4bit Autotrain compatible Base model:finetune:unsloth/ph... Base model:unsloth/phi-4-unslo... Conversational Dataset:bespokelabs/bespoke-st... Dataset:bespokelabs/bespoke-st... Dataset:novasky-ai/sky-t1 data... Dataset:open-thoughts/openthou... Dataset:quazim0t0/benfordslawr... En Endpoints compatible Gguf Llama Model-index Quantized Region:us Safetensors Sharded Tensorflow Unsloth
Model Card on HF 🤗: https://huggingface.co/Quazim0t0/Phi4.Turn.R1Distill_v1.5.1-Tensors
Phi4.Turn.R1Distill V1.5.1 Tensors Benchmarks
MMLU Pro: 45.75
GPQA: 2.46
MUSR: 7.04
BBH: 49.22
IFEval: 29.95 vs 88 (so35)-66%
MATH Lvl 5: 21.9
LLME Score: 0.337
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)
Phi4.Turn.R1Distill V1.5.1 Tensors Parameters and Internals
| LLM Name | Phi4.Turn.R1Distill V1.5.1 Tensors |
| Repository 🤗 | https://huggingface.co/Quazim0t0/Phi4.Turn.R1Distill_v1.5.1-Tensors |
| Base Model(s) | |
| Model Size | 14.7b |
| Required VRAM | 29.4 GB |
| Updated | 2025-03-14 |
| Maintainer | Quazim0t0 |
| Model Type | llama |
| Model Files | |
| Supported Languages | en |
| GGUF Quantization | Yes |
| Quantization Type | gguf|4bit |
| Model Architecture | LlamaForCausalLM |
| License | apache-2.0 |
| Context Length | 16384 |
| Model Max Length | 16384 |
| Transformers Version | 4.47.1 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|dummy_87|> |
| Vocabulary Size | 100352 |
| Torch Data Type | bfloat16 |
Best Alternatives to Phi4.Turn.R1Distill V1.5.1 Tensors
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Imagine V0.5 16bit | 16K / 29.4 GB | 25 | 0 |
| ThinkPhi1.1 Tensors | 16K / 29.4 GB | 129 | 2 |
| DeepThinkers Phi4 | 16K / 29.4 GB | 290 | 4 |
| DeepThink Phi4 | 16K / 29.4 GB | 24 | 1 |
| Unaligned Thinker PHI 4 | 16K / 29.4 GB | 137 | 1 |
| Phi 4 COT | 16K / 29.4 GB | 13 | 0 |
| Phi4 New Params 16bit | 16K / 29.4 GB | 43 | 0 |
| ...APhi4 GRPO 250218 Merged 16bit | 16K / 29.4 GB | 10 | 0 |
| Phi 4 Llama T1 Full | 16K / 29.4 GB | 43 | 1 |
| ...i4.Turn.R1Distill V1.0 Tensors | 16K / 29.4 GB | 0 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than Quazim0t0/Phi4.Turn.R1Distill_v1.5.1-Tensors .
Rank the Phi4.Turn.R1Distill V1.5.1 Tensors 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? 45019 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227