Ara Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-1.5b Chat Conversational Deu Eng Fra Instruct Ita Jpn Kor Por Qwen2 Region:us Rus Safetensors Spa Tha Vie Zho
Model Card on HF 🤗: https://huggingface.co/Goekdeniz-Guelmez/Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v1
Josiefied Qwen2.5 1.5B Instruct Abliterated V1 Benchmarks
MMLU Pro: 19.81
MUSR: 4
BBH: 18.31
IFEval: 47.69 vs 88 (so35)-45.8%
MATH Lvl 5: 20.85
LLME Score: 0.24667
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)
Josiefied Qwen2.5 1.5B Instruct Abliterated V1 Parameters and Internals
| LLM Name | Josiefied Qwen2.5 1.5B Instruct Abliterated V1 |
| Repository 🤗 | https://huggingface.co/Goekdeniz-Guelmez/Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v1 |
| Base Model(s) | |
| Model Size | 1.5b |
| Required VRAM | 3.5 GB |
| Updated | 2025-07-02 |
| Maintainer | Goekdeniz-Guelmez |
| Model Type | qwen2 |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Model Architecture | Qwen2ForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.44.2 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Josiefied Qwen2.5 1.5B Instruct Abliterated V1
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| AceInstruct 1.5B | 128K / 3.5 GB | 5382 | 20 |
| Gte Qwen2 1.5B Instruct | 128K / 7.1 GB | 102496 | 221 |
| WiroAI Finance Qwen 1.5B | 128K / 3.5 GB | 1962 | 19 |
| ... Abliterated TIES Qwen2.5 1.5B | 128K / 3.5 GB | 12 | 0 |
| GCIRS Reasoning 1.5B R1 | 128K / 3.5 GB | 37 | 1 |
| Saba1 1.8B | 128K / 3.6 GB | 18 | 1 |
| Bellatrix 1.5B XElite | 128K / 3.5 GB | 23 | 3 |
| Miniclaus Qw1.5B UNAMGS | 128K / 3.5 GB | 22 | 8 |
| ...illed Scout 1.5B Instruct Gen1 | 128K / 3.5 GB | 7 | 0 |
| ...pmath Competitive 1.5B Preview | 128K / 7.1 GB | 32 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than Goekdeniz-Guelmez/Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v1 .
Rank the Josiefied Qwen2.5 1.5B Instruct Abliterated V1 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? 49328 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124