B Reponx Network Cloud Ops | 0K / 0.2 GB | 14 | 2 |
| ...27 Llama31 8B Sgd New Rank 128 | 0K / 1.3 GB | 20 | 1 |
| VitaGridProtocol | 0K / GB | 15 | 1 |