Base model:finetune:goekdeniz-... Base model:goekdeniz-guelmez/j... Chat Conversational De En Instruct Mlx Qwen2 Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/mlx-community/Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1-float32
Josiefied Qwen2.5 0.5B Instruct Abliterated V1 Float32 Benchmarks
MMLU Pro: 7.09
GPQA: 1.01
MUSR: 0.78
BBH: 7.22
IFEval: 33.69 vs 88 (so35)-61.7%
MATH Lvl 5: 8.46
LLME Score: 0.25457
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 0.5B Instruct Abliterated V1 Float32 Parameters and Internals
| LLM Name | Josiefied Qwen2.5 0.5B Instruct Abliterated V1 Float32 |
| Repository 🤗 | https://huggingface.co/mlx-community/Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1-float32 |
| Base Model(s) | |
| Model Size | 0.5b |
| Required VRAM | 2 GB |
| Updated | 2025-03-24 |
| Maintainer | mlx-community |
| Model Type | qwen2 |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en de |
| Model Architecture | Qwen2ForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.46.2 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|im_end|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Josiefied Qwen2.5 0.5B Instruct Abliterated V1 Float32
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen2 0.5B Abyme Merge3 | 128K / 1.3 GB | 35 | 1 |
| Qwen2 0.5B Abyme Merge2 | 128K / 0.3 GB | 14 | 0 |
| Qwen2.5 0.5B Instruct | 32K / 1 GB | 972662 | 275 |
| Qwen2 0.5B Instruct | 32K / 1 GB | 336685 | 181 |
| Qwen2.5 Coder 0.5B Instruct | 32K / 1 GB | 47414 | 42 |
| Qwen2.5 0.5B Portuguese V1 | 32K / 1 GB | 2470 | 4 |
| QwQ 0.5B | 32K / 1 GB | 687 | 3 |
| Lb Reranker 0.5B V1.0 | 32K / 1 GB | 1564 | 63 |
| FastThink 0.5B Tiny | 32K / 1 GB | 1304 | 4 |
| Hammer2.1 0.5B | 32K / 1 GB | 7624 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1-float32 .
Rank the Josiefied Qwen2.5 0.5B Instruct Abliterated V1 Float32 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? 45494 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227