Phi 3.5 Mini Instruct Hermes Fc Json is an open-source language model by vonjack. Features: LLM, VRAM: 0.1GB, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.17.
4bit Adapter Base model:quantized:unsloth/p... Base model:unsloth/phi-3.5-min... Conversational Dataset:nousresearch/hermes-fu... Endpoints compatible Finetuned Ggml Gguf Instruct Lora Q4 Quantized Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/vonjack/Phi-3.5-mini-instruct-hermes-fc-json
Phi 3.5 Mini Instruct Hermes Fc Json Benchmarks
MMLU Pro: 1.54
GPQA: 0.56
MUSR: 8.45
BBH: 2.39
IFEval: 14.16 vs 88 (so35)-83.9%
MATH Lvl 5: 0.76
LLME Score: 0.17336
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)
Phi 3.5 Mini Instruct Hermes Fc Json Parameters and Internals
| LLM Name | Phi 3.5 Mini Instruct Hermes Fc Json |
| Repository 🤗 | https://huggingface.co/vonjack/Phi-3.5-mini-instruct-hermes-fc-json |
| Base Model(s) | |
| Required VRAM | 0.1 GB |
| Updated | 2026-04-25 |
| Maintainer | vonjack |
| Instruction-Based | Yes |
| Model Files | |
| GGML Quantization | Yes |
| GGUF Quantization | Yes |
| Quantization Type | gguf|ggml|q4|4bit |
| Model Architecture | Adapter |
| License | apache-2.0 |
| Model Max Length | 131072 |
| Is Biased | none |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|placeholder6|> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | down_proj|gate_proj|k_proj|q_proj|o_proj|up_proj|v_proj |
| LoRA Alpha | 16 |
| LoRA Dropout | 0 |
| R Param | 16 |
Best Alternatives to Phi 3.5 Mini Instruct Hermes Fc Json
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| NaturalLanguagePioneersSTEMExp | 0K / 0.4 GB | 5 | 0 |
| Mymodel | 0K / 0.1 GB | 8 | 0 |
| Phi 3 Mini 4K Instruct Sa V0.1 | 0K / 0 GB | 6 | 0 |
| ...caaaf043da230d9a30d8e0ddcbe879 | 0K / 0.4 GB | 11 | 0 |
| ...357cade9cc1096cecc35c34dba8992 | 0K / 1.3 GB | 10 | 0 |
| ...ini Instruct MedicalChat QLoRA | 0K / 0.1 GB | 0 | 2 |
| ...mall Physics Finetuned Adapter | 0K / 0.1 GB | 1 | 1 |
| Mistral Small Dampf Qlora | 0K / 0.8 GB | 8 | 0 |
| Mistral Small Fujin Qlora | 0K / 0.8 GB | 6 | 2 |
| Test | 0K / 0 GB | 5 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than vonjack/Phi-3.5-mini-instruct-hermes-fc-json .
Rank the Phi 3.5 Mini Instruct Hermes Fc Json 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? 53185 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a