RichardErkhov/unsloth_-_phi-2-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

phi-2 - GGUF

• Model creator: https://huggingface.co/unsloth/
• Original model: https://huggingface.co/unsloth/phi-2/

Name	Quant method	Size
phi-2.Q2_K.gguf	Q2_K	1.03GB
phi-2.IQ3_XS.gguf	IQ3_XS	1.12GB
phi-2.IQ3_S.gguf	IQ3_S	1.16GB
phi-2.Q3_K_S.gguf	Q3_K_S	1.16GB
phi-2.IQ3_M.gguf	IQ3_M	1.23GB
phi-2.Q3_K.gguf	Q3_K	1.33GB
phi-2.Q3_K_M.gguf	Q3_K_M	1.33GB
phi-2.Q3_K_L.gguf	Q3_K_L	1.47GB
phi-2.IQ4_XS.gguf	IQ4_XS	1.43GB
phi-2.Q4_0.gguf	Q4_0	1.49GB
phi-2.IQ4_NL.gguf	IQ4_NL	1.5GB
phi-2.Q4_K_S.gguf	Q4_K_S	1.51GB
phi-2.Q4_K.gguf	Q4_K	1.62GB
phi-2.Q4_K_M.gguf	Q4_K_M	1.62GB
phi-2.Q4_1.gguf	Q4_1	1.65GB
phi-2.Q5_0.gguf	Q5_0	1.8GB
phi-2.Q5_K_S.gguf	Q5_K_S	1.8GB
phi-2.Q5_K.gguf	Q5_K	1.87GB
phi-2.Q5_K_M.gguf	Q5_K_M	1.87GB
phi-2.Q5_1.gguf	Q5_1	1.95GB
phi-2.Q6_K.gguf	Q6_K	2.13GB
phi-2.Q8_0.gguf	Q8_0	2.75GB

Original model description:

language:

• en license: apache-2.0 library_name: transformers tags:
• unsloth
• transformers
• phi
• phi2
• phi-2

---

Finetune Mistral, Gemma, Llama 2-5x faster with 70% less memory via Unsloth!

✨ Finetune for Free

All notebooks are beginner friendly! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model which can be exported to GGUF, vLLM or uploaded to Hugging Face.

Unsloth supports	Free Notebooks	Performance	Memory use
Gemma 7b	▶️ Start on Colab	2.4x faster	58% less
Mistral 7b	▶️ Start on Colab	2.2x faster	62% less
Llama-2 7b	▶️ Start on Colab	2.2x faster	43% less
TinyLlama	▶️ Start on Colab	3.9x faster	74% less
CodeLlama 34b A100	▶️ Start on Colab	1.9x faster	27% less
Mistral 7b 1xT4	▶️ Start on Kaggle	5x faster*	62% less
DPO - Zephyr	▶️ Start on Colab	1.9x faster	19% less

• This conversational notebook is useful for ShareGPT ChatML / Vicuna templates.
• This text completion notebook is for raw text. This DPO notebook replicates Zephyr.
• * Kaggle has 2x T4s, but we use 1. Due to overhead, 1x T4 is 5x faster.