Merged Model Arxiv:2306.01708 Arxiv:2311.03099 Autotrain compatible Base model:powerinfer/smallthi... Base model:prithivmlmods/qwq-l... Base model:qwen/qwen2.5-3b-ins... Conversational Endpoints compatible Instruct Qwen2 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/Ahdoot/StructuredThinker-v0.3-MoreStructure
StructuredThinker V0.3 MoreStructure Benchmarks
MMLU Pro: 29
GPQA: 6.26
MUSR: 10.01
BBH: 27.26
IFEval: 41.93 vs 88 (so35)-52.4%
MATH Lvl 5: 23.49
LLME Score: 0.32671
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)
StructuredThinker V0.3 MoreStructure Parameters and Internals
| LLM Name | StructuredThinker V0.3 MoreStructure |
| Repository 🤗 | https://huggingface.co/Ahdoot/StructuredThinker-v0.3-MoreStructure |
| Base Model(s) | |
| Merged Model | Yes |
| Model Size | 3b |
| Required VRAM | 6.8 GB |
| Updated | 2025-02-05 |
| Maintainer | Ahdoot |
| Model Type | qwen2 |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | Qwen2ForCausalLM |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.46.2 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to StructuredThinker V0.3 MoreStructure
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Saba2 3B | 128K / 6.2 GB | 330 | 0 |
| SmallThinker 3B Preview | 32K / 6.8 GB | 130211 | 379 |
| Qwen2.5 3B Instruct | 32K / 6.2 GB | 326544 | 158 |
| Calme 3.2 Instruct 3B | 32K / 11 GB | 3022 | 1 |
| Calme 3.1 Baguette 3B | 32K / 6.2 GB | 3008 | 1 |
| Calme 3.2 Baguette 3B | 32K / 11 GB | 2910 | 1 |
| Dria Agent A 3B | 32K / 6.2 GB | 1465 | 48 |
| Calme 3.1 Instruct 3B | 32K / 11 GB | 2974 | 3 |
| Qwen2.5 Coder 3B Instruct | 32K / 6.2 GB | 35259 | 34 |
| ...M V1.5 Base QwQ Qwen 2.5 O1 3B | 32K / 6.2 GB | 178 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than Ahdoot/StructuredThinker-v0.3-MoreStructure .
Rank the StructuredThinker V0.3 MoreStructure 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? 42577 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227