Merged Model Autotrain compatible Base model:finetune:sakalti/sa... Base model:sakalti/saba1.5-pro Conversational Endpoints compatible Qwen2 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/Sakalti/Saba-Passthrough-2
Saba Passthrough 2 Benchmarks
MMLU Pro: 11.97
GPQA: 1.79
MUSR: 5.42
BBH: 11.95
IFEval: 16.91 vs 88 (so35)-80.8%
MATH Lvl 5: 0.08
LLME Score: 0.26534
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)
Saba Passthrough 2 Parameters and Internals
| LLM Name | Saba Passthrough 2 |
| Repository 🤗 | https://huggingface.co/Sakalti/Saba-Passthrough-2 |
| Base Model(s) | |
| Merged Model | Yes |
| Model Size | 3.1b |
| Required VRAM | 6.2 GB |
| Updated | 2025-02-22 |
| Maintainer | Sakalti |
| Model Type | qwen2 |
| Model Files | |
| Model Architecture | Qwen2ForCausalLM |
| License | apache-2.0 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.46.3 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|vision_pad|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Saba Passthrough 2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Thynk | 32K / 6.2 GB | 45 | 0 |
Rank the Saba Passthrough 2 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? 43470 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227