From 64e78f25b533472e4acedd1a355de6892d3575ad Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Mon, 5 Oct 2026 14:19:17 +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/Final-Llama-Code-1L-GGUF Source: Original Platform --- .gitattributes | 47 ++++++++++++++++++++++++ Final-Llama-Code-1L.IQ4_XS.gguf | 3 ++ Final-Llama-Code-1L.Q2_K.gguf | 3 ++ Final-Llama-Code-1L.Q3_K_L.gguf | 3 ++ Final-Llama-Code-1L.Q3_K_M.gguf | 3 ++ Final-Llama-Code-1L.Q3_K_S.gguf | 3 ++ Final-Llama-Code-1L.Q4_K_M.gguf | 3 ++ Final-Llama-Code-1L.Q4_K_S.gguf | 3 ++ Final-Llama-Code-1L.Q5_K_M.gguf | 3 ++ Final-Llama-Code-1L.Q5_K_S.gguf | 3 ++ Final-Llama-Code-1L.Q6_K.gguf | 3 ++ Final-Llama-Code-1L.Q8_0.gguf | 3 ++ Final-Llama-Code-1L.f16.gguf | 3 ++ README.md | 64 +++++++++++++++++++++++++++++++++ 14 files changed, 147 insertions(+) create mode 100644 .gitattributes create mode 100644 Final-Llama-Code-1L.IQ4_XS.gguf create mode 100644 Final-Llama-Code-1L.Q2_K.gguf create mode 100644 Final-Llama-Code-1L.Q3_K_L.gguf create mode 100644 Final-Llama-Code-1L.Q3_K_M.gguf create mode 100644 Final-Llama-Code-1L.Q3_K_S.gguf create mode 100644 Final-Llama-Code-1L.Q4_K_M.gguf create mode 100644 Final-Llama-Code-1L.Q4_K_S.gguf create mode 100644 Final-Llama-Code-1L.Q5_K_M.gguf create mode 100644 Final-Llama-Code-1L.Q5_K_S.gguf create mode 100644 Final-Llama-Code-1L.Q6_K.gguf create mode 100644 Final-Llama-Code-1L.Q8_0.gguf create mode 100644 Final-Llama-Code-1L.f16.gguf create mode 100644 README.md diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..54bebd4 --- /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 +Final-Llama-Code-1L.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Final-Llama-Code-1L.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Final-Llama-Code-1L.f16.gguf filter=lfs diff=lfs merge=lfs -text +Final-Llama-Code-1L.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Final-Llama-Code-1L.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Final-Llama-Code-1L.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Final-Llama-Code-1L.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Final-Llama-Code-1L.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Final-Llama-Code-1L.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Final-Llama-Code-1L.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Final-Llama-Code-1L.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Final-Llama-Code-1L.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Final-Llama-Code-1L.IQ4_XS.gguf b/Final-Llama-Code-1L.IQ4_XS.gguf new file mode 100644 index 0000000..c211fbb --- /dev/null +++ b/Final-Llama-Code-1L.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f39d28e85c605719a92b09a34a12f72679d444c1b0479d777bab9868bff5d77 +size 4484367712 diff --git a/Final-Llama-Code-1L.Q2_K.gguf b/Final-Llama-Code-1L.Q2_K.gguf new file mode 100644 index 0000000..392d362 --- /dev/null +++ b/Final-Llama-Code-1L.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff62c432b8a9bcf65e3c48e3b65fd6883c08ee23e8993720a85186ff981a6443 +size 3179136352 diff --git a/Final-Llama-Code-1L.Q3_K_L.gguf b/Final-Llama-Code-1L.Q3_K_L.gguf new file mode 100644 index 0000000..a81fe8f --- /dev/null +++ b/Final-Llama-Code-1L.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b60165e0f03dc889a9903139c06534e13c2088f7ac5ccada09044f9141bc080 +size 4321961312 diff --git a/Final-Llama-Code-1L.Q3_K_M.gguf b/Final-Llama-Code-1L.Q3_K_M.gguf new file mode 100644 index 0000000..af4d8b3 --- /dev/null +++ b/Final-Llama-Code-1L.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a37d5a065303aae4e5d13edb30664f56be3c496c3e4b4c9549277ce94a0258d +size 4018922848 diff --git a/Final-Llama-Code-1L.Q3_K_S.gguf b/Final-Llama-Code-1L.Q3_K_S.gguf new file mode 100644 index 0000000..4f6cffe --- /dev/null +++ b/Final-Llama-Code-1L.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bf2096ae54d9f4c68f1ce409c2a1073281297beb81beaf1d2812f93cd798440 +size 3664504160 diff --git a/Final-Llama-Code-1L.Q4_K_M.gguf b/Final-Llama-Code-1L.Q4_K_M.gguf new file mode 100644 index 0000000..7dfe820 --- /dev/null +++ b/Final-Llama-Code-1L.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:760eaae7a94938eb4f45b316b9c9c4f4812380c6845c915970d1b03c6ce083c4 +size 4920739168 diff --git a/Final-Llama-Code-1L.Q4_K_S.gguf b/Final-Llama-Code-1L.Q4_K_S.gguf new file mode 100644 index 0000000..4e59636 --- /dev/null +++ b/Final-Llama-Code-1L.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb88f74b22dfe36a7884e3c50ef041165c314cf8fe68f4f7518edc0464e36f09 +size 4692673888 diff --git a/Final-Llama-Code-1L.Q5_K_M.gguf b/Final-Llama-Code-1L.Q5_K_M.gguf new file mode 100644 index 0000000..b80f213 --- /dev/null +++ b/Final-Llama-Code-1L.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92d4087f4d7638a2e1e87eb3ef2eb6cdf03f3b5bb4cffeba63f361fe5d271336 +size 5732992352 diff --git a/Final-Llama-Code-1L.Q5_K_S.gguf b/Final-Llama-Code-1L.Q5_K_S.gguf new file mode 100644 index 0000000..c090093 --- /dev/null +++ b/Final-Llama-Code-1L.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0a8a4257eab084083d1b01be287a56d4d364828c1141b11d810a18d5cb0f825 +size 5599298912 diff --git a/Final-Llama-Code-1L.Q6_K.gguf b/Final-Llama-Code-1L.Q6_K.gguf new file mode 100644 index 0000000..07531fa --- /dev/null +++ b/Final-Llama-Code-1L.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0137831479faefbc9fd967e5ae4157ebc1cb19156dd2881476393b2881f85ab +size 6596011360 diff --git a/Final-Llama-Code-1L.Q8_0.gguf b/Final-Llama-Code-1L.Q8_0.gguf new file mode 100644 index 0000000..d8ebd27 --- /dev/null +++ b/Final-Llama-Code-1L.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3080217fb7866140ce9402faccbaf79df47cd45d56f7bfb5e1c36b338c99b71f +size 8540775776 diff --git a/Final-Llama-Code-1L.f16.gguf b/Final-Llama-Code-1L.f16.gguf new file mode 100644 index 0000000..0dbe45c --- /dev/null +++ b/Final-Llama-Code-1L.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec4c9682269311bb155199658cca3760c946a6c56c59b1454e2a0f6266380f84 +size 16068896096 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d5fb2c8 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: psyonp/Final-Llama-Code-1L +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/psyonp/Final-Llama-Code-1L + + +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/Final-Llama-Code-1L-GGUF/resolve/main/Final-Llama-Code-1L.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Final-Llama-Code-1L-GGUF/resolve/main/Final-Llama-Code-1L.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Final-Llama-Code-1L-GGUF/resolve/main/Final-Llama-Code-1L.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Final-Llama-Code-1L-GGUF/resolve/main/Final-Llama-Code-1L.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Final-Llama-Code-1L-GGUF/resolve/main/Final-Llama-Code-1L.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Final-Llama-Code-1L-GGUF/resolve/main/Final-Llama-Code-1L.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Final-Llama-Code-1L-GGUF/resolve/main/Final-Llama-Code-1L.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Final-Llama-Code-1L-GGUF/resolve/main/Final-Llama-Code-1L.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Final-Llama-Code-1L-GGUF/resolve/main/Final-Llama-Code-1L.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Final-Llama-Code-1L-GGUF/resolve/main/Final-Llama-Code-1L.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Final-Llama-Code-1L-GGUF/resolve/main/Final-Llama-Code-1L.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Final-Llama-Code-1L-GGUF/resolve/main/Final-Llama-Code-1L.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. + +