From 42efe9ded961dd4dcaf94e30d1976d6caee605f0 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Thu, 27 Aug 2026 11:32:17 +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-3.1-Pro-Coder-v1-GGUF Source: Original Platform --- .gitattributes | 46 +++++++++++++++++ Llama-3.1-Pro-Coder-v1.IQ4_XS.gguf | 3 ++ Llama-3.1-Pro-Coder-v1.Q2_K.gguf | 3 ++ Llama-3.1-Pro-Coder-v1.Q3_K_L.gguf | 3 ++ Llama-3.1-Pro-Coder-v1.Q3_K_M.gguf | 3 ++ Llama-3.1-Pro-Coder-v1.Q3_K_S.gguf | 3 ++ Llama-3.1-Pro-Coder-v1.Q4_K_M.gguf | 3 ++ Llama-3.1-Pro-Coder-v1.Q4_K_S.gguf | 3 ++ Llama-3.1-Pro-Coder-v1.Q5_K_M.gguf | 3 ++ Llama-3.1-Pro-Coder-v1.Q5_K_S.gguf | 3 ++ Llama-3.1-Pro-Coder-v1.Q6_K.gguf | 3 ++ Llama-3.1-Pro-Coder-v1.Q8_0.gguf | 3 ++ Llama-3.1-Pro-Coder-v1.f16.gguf | 3 ++ README.md | 82 ++++++++++++++++++++++++++++++ 14 files changed, 164 insertions(+) create mode 100644 .gitattributes create mode 100644 Llama-3.1-Pro-Coder-v1.IQ4_XS.gguf create mode 100644 Llama-3.1-Pro-Coder-v1.Q2_K.gguf create mode 100644 Llama-3.1-Pro-Coder-v1.Q3_K_L.gguf create mode 100644 Llama-3.1-Pro-Coder-v1.Q3_K_M.gguf create mode 100644 Llama-3.1-Pro-Coder-v1.Q3_K_S.gguf create mode 100644 Llama-3.1-Pro-Coder-v1.Q4_K_M.gguf create mode 100644 Llama-3.1-Pro-Coder-v1.Q4_K_S.gguf create mode 100644 Llama-3.1-Pro-Coder-v1.Q5_K_M.gguf create mode 100644 Llama-3.1-Pro-Coder-v1.Q5_K_S.gguf create mode 100644 Llama-3.1-Pro-Coder-v1.Q6_K.gguf create mode 100644 Llama-3.1-Pro-Coder-v1.Q8_0.gguf create mode 100644 Llama-3.1-Pro-Coder-v1.f16.gguf create mode 100644 README.md diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7b9256e --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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-3.1-Pro-Coder-v1.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Pro-Coder-v1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Pro-Coder-v1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Pro-Coder-v1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Pro-Coder-v1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Pro-Coder-v1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Pro-Coder-v1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Pro-Coder-v1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Pro-Coder-v1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Pro-Coder-v1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Pro-Coder-v1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-Pro-Coder-v1.IQ4_XS.gguf b/Llama-3.1-Pro-Coder-v1.IQ4_XS.gguf new file mode 100644 index 0000000..82ce94f --- /dev/null +++ b/Llama-3.1-Pro-Coder-v1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04129c997840a5ca186a23ae0298d55a44deb0bfa651dcfd468c975d12b0112f +size 4484368512 diff --git a/Llama-3.1-Pro-Coder-v1.Q2_K.gguf b/Llama-3.1-Pro-Coder-v1.Q2_K.gguf new file mode 100644 index 0000000..f4283a0 --- /dev/null +++ b/Llama-3.1-Pro-Coder-v1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03759a2200ef41637372d6f1a73c367690c4e6364e5527d9dc24e9b79788be6b +size 3179137152 diff --git a/Llama-3.1-Pro-Coder-v1.Q3_K_L.gguf b/Llama-3.1-Pro-Coder-v1.Q3_K_L.gguf new file mode 100644 index 0000000..806300a --- /dev/null +++ b/Llama-3.1-Pro-Coder-v1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:917891d31dd909503f7b8c8c37e47a84e6c253e38b5c9f5bf3f2198665f47e13 +size 4321962112 diff --git a/Llama-3.1-Pro-Coder-v1.Q3_K_M.gguf b/Llama-3.1-Pro-Coder-v1.Q3_K_M.gguf new file mode 100644 index 0000000..db77adf --- /dev/null +++ b/Llama-3.1-Pro-Coder-v1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65089cb0c0515c3a5f7722b7f3fd4b5bae0f276338e3c0b7b1c04d4390bf331f +size 4018923648 diff --git a/Llama-3.1-Pro-Coder-v1.Q3_K_S.gguf b/Llama-3.1-Pro-Coder-v1.Q3_K_S.gguf new file mode 100644 index 0000000..fe78aeb --- /dev/null +++ b/Llama-3.1-Pro-Coder-v1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93f5612deab10ccf023f5aa98991d09a8c2bc1292e000bb137b5f481301fba2e +size 3664504960 diff --git a/Llama-3.1-Pro-Coder-v1.Q4_K_M.gguf b/Llama-3.1-Pro-Coder-v1.Q4_K_M.gguf new file mode 100644 index 0000000..e407266 --- /dev/null +++ b/Llama-3.1-Pro-Coder-v1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cc4934fb952da20ef4f4bf6f66964471b0afd5cfe8277f4cc3d7a45dac1e906 +size 4920739968 diff --git a/Llama-3.1-Pro-Coder-v1.Q4_K_S.gguf b/Llama-3.1-Pro-Coder-v1.Q4_K_S.gguf new file mode 100644 index 0000000..b0d43e2 --- /dev/null +++ b/Llama-3.1-Pro-Coder-v1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd47d0c549c1eeaca0da0c9b6cf0d6c425e5917dde674f46d80e9de36aa2eff9 +size 4692674688 diff --git a/Llama-3.1-Pro-Coder-v1.Q5_K_M.gguf b/Llama-3.1-Pro-Coder-v1.Q5_K_M.gguf new file mode 100644 index 0000000..d1994ed --- /dev/null +++ b/Llama-3.1-Pro-Coder-v1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:428bc48a5dc459f5a0745be0fd2b8005570da2007e71c895c84a41c98f2e236f +size 5732993152 diff --git a/Llama-3.1-Pro-Coder-v1.Q5_K_S.gguf b/Llama-3.1-Pro-Coder-v1.Q5_K_S.gguf new file mode 100644 index 0000000..99c24d9 --- /dev/null +++ b/Llama-3.1-Pro-Coder-v1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d643a08789af7669b465050e7edab8c6380cef15bbb2072f3d3f8e4cf5df2c2c +size 5599299712 diff --git a/Llama-3.1-Pro-Coder-v1.Q6_K.gguf b/Llama-3.1-Pro-Coder-v1.Q6_K.gguf new file mode 100644 index 0000000..1d74d21 --- /dev/null +++ b/Llama-3.1-Pro-Coder-v1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0854f2ce00e76595dbae545f16f402f1f9ff17fe06405b0c93cc3bfd73f8e23c +size 6596012160 diff --git a/Llama-3.1-Pro-Coder-v1.Q8_0.gguf b/Llama-3.1-Pro-Coder-v1.Q8_0.gguf new file mode 100644 index 0000000..9046b6a --- /dev/null +++ b/Llama-3.1-Pro-Coder-v1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8131d79799ed1cad5572c62347a05767893b58c7c4e6e6ea7bce9147a648af03 +size 8540776576 diff --git a/Llama-3.1-Pro-Coder-v1.f16.gguf b/Llama-3.1-Pro-Coder-v1.f16.gguf new file mode 100644 index 0000000..70e67fa --- /dev/null +++ b/Llama-3.1-Pro-Coder-v1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:417eca16821367f29979275e1aa7d632c100b3788a525435b0b8921b59478bef +size 16068896896 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f06c6b5 --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: HemanthKari/Llama-3.1-Pro-Coder-v1 +language: +- en +library_name: transformers +license: llama3.1 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- code +- coding +- llama +- llama-3.1 +- fine-tuned +- python +- java +- javascript +- sql +--- +## About + + + + + + + + + +static quants of https://huggingface.co/HemanthKari/Llama-3.1-Pro-Coder-v1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.1-Pro-Coder-v1-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.1-Pro-Coder-v1-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-3.1-Pro-Coder-v1-GGUF/resolve/main/Llama-3.1-Pro-Coder-v1.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Pro-Coder-v1-GGUF/resolve/main/Llama-3.1-Pro-Coder-v1.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Pro-Coder-v1-GGUF/resolve/main/Llama-3.1-Pro-Coder-v1.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Pro-Coder-v1-GGUF/resolve/main/Llama-3.1-Pro-Coder-v1.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Pro-Coder-v1-GGUF/resolve/main/Llama-3.1-Pro-Coder-v1.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Pro-Coder-v1-GGUF/resolve/main/Llama-3.1-Pro-Coder-v1.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Pro-Coder-v1-GGUF/resolve/main/Llama-3.1-Pro-Coder-v1.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Pro-Coder-v1-GGUF/resolve/main/Llama-3.1-Pro-Coder-v1.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Pro-Coder-v1-GGUF/resolve/main/Llama-3.1-Pro-Coder-v1.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Pro-Coder-v1-GGUF/resolve/main/Llama-3.1-Pro-Coder-v1.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Pro-Coder-v1-GGUF/resolve/main/Llama-3.1-Pro-Coder-v1.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Pro-Coder-v1-GGUF/resolve/main/Llama-3.1-Pro-Coder-v1.f16.gguf) | f16 | 16.2 | 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. + +