From 934a0333d60d0533a55523cb6effa53cf4b0066c Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Mon, 1 Jun 2026 18:00:24 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: mradermacher/Llama-SMUGRI-7B-Instruct-MTI-GGUF Source: Original Platform --- .gitattributes | 47 +++++++++++++++ Llama-SMUGRI-7B-Instruct-MTI.IQ4_XS.gguf | 3 + Llama-SMUGRI-7B-Instruct-MTI.Q2_K.gguf | 3 + Llama-SMUGRI-7B-Instruct-MTI.Q3_K_L.gguf | 3 + Llama-SMUGRI-7B-Instruct-MTI.Q3_K_M.gguf | 3 + Llama-SMUGRI-7B-Instruct-MTI.Q3_K_S.gguf | 3 + Llama-SMUGRI-7B-Instruct-MTI.Q4_K_M.gguf | 3 + Llama-SMUGRI-7B-Instruct-MTI.Q4_K_S.gguf | 3 + Llama-SMUGRI-7B-Instruct-MTI.Q5_K_M.gguf | 3 + Llama-SMUGRI-7B-Instruct-MTI.Q5_K_S.gguf | 3 + Llama-SMUGRI-7B-Instruct-MTI.Q6_K.gguf | 3 + Llama-SMUGRI-7B-Instruct-MTI.Q8_0.gguf | 3 + Llama-SMUGRI-7B-Instruct-MTI.f16.gguf | 3 + README.md | 73 ++++++++++++++++++++++++ 14 files changed, 156 insertions(+) create mode 100644 .gitattributes create mode 100644 Llama-SMUGRI-7B-Instruct-MTI.IQ4_XS.gguf create mode 100644 Llama-SMUGRI-7B-Instruct-MTI.Q2_K.gguf create mode 100644 Llama-SMUGRI-7B-Instruct-MTI.Q3_K_L.gguf create mode 100644 Llama-SMUGRI-7B-Instruct-MTI.Q3_K_M.gguf create mode 100644 Llama-SMUGRI-7B-Instruct-MTI.Q3_K_S.gguf create mode 100644 Llama-SMUGRI-7B-Instruct-MTI.Q4_K_M.gguf create mode 100644 Llama-SMUGRI-7B-Instruct-MTI.Q4_K_S.gguf create mode 100644 Llama-SMUGRI-7B-Instruct-MTI.Q5_K_M.gguf create mode 100644 Llama-SMUGRI-7B-Instruct-MTI.Q5_K_S.gguf create mode 100644 Llama-SMUGRI-7B-Instruct-MTI.Q6_K.gguf create mode 100644 Llama-SMUGRI-7B-Instruct-MTI.Q8_0.gguf create mode 100644 Llama-SMUGRI-7B-Instruct-MTI.f16.gguf create mode 100644 README.md diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3a911ba --- /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 +Llama-SMUGRI-7B-Instruct-MTI.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-SMUGRI-7B-Instruct-MTI.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-SMUGRI-7B-Instruct-MTI.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-SMUGRI-7B-Instruct-MTI.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-SMUGRI-7B-Instruct-MTI.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-SMUGRI-7B-Instruct-MTI.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-SMUGRI-7B-Instruct-MTI.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-SMUGRI-7B-Instruct-MTI.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-SMUGRI-7B-Instruct-MTI.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-SMUGRI-7B-Instruct-MTI.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-SMUGRI-7B-Instruct-MTI.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-SMUGRI-7B-Instruct-MTI.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-SMUGRI-7B-Instruct-MTI.IQ4_XS.gguf b/Llama-SMUGRI-7B-Instruct-MTI.IQ4_XS.gguf new file mode 100644 index 0000000..0424d9a --- /dev/null +++ b/Llama-SMUGRI-7B-Instruct-MTI.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11919beb52cea5de538fd22c1e347db87aba28dc276585ca91baa331c30b77f9 +size 3647518240 diff --git a/Llama-SMUGRI-7B-Instruct-MTI.Q2_K.gguf b/Llama-SMUGRI-7B-Instruct-MTI.Q2_K.gguf new file mode 100644 index 0000000..df8fe20 --- /dev/null +++ b/Llama-SMUGRI-7B-Instruct-MTI.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58622653390e2684a0a387d861a6461cc065a587a7d2c2b666ca3aaf173eeb6d +size 2532865568 diff --git a/Llama-SMUGRI-7B-Instruct-MTI.Q3_K_L.gguf b/Llama-SMUGRI-7B-Instruct-MTI.Q3_K_L.gguf new file mode 100644 index 0000000..c1fc8c5 --- /dev/null +++ b/Llama-SMUGRI-7B-Instruct-MTI.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e90df3cd3912928720bc92870359e281aa86a9d708a32febe54817a6d201ca11 +size 3597112864 diff --git a/Llama-SMUGRI-7B-Instruct-MTI.Q3_K_M.gguf b/Llama-SMUGRI-7B-Instruct-MTI.Q3_K_M.gguf new file mode 100644 index 0000000..6cc54af --- /dev/null +++ b/Llama-SMUGRI-7B-Instruct-MTI.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4616c66a4223d9e972ae36c718bf30f3f4dca71f1eb72840d32a6ff8bba8f30d +size 3298006560 diff --git a/Llama-SMUGRI-7B-Instruct-MTI.Q3_K_S.gguf b/Llama-SMUGRI-7B-Instruct-MTI.Q3_K_S.gguf new file mode 100644 index 0000000..f6d44e4 --- /dev/null +++ b/Llama-SMUGRI-7B-Instruct-MTI.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62e55916630df31e026c333ea98ec91abff7c8caad2e12a86e6cd86cbe100bbe +size 2948306464 diff --git a/Llama-SMUGRI-7B-Instruct-MTI.Q4_K_M.gguf b/Llama-SMUGRI-7B-Instruct-MTI.Q4_K_M.gguf new file mode 100644 index 0000000..7e4c418 --- /dev/null +++ b/Llama-SMUGRI-7B-Instruct-MTI.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8928346b6b78c9ab0a32ce31c1f82f1e770df9e2bcb37f7f1e8fd65757f586c0 +size 4081006112 diff --git a/Llama-SMUGRI-7B-Instruct-MTI.Q4_K_S.gguf b/Llama-SMUGRI-7B-Instruct-MTI.Q4_K_S.gguf new file mode 100644 index 0000000..5977d7c --- /dev/null +++ b/Llama-SMUGRI-7B-Instruct-MTI.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0534f76d20e0db5afdeb3c2e201ce3f6aadb1c1c8afd44fe71c44ccf1d776a22 +size 3856741920 diff --git a/Llama-SMUGRI-7B-Instruct-MTI.Q5_K_M.gguf b/Llama-SMUGRI-7B-Instruct-MTI.Q5_K_M.gguf new file mode 100644 index 0000000..6020bd1 --- /dev/null +++ b/Llama-SMUGRI-7B-Instruct-MTI.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c0f4068796e04606ae081cbd9bf81f2af78722f612954594b90ab89c175e3a3 +size 4783158816 diff --git a/Llama-SMUGRI-7B-Instruct-MTI.Q5_K_S.gguf b/Llama-SMUGRI-7B-Instruct-MTI.Q5_K_S.gguf new file mode 100644 index 0000000..c471dec --- /dev/null +++ b/Llama-SMUGRI-7B-Instruct-MTI.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1822b764caac687c27f960805f51654366878980465a9c600e5b82903dfcb74c +size 4651693600 diff --git a/Llama-SMUGRI-7B-Instruct-MTI.Q6_K.gguf b/Llama-SMUGRI-7B-Instruct-MTI.Q6_K.gguf new file mode 100644 index 0000000..2b2e746 --- /dev/null +++ b/Llama-SMUGRI-7B-Instruct-MTI.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:708e517a2fc7bb55856210b7a201f9adebb89e667469fab5f446a277edcaffab +size 5529196064 diff --git a/Llama-SMUGRI-7B-Instruct-MTI.Q8_0.gguf b/Llama-SMUGRI-7B-Instruct-MTI.Q8_0.gguf new file mode 100644 index 0000000..2877cce --- /dev/null +++ b/Llama-SMUGRI-7B-Instruct-MTI.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:473a3ecfb9a2aa69664c4c18c02a4fd1650fd00395551f73d56fffa49bf45026 +size 7161091616 diff --git a/Llama-SMUGRI-7B-Instruct-MTI.f16.gguf b/Llama-SMUGRI-7B-Instruct-MTI.f16.gguf new file mode 100644 index 0000000..c345683 --- /dev/null +++ b/Llama-SMUGRI-7B-Instruct-MTI.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a57741dcdefaf1bdb21c19f56e84fca3aa702f1569aca41068d23b6da63b8e8 +size 13478106656 diff --git a/README.md b/README.md new file mode 100644 index 0000000..88643b5 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: tartuNLP/Llama-SMUGRI-7B-Instruct-MTI +language: +- kv +- vro +- liv +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/tartuNLP/Llama-SMUGRI-7B-Instruct-MTI + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-SMUGRI-7B-Instruct-MTI-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-SMUGRI-7B-Instruct-MTI-i1-GGUF +## 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/Llama-SMUGRI-7B-Instruct-MTI-GGUF/resolve/main/Llama-SMUGRI-7B-Instruct-MTI.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-SMUGRI-7B-Instruct-MTI-GGUF/resolve/main/Llama-SMUGRI-7B-Instruct-MTI.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-SMUGRI-7B-Instruct-MTI-GGUF/resolve/main/Llama-SMUGRI-7B-Instruct-MTI.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-SMUGRI-7B-Instruct-MTI-GGUF/resolve/main/Llama-SMUGRI-7B-Instruct-MTI.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-SMUGRI-7B-Instruct-MTI-GGUF/resolve/main/Llama-SMUGRI-7B-Instruct-MTI.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-SMUGRI-7B-Instruct-MTI-GGUF/resolve/main/Llama-SMUGRI-7B-Instruct-MTI.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-SMUGRI-7B-Instruct-MTI-GGUF/resolve/main/Llama-SMUGRI-7B-Instruct-MTI.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-SMUGRI-7B-Instruct-MTI-GGUF/resolve/main/Llama-SMUGRI-7B-Instruct-MTI.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-SMUGRI-7B-Instruct-MTI-GGUF/resolve/main/Llama-SMUGRI-7B-Instruct-MTI.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-SMUGRI-7B-Instruct-MTI-GGUF/resolve/main/Llama-SMUGRI-7B-Instruct-MTI.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-SMUGRI-7B-Instruct-MTI-GGUF/resolve/main/Llama-SMUGRI-7B-Instruct-MTI.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-SMUGRI-7B-Instruct-MTI-GGUF/resolve/main/Llama-SMUGRI-7B-Instruct-MTI.f16.gguf) | f16 | 13.6 | 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. + +