Quantization made by Richard Erkhov.

Phi3_intent_v47_4_w_unknown_7_lr_0.002 - GGUF

Name	Quant method	Size
Phi3_intent_v47_4_w_unknown_7_lr_0.002.Q2_K.gguf	Q2_K	1.35GB
Phi3_intent_v47_4_w_unknown_7_lr_0.002.IQ3_XS.gguf	IQ3_XS	1.49GB
Phi3_intent_v47_4_w_unknown_7_lr_0.002.IQ3_S.gguf	IQ3_S	1.57GB
Phi3_intent_v47_4_w_unknown_7_lr_0.002.Q3_K_S.gguf	Q3_K_S	1.57GB
Phi3_intent_v47_4_w_unknown_7_lr_0.002.IQ3_M.gguf	IQ3_M	1.65GB
Phi3_intent_v47_4_w_unknown_7_lr_0.002.Q3_K.gguf	Q3_K	1.75GB
Phi3_intent_v47_4_w_unknown_7_lr_0.002.Q3_K_M.gguf	Q3_K_M	1.75GB
Phi3_intent_v47_4_w_unknown_7_lr_0.002.Q3_K_L.gguf	Q3_K_L	1.9GB
Phi3_intent_v47_4_w_unknown_7_lr_0.002.IQ4_XS.gguf	IQ4_XS	1.93GB
Phi3_intent_v47_4_w_unknown_7_lr_0.002.Q4_0.gguf	Q4_0	2.03GB
Phi3_intent_v47_4_w_unknown_7_lr_0.002.IQ4_NL.gguf	IQ4_NL	2.04GB
Phi3_intent_v47_4_w_unknown_7_lr_0.002.Q4_K_S.gguf	Q4_K_S	2.04GB
Phi3_intent_v47_4_w_unknown_7_lr_0.002.Q4_K.gguf	Q4_K	2.16GB
Phi3_intent_v47_4_w_unknown_7_lr_0.002.Q4_K_M.gguf	Q4_K_M	2.16GB
Phi3_intent_v47_4_w_unknown_7_lr_0.002.Q4_1.gguf	Q4_1	2.24GB
Phi3_intent_v47_4_w_unknown_7_lr_0.002.Q5_0.gguf	Q5_0	2.46GB
Phi3_intent_v47_4_w_unknown_7_lr_0.002.Q5_K_S.gguf	Q5_K_S	2.46GB
Phi3_intent_v47_4_w_unknown_7_lr_0.002.Q5_K.gguf	Q5_K	2.53GB
Phi3_intent_v47_4_w_unknown_7_lr_0.002.Q5_K_M.gguf	Q5_K_M	2.53GB
Phi3_intent_v47_4_w_unknown_7_lr_0.002.Q5_1.gguf	Q5_1	2.68GB
Phi3_intent_v47_4_w_unknown_7_lr_0.002.Q6_K.gguf	Q6_K	2.92GB
Phi3_intent_v47_4_w_unknown_7_lr_0.002.Q8_0.gguf	Q8_0	3.78GB

Original model description:

Developed by: magnifi
License: apache-2.0
Finetuned from model: unsloth/Phi-3-mini-4k-instruct-bnb-4bit

language: - en license: apache-2.0 tags: - text-generation-inference - transformers - unsloth - mistral - trl base_model: unsloth/Phi-3-mini-4k-instruct-bnb-4bit

This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.