Refined Llama3 is an open-source language model by Gab-Chung. Features: 7b LLM, VRAM: 0.2GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.12.
| Model Type |
| |
| Additional Notes |
| |
| Supported Languages |
|
| LLM Name | Refined Llama3 |
| Repository 🤗 | https://huggingface.co/Gab-Chung/Refined-Llama3 |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 0.2 GB |
| Updated | 2026-07-11 |
| Maintainer | Gab-Chung |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 4bit |
| Model Architecture | AutoModelForCausalLM |
| License | apache-2.0 |
| Model Max Length | 8192 |
| Is Biased | none |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|reserved_special_token_250|> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | k_proj|v_proj|q_proj|o_proj|down_proj|gate_proj|up_proj |
| LoRA Alpha | 16 |
| LoRA Dropout | 0 |
| R Param | 16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen2.5 8K Sports | 0K / 15.2 GB | 14 | 0 |
| WorldBuilder 7B | 0K / 14.5 GB | 4 | 1 |
| Unsloth Alpaca | 0K / 14.5 GB | 5 | 0 |
| ... WAEMU Africa Banking Analysis | 0K / 15.2 GB | 6 | 1 |
| Gemma 7B Bnb 4bit | 0K / 17.1 GB | 5 | 0 |
| Mistral 7B V0.3 | 0K / 14.5 GB | 5 | 0 |
| Mistralbasket1 | 0K / 0.2 GB | 7 | 0 |
| Unsloth Vinallama | 0K / 14.4 GB | 22 | 0 |
| Gemma Unsloth Alpaca | 0K / 17.1 GB | 5 | 2 |
| Mistral 7B Instruct 4bit | 0K / 0.2 GB | 11 | 1 |