commit d0935a77b73c3367d30ace2f941232316ba6a277 Author: ModelHub XC Date: Mon Jul 27 11:55:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: nguyenviet/PhoGPT-7B5-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f053e37 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +PhoGPT-7B5-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text +PhoGPT-7B5-Instruct-q2_k.gguf filter=lfs diff=lfs merge=lfs -text +PhoGPT-7B5-Instruct-q3_k_l.gguf filter=lfs diff=lfs merge=lfs -text +PhoGPT-7B5-Instruct-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text +PhoGPT-7B5-Instruct-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text +PhoGPT-7B5-Instruct-q4_0.gguf filter=lfs diff=lfs merge=lfs -text +PhoGPT-7B5-Instruct-q4_1.gguf filter=lfs diff=lfs merge=lfs -text +PhoGPT-7B5-Instruct-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text +PhoGPT-7B5-Instruct-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text +PhoGPT-7B5-Instruct-q5_0.gguf filter=lfs diff=lfs merge=lfs -text +PhoGPT-7B5-Instruct-q5_1.gguf filter=lfs diff=lfs merge=lfs -text +PhoGPT-7B5-Instruct-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text +PhoGPT-7B5-Instruct-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text +PhoGPT-7B5-Instruct-q6_k.gguf filter=lfs diff=lfs merge=lfs -text +PhoGPT-7B5-Instruct-q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/PhoGPT-7B5-Instruct-f16.gguf b/PhoGPT-7B5-Instruct-f16.gguf new file mode 100644 index 0000000..441d73d --- /dev/null +++ b/PhoGPT-7B5-Instruct-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fa821d779fbc1724cdcbf4da3f3b6a567469a400c89bfc9caaf7bfe2dcaf5b9 +size 17014795424 diff --git a/PhoGPT-7B5-Instruct-q2_k.gguf b/PhoGPT-7B5-Instruct-q2_k.gguf new file mode 100644 index 0000000..10db323 --- /dev/null +++ b/PhoGPT-7B5-Instruct-q2_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84f6211ea1b3ef93b7a51d18d6aee8f07177039d28b218b7a7d32654669a4bfb +size 3804277984 diff --git a/PhoGPT-7B5-Instruct-q3_k_l.gguf b/PhoGPT-7B5-Instruct-q3_k_l.gguf new file mode 100644 index 0000000..27dcee2 --- /dev/null +++ b/PhoGPT-7B5-Instruct-q3_k_l.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b506aed98a88dd32f555b744bbfbf6e1a106747e170c8fb4043d483629bb0b9 +size 4978191584 diff --git a/PhoGPT-7B5-Instruct-q3_k_m.gguf b/PhoGPT-7B5-Instruct-q3_k_m.gguf new file mode 100644 index 0000000..4d6b643 --- /dev/null +++ b/PhoGPT-7B5-Instruct-q3_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:363f9c6a0bdb25a9b578785058e4cd26ae60bad7c19b34cd8c1a945c2e659108 +size 4659424480 diff --git a/PhoGPT-7B5-Instruct-q3_k_s.gguf b/PhoGPT-7B5-Instruct-q3_k_s.gguf new file mode 100644 index 0000000..99a3dda --- /dev/null +++ b/PhoGPT-7B5-Instruct-q3_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d4ca305eb3899b0c39f7818c4f5ae7177162e8948d1fb35cc8e340d7df077ab +size 4072221920 diff --git a/PhoGPT-7B5-Instruct-q4_0.gguf b/PhoGPT-7B5-Instruct-q4_0.gguf new file mode 100644 index 0000000..5ba981f --- /dev/null +++ b/PhoGPT-7B5-Instruct-q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c5f5fc4fbc98825d4cc21560aaa03772a750783cd67389c970648d40b9a187f +size 5064338656 diff --git a/PhoGPT-7B5-Instruct-q4_1.gguf b/PhoGPT-7B5-Instruct-q4_1.gguf new file mode 100644 index 0000000..e60684e --- /dev/null +++ b/PhoGPT-7B5-Instruct-q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a48670ee96f552f25fbcd5018c3b592742c54f6521fd7a0acfbe92597aab2be +size 5531217120 diff --git a/PhoGPT-7B5-Instruct-q4_k_m.gguf b/PhoGPT-7B5-Instruct-q4_k_m.gguf new file mode 100644 index 0000000..a51379a --- /dev/null +++ b/PhoGPT-7B5-Instruct-q4_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61a006ece8676230f0f82b0f29ec1023cce50effb54769b98c7a40fad64da146 +size 5542489312 diff --git a/PhoGPT-7B5-Instruct-q4_k_s.gguf b/PhoGPT-7B5-Instruct-q4_k_s.gguf new file mode 100644 index 0000000..c363695 --- /dev/null +++ b/PhoGPT-7B5-Instruct-q4_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d95b7d4d77859681cd50c0482d6ae2ff66b0381774f9d14eed2a82440484faac +size 5097893088 diff --git a/PhoGPT-7B5-Instruct-q5_0.gguf b/PhoGPT-7B5-Instruct-q5_0.gguf new file mode 100644 index 0000000..b23bc5b --- /dev/null +++ b/PhoGPT-7B5-Instruct-q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:289245702d8b1f75adb08eef340916089cf310bbcffdf748274d672ec70ff18a +size 5998095584 diff --git a/PhoGPT-7B5-Instruct-q5_1.gguf b/PhoGPT-7B5-Instruct-q5_1.gguf new file mode 100644 index 0000000..c939590 --- /dev/null +++ b/PhoGPT-7B5-Instruct-q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2a6e1867509f249f629060492f6888e45f2d91db07dcea2fd0d9cf4fa5bfcbc +size 6464974048 diff --git a/PhoGPT-7B5-Instruct-q5_k_m.gguf b/PhoGPT-7B5-Instruct-q5_k_m.gguf new file mode 100644 index 0000000..eb9c797 --- /dev/null +++ b/PhoGPT-7B5-Instruct-q5_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dbaa11561f9a4e9030d601e5369c42818aec19178975f3972a8c5afec91ffe8 +size 6354611424 diff --git a/PhoGPT-7B5-Instruct-q5_k_s.gguf b/PhoGPT-7B5-Instruct-q5_k_s.gguf new file mode 100644 index 0000000..59957be --- /dev/null +++ b/PhoGPT-7B5-Instruct-q5_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d986fc1aae234ea6bcfb9834d8458272d80de89fbc7518a6cd461f9b4935dcd1 +size 5998095584 diff --git a/PhoGPT-7B5-Instruct-q6_k.gguf b/PhoGPT-7B5-Instruct-q6_k.gguf new file mode 100644 index 0000000..892f0d2 --- /dev/null +++ b/PhoGPT-7B5-Instruct-q6_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7068747c48c2a6fe2ec6cffd024fd78d91a55dc868bff4659c150756a6e19793 +size 6990212320 diff --git a/PhoGPT-7B5-Instruct-q8_0.gguf b/PhoGPT-7B5-Instruct-q8_0.gguf new file mode 100644 index 0000000..3be2c2b --- /dev/null +++ b/PhoGPT-7B5-Instruct-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d41710133afd3b19ef1ca31ba27847aa5b12fe4be270f816009812eee4ead3d +size 9048239328 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a331475 --- /dev/null +++ b/README.md @@ -0,0 +1,49 @@ +--- +license: other +language: +- vi +model_name: PhoGPT 7B5 Instruct +inference: false +model_creator: VinAI Research +model_link: https://huggingface.co/vinai/PhoGPT-7B5-Instruct +model_type: mpt +pipeline_tag: text-generation +quantized_by: nguyenviet +base_model: vinai/PhoGPT-7B5-Instruct +--- + +# PhoGPT-7B5-Instruct.GGUF + +GGUF format files of the model [vinai/PhoGPT-7B5-Instruct](https://huggingface.co/vinai/PhoGPT-7B5-Instruct). + +## Model Details + +For detailed information about the original model, please refer to [phoGPT's repository](https://github.com/VinAIResearch/PhoGPT). + +## Uses + +Select and download the quantization version that fits the needs. + +## License + +PhoGPT is licensed under the [PhoGPT Community License](https://github.com/VinAIResearch/PhoGPT/blob/main/LICENSE), Copyright (c) VinAI. All Rights Reserved. + +## Provided files + +| Name | Quant method | Size | Use case | +| ---- | ---- | ---- | ----- | +| [PhoGPT-7B5-Instruct-q2_k.gguf](https://huggingface.co/nguyenviet/PhoGPT-7B5-Instruct-GGUF/blob/main/PhoGPT-7B5-Instruct-q2_k.gguf) | Q2_K | 3.8 GB | smallest, significant quality loss - not recommended for most purposes | +| [PhoGPT-7B5-Instruct-q3_k_s.gguf](https://huggingface.co/nguyenviet/PhoGPT-7B5-Instruct-GGUF/blob/main/PhoGPT-7B5-Instruct-q3_k_s.gguf) | Q3_K_S | 4.07 GB | very small, high quality loss | +| [PhoGPT-7B5-Instruct-q3_k_m.gguf](https://huggingface.co/nguyenviet/PhoGPT-7B5-Instruct-GGUF/blob/main/PhoGPT-7B5-Instruct-q3_k_m.gguf) | Q3_K_M | 4.66 GB | very small, high quality loss | +| [PhoGPT-7B5-Instruct-q3_k_l.gguf](https://huggingface.co/nguyenviet/PhoGPT-7B5-Instruct-GGUF/blob/main/PhoGPT-7B5-Instruct-q3_k_l.gguf) | Q3_K_L | 4.98 GB | small, substantial quality loss | +| [PhoGPT-7B5-Instruct-q4_0.gguf](https://huggingface.co/nguyenviet/PhoGPT-7B5-Instruct-GGUF/blob/main/PhoGPT-7B5-Instruct-q4_0.gguf) | Q4_0 | 5.06 GB | legacy; small, very high quality loss - prefer using Q3_K_M | +| [PhoGPT-7B5-Instruct-q4_k_s.gguf](https://huggingface.co/nguyenviet/PhoGPT-7B5-Instruct-GGUF/blob/main/PhoGPT-7B5-Instruct-q4_k_s.gguf) | Q4_K_S | 5.1 GB | small, greater quality loss | +| [PhoGPT-7B5-Instruct-q4_k_m.gguf](https://huggingface.co/nguyenviet/PhoGPT-7B5-Instruct-GGUF/blob/main/PhoGPT-7B5-Instruct-q4_k_m.gguf) | Q4_K_M | 5.54 GB | medium, balanced quality - recommended | +| [PhoGPT-7B5-Instruct-q4_1.gguf](https://huggingface.co/nguyenviet/PhoGPT-7B5-Instruct-GGUF/blob/main/PhoGPT-7B5-Instruct-q4_1.gguf) | Q4_1 | 5.53 GB | legacy; higher accuracy than Q4_0 but not as high as Q5_0, however has quicker inference than Q5 models. +| [PhoGPT-7B5-Instruct-q5_0.gguf](https://huggingface.co/nguyenviet/PhoGPT-7B5-Instruct-GGUF/blob/main/PhoGPT-7B5-Instruct-q5_0.gguf) | Q5_0 | 6 GB | legacy; medium, balanced quality - prefer using Q4_K_M | +| [PhoGPT-7B5-Instruct-q5_k_s.gguf](https://huggingface.co/nguyenviet/PhoGPT-7B5-Instruct-GGUF/blob/main/PhoGPT-7B5-Instruct-q5_k_s.gguf) | Q5_K_S | 6 GB | large, low quality loss - recommended | +| [PhoGPT-7B5-Instruct-q5_k_m.gguf](https://huggingface.co/nguyenviet/PhoGPT-7B5-Instruct-GGUF/blob/main/PhoGPT-7B5-Instruct-q5_k_m.gguf) | Q5_K_M | 6.35 GB | large, very low quality loss - recommended | +| [PhoGPT-7B5-Instruct-q5_1.gguf](https://huggingface.co/nguyenviet/PhoGPT-7B5-Instruct-GGUF/blob/main/PhoGPT-7B5-Instruct-q5_1.gguf) | Q5_1 | 6.46 GB | legacy; even higher accuracy, resource usage and slower inference. +| [PhoGPT-7B5-Instruct-q6_k.gguf](https://huggingface.co/nguyenviet/PhoGPT-7B5-Instruct-GGUF/blob/main/PhoGPT-7B5-Instruct-q6_k.gguf) | Q6_K | 6.99 GB | very large, extremely low quality loss | +| [PhoGPT-7B5-Instruct-q8_0.gguf](https://huggingface.co/nguyenviet/PhoGPT-7B5-Instruct-GGUF/blob/main/PhoGPT-7B5-Instruct-q8_0.gguf) | Q8_0 | 9.05 GB | almost indistinguishable from float16. High resource use and slow, not recommended for most users | +| [PhoGPT-7B5-Instruct-f16.gguf](https://huggingface.co/nguyenviet/PhoGPT-7B5-Instruct-GGUF/blob/main/PhoGPT-7B5-Instruct-f16.gguf) | float16 | 17 GB | very large, extremely low quality loss - not recommended |