commit a505c1b56f0a6959ce8fafb99afdc947bbc5ea0c Author: ModelHub XC Date: Mon Sep 21 06:02:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/codellama-7b-tofutune-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9bd367b --- /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 +codellama-7b-tofutune.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +codellama-7b-tofutune.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +codellama-7b-tofutune.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +codellama-7b-tofutune.f16.gguf filter=lfs diff=lfs merge=lfs -text +codellama-7b-tofutune.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +codellama-7b-tofutune.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +codellama-7b-tofutune.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +codellama-7b-tofutune.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +codellama-7b-tofutune.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +codellama-7b-tofutune.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +codellama-7b-tofutune.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +codellama-7b-tofutune.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +codellama-7b-tofutune.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +codellama-7b-tofutune.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +codellama-7b-tofutune.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..af5c512 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: simonbutt/codellama-7b-tofutune +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/simonbutt/codellama-7b-tofutune + + +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/codellama-7b-tofutune-GGUF/resolve/main/codellama-7b-tofutune.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/codellama-7b-tofutune-GGUF/resolve/main/codellama-7b-tofutune.IQ3_XS.gguf) | IQ3_XS | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/codellama-7b-tofutune-GGUF/resolve/main/codellama-7b-tofutune.IQ3_S.gguf) | IQ3_S | 3.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/codellama-7b-tofutune-GGUF/resolve/main/codellama-7b-tofutune.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/codellama-7b-tofutune-GGUF/resolve/main/codellama-7b-tofutune.IQ3_M.gguf) | IQ3_M | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/codellama-7b-tofutune-GGUF/resolve/main/codellama-7b-tofutune.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/codellama-7b-tofutune-GGUF/resolve/main/codellama-7b-tofutune.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/codellama-7b-tofutune-GGUF/resolve/main/codellama-7b-tofutune.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/codellama-7b-tofutune-GGUF/resolve/main/codellama-7b-tofutune.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/codellama-7b-tofutune-GGUF/resolve/main/codellama-7b-tofutune.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/codellama-7b-tofutune-GGUF/resolve/main/codellama-7b-tofutune.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/codellama-7b-tofutune-GGUF/resolve/main/codellama-7b-tofutune.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/codellama-7b-tofutune-GGUF/resolve/main/codellama-7b-tofutune.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/codellama-7b-tofutune-GGUF/resolve/main/codellama-7b-tofutune.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/codellama-7b-tofutune-GGUF/resolve/main/codellama-7b-tofutune.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. + + diff --git a/codellama-7b-tofutune.IQ3_M.gguf b/codellama-7b-tofutune.IQ3_M.gguf new file mode 100644 index 0000000..a2b603c --- /dev/null +++ b/codellama-7b-tofutune.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e3c35625eaa713702ecada26162cbcc85822677b82844faaffb265c705d6d4d +size 3114947584 diff --git a/codellama-7b-tofutune.IQ3_S.gguf b/codellama-7b-tofutune.IQ3_S.gguf new file mode 100644 index 0000000..ca49043 --- /dev/null +++ b/codellama-7b-tofutune.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e7430499f4954fc3cc6faacb522196809901fba1107c5dbb34710cb4a9a6536 +size 2948387840 diff --git a/codellama-7b-tofutune.IQ3_XS.gguf b/codellama-7b-tofutune.IQ3_XS.gguf new file mode 100644 index 0000000..7e275c5 --- /dev/null +++ b/codellama-7b-tofutune.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a47643254a8de661c07ffe12c2506fc967368a7d30ec211bf5d8c142d7c6136 +size 2796606464 diff --git a/codellama-7b-tofutune.IQ4_XS.gguf b/codellama-7b-tofutune.IQ4_XS.gguf new file mode 100644 index 0000000..2e48788 --- /dev/null +++ b/codellama-7b-tofutune.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00a30eb1bd15e647644d82c9c6c5ba91c0542a4fce3663bcb757261a60e482cb +size 3647606272 diff --git a/codellama-7b-tofutune.Q2_K.gguf b/codellama-7b-tofutune.Q2_K.gguf new file mode 100644 index 0000000..db7d574 --- /dev/null +++ b/codellama-7b-tofutune.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbb3d760435960f7ce3e117adfed462db552e727968fde3c115e6033cf786dde +size 2532940288 diff --git a/codellama-7b-tofutune.Q3_K_L.gguf b/codellama-7b-tofutune.Q3_K_L.gguf new file mode 100644 index 0000000..13edc4c --- /dev/null +++ b/codellama-7b-tofutune.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a8b76ef5fa04381875a8c579dbb711d58532b0f30931cceadd4aa319f66bd40 +size 3597194240 diff --git a/codellama-7b-tofutune.Q3_K_M.gguf b/codellama-7b-tofutune.Q3_K_M.gguf new file mode 100644 index 0000000..48f5df6 --- /dev/null +++ b/codellama-7b-tofutune.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d17f2cf49b872fc8b2b63bc719025489d054942e361f208aa0090bd2ad234ed0 +size 3298087936 diff --git a/codellama-7b-tofutune.Q3_K_S.gguf b/codellama-7b-tofutune.Q3_K_S.gguf new file mode 100644 index 0000000..d370845 --- /dev/null +++ b/codellama-7b-tofutune.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5be31875d2c8022c6a755fba273add35bf14e726003a61742c44aabf14f7568 +size 2948387840 diff --git a/codellama-7b-tofutune.Q4_K_M.gguf b/codellama-7b-tofutune.Q4_K_M.gguf new file mode 100644 index 0000000..ec076da --- /dev/null +++ b/codellama-7b-tofutune.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c4120aa23158570a360ab8256fc6c1064599489a95c179831008e2b679d9734 +size 4081096192 diff --git a/codellama-7b-tofutune.Q4_K_S.gguf b/codellama-7b-tofutune.Q4_K_S.gguf new file mode 100644 index 0000000..0605d3f --- /dev/null +++ b/codellama-7b-tofutune.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a828e9f0f3c0443ed13adc408e41c876181cea1cb86dcfa23db8721bd5ae147 +size 3856832000 diff --git a/codellama-7b-tofutune.Q5_K_M.gguf b/codellama-7b-tofutune.Q5_K_M.gguf new file mode 100644 index 0000000..74d4bf6 --- /dev/null +++ b/codellama-7b-tofutune.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7960f8fff17b649277d975f2fdf6dc982f78a20c1ba62bb0091e6b7663af06c2 +size 4783257088 diff --git a/codellama-7b-tofutune.Q5_K_S.gguf b/codellama-7b-tofutune.Q5_K_S.gguf new file mode 100644 index 0000000..4a54613 --- /dev/null +++ b/codellama-7b-tofutune.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7afc33aebc84f081d0aaf812fd3194cfd7f48673de14387a433919a9af5bf0c4 +size 4651791872 diff --git a/codellama-7b-tofutune.Q6_K.gguf b/codellama-7b-tofutune.Q6_K.gguf new file mode 100644 index 0000000..4017ee8 --- /dev/null +++ b/codellama-7b-tofutune.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57c55204e5e0323b8447b51b2d2763d7a07466ac067d2862025b684b6194a0f2 +size 5529303040 diff --git a/codellama-7b-tofutune.Q8_0.gguf b/codellama-7b-tofutune.Q8_0.gguf new file mode 100644 index 0000000..78941a8 --- /dev/null +++ b/codellama-7b-tofutune.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2222f9658bf7d3c2a082947001a6d6a376ca7ba9dded7f1a86d314875229d719 +size 7161230336 diff --git a/codellama-7b-tofutune.f16.gguf b/codellama-7b-tofutune.f16.gguf new file mode 100644 index 0000000..7d4582e --- /dev/null +++ b/codellama-7b-tofutune.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9600f0d8a804c6628c5fb4a9508a4d5d0dd3ca0b2847b2f010f90b802a8824b6 +size 13478368256