4bit Autotrain compatible Base model:quantized:unsloth/p... Base model:unsloth/phi-3-mini-... Conversational Dataset:kms7530/chemeng En Endpoints compatible Gguf Instruct Lora Mistral Pytorch Quantized Region:us Safetensors Sft Sharded Tensorflow Trl Unsloth
Model Card on HF 🤗: https://huggingface.co/kms7530/chemeng_phi-3-mini-4k-instruct-bnb-4bit_16_4_100_1_nonmath
Chemeng Phi 3 Mini 4K Instruct Bnb 4bit 16 4 100 1 Nonmath Benchmarks
MMLU Pro: 27.56
GPQA: 8.05
MUSR: 8.35
BBH: 29.26
IFEval: 48.63 vs 88 (so35)-44.7%
MATH Lvl 5: 10.8
LLME Score: 0.25463
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)
Chemeng Phi 3 Mini 4K Instruct Bnb 4bit 16 4 100 1 Nonmath Parameters and Internals
| LLM Name | Chemeng Phi 3 Mini 4K Instruct Bnb 4bit 16 4 100 1 Nonmath |
| Repository 🤗 | https://huggingface.co/kms7530/chemeng_phi-3-mini-4k-instruct-bnb-4bit_16_4_100_1_nonmath |
| Base Model(s) | |
| Model Size | 3.8b |
| Required VRAM | 7.6 GB |
| Updated | 2025-09-23 |
| Maintainer | kms7530 |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| GGUF Quantization | Yes |
| Quantization Type | gguf|4bit |
| Model Architecture | AutoModelForCausalLM |
| License | apache-2.0 |
| Model Max Length | 4096 |
| Is Biased | none |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|placeholder6|> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | k_proj|q_proj|up_proj|down_proj|v_proj|o_proj|gate_proj |
| LoRA Alpha | 16 |
| LoRA Dropout | 0 |
| R Param | 16 |
Best Alternatives to Chemeng Phi 3 Mini 4K Instruct Bnb 4bit 16 4 100 1 Nonmath
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Phi 3 Mini Instruct 16bit | 0K / 7.6 GB | 8 | 0 |
| Followup V6 | 0K / 7.6 GB | 0 | 0 |
Rank the Chemeng Phi 3 Mini 4K Instruct Bnb 4bit 16 4 100 1 Nonmath 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? 51544 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124