commit aaa0a890d6c2a5b3cec8d733e8f4f391d433feaf Author: ModelHub XC Date: Sun May 10 03:30:52 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/vinallama-2.7b-chat-sft-v1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c7f0778 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +vinallama-2.7b-chat-sft-v1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +vinallama-2.7b-chat-sft-v1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +vinallama-2.7b-chat-sft-v1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +vinallama-2.7b-chat-sft-v1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +vinallama-2.7b-chat-sft-v1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +vinallama-2.7b-chat-sft-v1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +vinallama-2.7b-chat-sft-v1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +vinallama-2.7b-chat-sft-v1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +vinallama-2.7b-chat-sft-v1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +vinallama-2.7b-chat-sft-v1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +vinallama-2.7b-chat-sft-v1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +vinallama-2.7b-chat-sft-v1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..e1d41aa --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: DuongTrongChi/vinallama-2.7b-chat-sft-v1 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + + + + +static quants of https://huggingface.co/DuongTrongChi/vinallama-2.7b-chat-sft-v1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#vinallama-2.7b-chat-sft-v1-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/vinallama-2.7b-chat-sft-v1-GGUF/resolve/main/vinallama-2.7b-chat-sft-v1.Q2_K.gguf) | Q2_K | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/vinallama-2.7b-chat-sft-v1-GGUF/resolve/main/vinallama-2.7b-chat-sft-v1.Q3_K_S.gguf) | Q3_K_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/vinallama-2.7b-chat-sft-v1-GGUF/resolve/main/vinallama-2.7b-chat-sft-v1.Q3_K_M.gguf) | Q3_K_M | 1.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/vinallama-2.7b-chat-sft-v1-GGUF/resolve/main/vinallama-2.7b-chat-sft-v1.Q3_K_L.gguf) | Q3_K_L | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/vinallama-2.7b-chat-sft-v1-GGUF/resolve/main/vinallama-2.7b-chat-sft-v1.IQ4_XS.gguf) | IQ4_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/vinallama-2.7b-chat-sft-v1-GGUF/resolve/main/vinallama-2.7b-chat-sft-v1.Q4_K_S.gguf) | Q4_K_S | 1.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/vinallama-2.7b-chat-sft-v1-GGUF/resolve/main/vinallama-2.7b-chat-sft-v1.Q4_K_M.gguf) | Q4_K_M | 1.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/vinallama-2.7b-chat-sft-v1-GGUF/resolve/main/vinallama-2.7b-chat-sft-v1.Q5_K_S.gguf) | Q5_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/vinallama-2.7b-chat-sft-v1-GGUF/resolve/main/vinallama-2.7b-chat-sft-v1.Q5_K_M.gguf) | Q5_K_M | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/vinallama-2.7b-chat-sft-v1-GGUF/resolve/main/vinallama-2.7b-chat-sft-v1.Q6_K.gguf) | Q6_K | 2.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/vinallama-2.7b-chat-sft-v1-GGUF/resolve/main/vinallama-2.7b-chat-sft-v1.Q8_0.gguf) | Q8_0 | 3.0 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/vinallama-2.7b-chat-sft-v1-GGUF/resolve/main/vinallama-2.7b-chat-sft-v1.f16.gguf) | f16 | 5.7 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + + diff --git a/vinallama-2.7b-chat-sft-v1.IQ4_XS.gguf b/vinallama-2.7b-chat-sft-v1.IQ4_XS.gguf new file mode 100644 index 0000000..f112295 --- /dev/null +++ b/vinallama-2.7b-chat-sft-v1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0622868643b0836fc46bfa3dfd4cc61b10dfe0fa39223f4c602a7e42b2334063 +size 1521090240 diff --git a/vinallama-2.7b-chat-sft-v1.Q2_K.gguf b/vinallama-2.7b-chat-sft-v1.Q2_K.gguf new file mode 100644 index 0000000..35e4b0f --- /dev/null +++ b/vinallama-2.7b-chat-sft-v1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61a021898c930f2083b4ea95303539067134a5b1746e38f75a29e27cd5a31729 +size 1070617536 diff --git a/vinallama-2.7b-chat-sft-v1.Q3_K_L.gguf b/vinallama-2.7b-chat-sft-v1.Q3_K_L.gguf new file mode 100644 index 0000000..e83956c --- /dev/null +++ b/vinallama-2.7b-chat-sft-v1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7483bc87f78ffca23648b170e5fbe5b39d26694b99d6ec33be8f0042a0889b3 +size 1494387008 diff --git a/vinallama-2.7b-chat-sft-v1.Q3_K_M.gguf b/vinallama-2.7b-chat-sft-v1.Q3_K_M.gguf new file mode 100644 index 0000000..dcfd487 --- /dev/null +++ b/vinallama-2.7b-chat-sft-v1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57b30dd252b59a8736e261f43d1fcb7c78e11bdd0fed0dde9f83dfd0da350a25 +size 1377241408 diff --git a/vinallama-2.7b-chat-sft-v1.Q3_K_S.gguf b/vinallama-2.7b-chat-sft-v1.Q3_K_S.gguf new file mode 100644 index 0000000..7ce4fdd --- /dev/null +++ b/vinallama-2.7b-chat-sft-v1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a09dbbc3dcce7755d7dd33cba3cf67ead045332c08e804e7d9d7849e9dc0b38b +size 1240271168 diff --git a/vinallama-2.7b-chat-sft-v1.Q4_K_M.gguf b/vinallama-2.7b-chat-sft-v1.Q4_K_M.gguf new file mode 100644 index 0000000..2d2dc0b --- /dev/null +++ b/vinallama-2.7b-chat-sft-v1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54374c352761b17858e47eff1b69f7db0bcd67c78874882aca1515bc2f8d3433 +size 1693058400 diff --git a/vinallama-2.7b-chat-sft-v1.Q4_K_S.gguf b/vinallama-2.7b-chat-sft-v1.Q4_K_S.gguf new file mode 100644 index 0000000..e266c87 --- /dev/null +++ b/vinallama-2.7b-chat-sft-v1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:374ece9827b679cd327430774467f5749ca960cf86986a6084d3a9a8aefaae0f +size 1605158240 diff --git a/vinallama-2.7b-chat-sft-v1.Q5_K_M.gguf b/vinallama-2.7b-chat-sft-v1.Q5_K_M.gguf new file mode 100644 index 0000000..c7f268f --- /dev/null +++ b/vinallama-2.7b-chat-sft-v1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22f7c9b7c0a2473a90e436ddf855fec02585c5e35c6419b948f8b6bc732f044b +size 1976573920 diff --git a/vinallama-2.7b-chat-sft-v1.Q5_K_S.gguf b/vinallama-2.7b-chat-sft-v1.Q5_K_S.gguf new file mode 100644 index 0000000..c53dde4 --- /dev/null +++ b/vinallama-2.7b-chat-sft-v1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1b165ec4459fd5cdd3a13a65749ea2fce9cd07351675c6ed70ea0d68f219c93 +size 1925046240 diff --git a/vinallama-2.7b-chat-sft-v1.Q6_K.gguf b/vinallama-2.7b-chat-sft-v1.Q6_K.gguf new file mode 100644 index 0000000..930907e --- /dev/null +++ b/vinallama-2.7b-chat-sft-v1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bef14a3f779e3a30a95020b12a6eb12973b408e4ba11d720407e690fd750b75 +size 2277809184 diff --git a/vinallama-2.7b-chat-sft-v1.Q8_0.gguf b/vinallama-2.7b-chat-sft-v1.Q8_0.gguf new file mode 100644 index 0000000..1414317 --- /dev/null +++ b/vinallama-2.7b-chat-sft-v1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85d1be4cc83772762ef67ab8175efa4d63cfcb1f0e915fedcdf5fc38742c1862 +size 2949792416 diff --git a/vinallama-2.7b-chat-sft-v1.f16.gguf b/vinallama-2.7b-chat-sft-v1.f16.gguf new file mode 100644 index 0000000..81c5138 --- /dev/null +++ b/vinallama-2.7b-chat-sft-v1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e568662525f2d7876df183f74397ff6b1ef2b3a03be26f77ad4754450d4e0cf6 +size 5551018016