# fine-tuned-model-indonesian-2 by Hendri Mardani: Open Model Source: https://savrn.com/models/fine-tuned-model-indonesian-2 Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve fine-tuned-model-indonesian-2 (8B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them. | Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits | | --- | --- | --- | --- | --- | --- | | 16-bit | 16.1 GB | 19.3 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 8.0 GB | 9.6 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 4.0 GB | 4.8 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the [SAVRN Index](https://savrn.com/ai-index/pricing/gpus), read Oct 7, 2026. [fine-tuned-model-indonesian-2 on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/fine-tuned-model-indonesian-2/gpus) ## Model Card This model is a fine-tuned version of unsloth/Llama-3.1-8B-unsloth-bnb-4bit. It has been trained using TRL. This model was trained with SFT. Excerpt from the card by Hendri Mardani. ## Configuration Architecture LlamaForCausalLM Context length (tokens) 131,072 Layers 32 Hidden size 4,096 Feed-forward size 14,336 Attention heads 32 Key/value heads 8 Head dimension 128 Vocabulary size 128,256 RoPE base 500000 Stored precision bfloat16 Model type llama ## Identity and Version Repository hendrimardani/fine-tuned-model-indonesian-2 Publisher Hendri Mardani Task Text generation Modality Text Library transformers Parameters 8B parameters Languages trl, sft Revision c8d3378b1308da984cef0e7232eec5f95b880390 First published 2026-09-08 Last updated 2026-10-07 ## Files and Weights 31 files, 16.5 GB in total. The weights are 12 files totalling 16.5 GB in bin, pt, pth, safetensors. Weights12 files · 16.5 GB Configuration8 files · 35.0 KB Tokenizer4 files · 34.5 MB Documentation2 files · 6.8 KB Other4 files · 28.5 KB Repository1 file · 1.6 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | adapter_model.safetensors | Weights | 167.8 MB | 4a319eb9d01a | | last-checkpoint/adapter_model.safetensors | Weights | 167.8 MB | 4a319eb9d01a | | last-checkpoint/optimizer.pt | Weights | 86.9 MB | 03e6227e17b7 | | last-checkpoint/rng_state.pth | Weights | 14.7 KB | bc889aeff6d9 | | last-checkpoint/scaler.pt | Weights | 1.4 KB | 8d6fca631a6b | | last-checkpoint/scheduler.pt | Weights | 1.5 KB | 719bbded3901 | | last-checkpoint/training_args.bin | Weights | 6.4 KB | f981f8f922fc | | model-00001-of-00004.safetensors | Weights | 5.0 GB | 2311f928231b | | model-00002-of-00004.safetensors | Weights | 5.0 GB | 3f1b5d3e6e0c | | model-00003-of-00004.safetensors | Weights | 4.9 GB | 6d2c07cb93bc | | model-00004-of-00004.safetensors | Weights | 1.2 GB | 4155c17f9d14 | | training_args.bin | Weights | 6.4 KB | f981f8f922fc | | adapter_config.json | Configuration | 1.3 KB | — | | config.json | Configuration | 934 B | — | | generation_config.json | Configuration | 240 B | — | | last-checkpoint/adapter_config.json | Configuration | 1.3 KB | — | | last-checkpoint/special_tokens_map.json | Configuration | 459 B | — | | last-checkpoint/trainer_state.json | Configuration | 6.3 KB | — | | model.safetensors.index.json | Configuration | 23.9 KB | — | | special_tokens_map.json | Configuration | 459 B | — | | README.md | Documentation | 1.6 KB | — | | last-checkpoint/README.md | Documentation | 5.2 KB | — | | chat_template.jinja | Other | 4.6 KB | — | | last-checkpoint/chat_template.jinja | Other | 4.6 KB | — | | runs/Oct06_14-30-30_ccc67f815b2d/events.out.tfevents.1791297736.ccc67f815b2d.754.0 | Other | 11.7 KB | 73a7ccb3bb46 | | runs/Oct07_01-44-25_80d3f5d902fc/events.out.tfevents.1791337756.80d3f5d902fc.3287.0 | Other | 7.7 KB | fdea048c1282 | | .gitattributes | Repository | 1.6 KB | — | | last-checkpoint/tokenizer.json | Tokenizer | 17.2 MB | 6b9e4e7fb171 | | last-checkpoint/tokenizer_config.json | Tokenizer | 50.6 KB | — | | tokenizer.json | Tokenizer | 17.2 MB | 6b9e4e7fb171 | | tokenizer_config.json | Tokenizer | 50.6 KB | — | ## License and Download License Not stated by the source Access Open weights, no gate Download size 16.5 GB [Download from Hendri Mardani](https://huggingface.co/hendrimardani/fine-tuned-model-indonesian-2) Released by Hendri Mardani through its official repository on Hugging Face. ## Built From - Derived from unsloth/Llama-3.1-8B-unsloth-bnb-4bit ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 16.5 GB | | 16-bit | 16.1 GB | | 8-bit | 8.0 GB | | 4-bit | 4.0 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About fine-tuned-model-indonesian-2 ### How much GPU memory does fine-tuned-model-indonesian-2 need? About 19.3 GB at 16-bit and 4.8 GB at 4-bit: the weights (8B parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run fine-tuned-model-indonesian-2 on? At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists. ### What is fine-tuned-model-indonesian-2's context length? 131,072 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Text generation ### [Llama-3.1-8B-Instruct](https://savrn.com/models/llama-3-1-8b-instruct) [Meta Llama](https://savrn.com/model-publishers/meta-llama) The Meta Llama 3.1 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction tuned generative models in 8B, 70B and 405B sizes (text in/text out). The Llama 3.1 instruction tuned text only models (8B, 70B, 405B) are optimized for multilingual dialogue use cases and outperform many of the available open source and closed chat models on common industry benchmarks. Model Architecture: Llama 3.1 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.… Access requested at publisher llama3.1 8B parameters transformers [View model](https://savrn.com/models/llama-3-1-8b-instruct) Model · Text generation ### [Llama-3.1-8B-Instruct-4bit](https://savrn.com/models/llama-3-1-8b-instruct-4bit) [MLX Community](https://savrn.com/model-publishers/mlx-community) The Model mlx-community/Llama-3.1-8B-Instruct-4bit was converted to MLX format from meta-llama/Llama-3.1-8B-Instruct using mlx-lm version 0.21.4. Open weights llama3.1 8B parameters 131,072 tokens mlx [View model](https://savrn.com/models/llama-3-1-8b-instruct-4bit) Model · Text generation ### [Meta-Llama-3-8B-Instruct](https://savrn.com/models/meta-llama-3-8b-instruct) [Meta Llama](https://savrn.com/model-publishers/meta-llama) Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety. Model developers Meta Variations Llama 3 comes in two sizes — 8B and 70B parameters — in pre-trained and instruction tuned variants. Input Models input text only. Output Models generate text and code only. Model Architecture Llama 3 is an auto-regressive language… Access requested at publisher llama3 8B parameters transformers [View model](https://savrn.com/models/meta-llama-3-8b-instruct) Model · Text generation ### [Llama-3.1-8B-Instruct-Medical-Finetuned-merged](https://savrn.com/models/llama-3-1-8b-instruct-medical-finetuned-merged) [Mohamed Abo El-Enen](https://savrn.com/model-publishers/mohamedahmedae) This is the 8B (high-capacity flagship) member of the Med-LLaMA3 family introduced in the paper “Med-LLaMA3: Advancing Medical Question-Answering Through Parameter-Efficient Fine-Tuning of Large Language Models” (Applied Sciences, 2026). The family adapts the LLaMA-3 architecture to the medical domain by training only a small fraction of the base model’s parameters (4.01% for this 8B variant), achieving strong medical question-answering performance while keeping the memory footprint low — enabling development and inference on low-cost, consumer-grade hardware. The 8B variant is the high-capacity model for complex clinical reasoning. It attains a mean accuracy of 75.71% across the eight MMLU… Open weights llama3.1 8B parameters 131,072 tokens transformers [View model](https://savrn.com/models/llama-3-1-8b-instruct-medical-finetuned-merged) Model · Text generation ### [fine-tuned-model-indonesian](https://savrn.com/models/fine-tuned-model-indonesian) [Hendri Mardani](https://savrn.com/model-publishers/hendrimardani) This model is a fine-tuned version of unsloth/Llama-3.1-8B-unsloth-bnb-4bit. It has been trained using TRL. This model was trained with SFT. Open weights 8B parameters 131,072 tokens transformers [View model](https://savrn.com/models/fine-tuned-model-indonesian) Model · Text generation ### [lebanese-llama-3.1-8b](https://savrn.com/models/lebanese-llama-3-1-8b) [Anthony Assi](https://savrn.com/model-publishers/assix-research) Lebanese-Llama-3.1-8B is a high-performance LLM fine-tuned specifically for the Lebanese dialect (Ammiya). It bridges the gap between Modern Standard Arabic (MSA) and the multi-modal nature of Lebanese communication, seamlessly blending Arabic script, French/English influences, and Arabizi (Romanized Arabic with numbers). This model was trained and validated on the NVIDIA DGX Spark, the world’s first personal AI supercomputer powered by the Grace Blackwell (GB10) architecture. Try the model instantly in your browser without any setup: To get the most authentic "Ammiya" experience, use this system prompt. It activates the model's specialized cultural knowledge and linguistic patterns. Speak… Open weights mit 8B parameters 131,072 tokens transformers [View model](https://savrn.com/models/lebanese-llama-3-1-8b) ## Hendri Mardani [All models and datasets](https://savrn.com/model-publishers/hendrimardani) ## Versions - [c8d3378b1308](https://savrn.com/models/fine-tuned-model-indonesian-2/versions/c8d3378b1308) · current 2026-10-07 ## Explore More - [All text generation models](https://savrn.com/models/tasks/text-generation) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-07. - [Hugging Face record](https://huggingface.co/hendrimardani/fine-tuned-model-indonesian-2) - [How the hub is built](https://savrn.com/model-hub/methodology)