Base model:delta-vector/hamana... Base model:finetune:delta-vect... Dataset:neweden/claude-instruc... Dataset:neweden/claude-instruc... Dataset:neweden/gsm8k-r1-filte... Dataset:neweden/helpsteer-3-fi... Dataset:neweden/hydrus-chat er... Dataset:neweden/hydrus-helpste... Dataset:neweden/hydrus-instruc... Dataset:neweden/hydrus-r1-thin... Dataset:neweden/hydrus-sonneto... Dataset:nitral-ai/ares-sharegp... Dataset:pocketdoc/dans-assista... Dataset:pocketdoc/dans-memoryc... Finetuned Instruct Llama Qwen Region:us Roleplay Safetensors Sharded Storywriting Tensorflow
Model Card on HF 🤗: https://huggingface.co/Delta-Vector/Hamanasu-4B-Instruct
Hamanasu 4B Instruct 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)
Hamanasu 4B Instruct Parameters and Internals
| LLM Name | Hamanasu 4B Instruct |
| Repository 🤗 | https://huggingface.co/Delta-Vector/Hamanasu-4B-Instruct |
| Base Model(s) | |
| Model Size | 4b |
| Required VRAM | 9 GB |
| Updated | 2025-05-31 |
| Maintainer | Delta-Vector |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.49.0 |
| Tokenizer Class | PreTrainedTokenizer |
| Padding Token | <|finetune_right_pad_id|> |
| Vocabulary Size | 128256 |
| Torch Data Type | bfloat16 |
Best Alternatives to Hamanasu 4B Instruct
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Xgen Small 4B Instruct R | 256K / 17.7 GB | 40 | 2 |
| Aura 4B | 128K / 9 GB | 7 | 11 |
| Hamanasu Magnum 4B | 128K / 9 GB | 18 | 4 |
| Hamanasu Adventure 4B | 128K / 9.1 GB | 10 | 4 |
| Hamanasu 4B Chat Brainrot | 128K / 9 GB | 14 | 3 |
| Hamanasu 4B Instruct KTO V2 | 128K / 9 GB | 4 | 2 |
| 4B Inst | 128K / 9 GB | 16 | 0 |
| Hamanasu 4B Instruct KTO V1 | 128K / 9 GB | 4 | 2 |
| 4B Inst | 128K / 9 GB | 9 | 0 |
| Holland 4B V1 | 128K / 9 GB | 50 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than Delta-Vector/Hamanasu-4B-Instruct .
Rank the Hamanasu 4B Instruct 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? 47753 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227