commit 700e01c40cf0f96e7d1c0b96e3528b3455042e47 Author: ModelHub XC Date: Fri Jul 31 13:36:04 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-8B-Instruct-Coder-v2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..72f2c4d --- /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 +Llama-3-8B-Instruct-Coder-v2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Coder-v2.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Coder-v2.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Coder-v2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Coder-v2.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Coder-v2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Coder-v2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Coder-v2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Coder-v2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Coder-v2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Coder-v2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Coder-v2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Coder-v2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Coder-v2.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Coder-v2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-8B-Instruct-Coder-v2.IQ3_M.gguf b/Llama-3-8B-Instruct-Coder-v2.IQ3_M.gguf new file mode 100644 index 0000000..aecb115 --- /dev/null +++ b/Llama-3-8B-Instruct-Coder-v2.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:add570de3815da4cfd6f013e7d97b39d91e6d11dc052813e8c4b293bc925c6ce +size 3784823584 diff --git a/Llama-3-8B-Instruct-Coder-v2.IQ3_S.gguf b/Llama-3-8B-Instruct-Coder-v2.IQ3_S.gguf new file mode 100644 index 0000000..b10afea --- /dev/null +++ b/Llama-3-8B-Instruct-Coder-v2.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac5388f569000a6f9bb41aca3d942920be2f2c3c576e46b4a42d044f0554c5b4 +size 3682325280 diff --git a/Llama-3-8B-Instruct-Coder-v2.IQ3_XS.gguf b/Llama-3-8B-Instruct-Coder-v2.IQ3_XS.gguf new file mode 100644 index 0000000..bcf1ac8 --- /dev/null +++ b/Llama-3-8B-Instruct-Coder-v2.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:265a6116e9375db00d257290c3a8f450f3441ba96732413371f8dbca9c28be8e +size 3518747424 diff --git a/Llama-3-8B-Instruct-Coder-v2.IQ4_XS.gguf b/Llama-3-8B-Instruct-Coder-v2.IQ4_XS.gguf new file mode 100644 index 0000000..77c10e6 --- /dev/null +++ b/Llama-3-8B-Instruct-Coder-v2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c342445ba19e0857a238c32dc29f554904c9b010957d57164ac953c4918a57e3 +size 4484363040 diff --git a/Llama-3-8B-Instruct-Coder-v2.Q2_K.gguf b/Llama-3-8B-Instruct-Coder-v2.Q2_K.gguf new file mode 100644 index 0000000..d39e6f2 --- /dev/null +++ b/Llama-3-8B-Instruct-Coder-v2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b01f21a6a294a0d8b8ba5d9de6229e71f2c280665b539582694a30c552b8754 +size 3179131680 diff --git a/Llama-3-8B-Instruct-Coder-v2.Q3_K_L.gguf b/Llama-3-8B-Instruct-Coder-v2.Q3_K_L.gguf new file mode 100644 index 0000000..2170fce --- /dev/null +++ b/Llama-3-8B-Instruct-Coder-v2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38609bdc137efd4ea399c420fe1a5dd10615a9e9e790b514c8b01f1e87890645 +size 4321956640 diff --git a/Llama-3-8B-Instruct-Coder-v2.Q3_K_M.gguf b/Llama-3-8B-Instruct-Coder-v2.Q3_K_M.gguf new file mode 100644 index 0000000..9a3d342 --- /dev/null +++ b/Llama-3-8B-Instruct-Coder-v2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88ff5cbc63d7cb7961512bbc295f3aeb4b1561207c65717ac094851a42f1b7c0 +size 4018918176 diff --git a/Llama-3-8B-Instruct-Coder-v2.Q3_K_S.gguf b/Llama-3-8B-Instruct-Coder-v2.Q3_K_S.gguf new file mode 100644 index 0000000..679bad3 --- /dev/null +++ b/Llama-3-8B-Instruct-Coder-v2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67f479d0cf2e1070755ad6db9e8b00a6d47b2ea2e6324907c5584a79c36e510b +size 3664499488 diff --git a/Llama-3-8B-Instruct-Coder-v2.Q4_K_M.gguf b/Llama-3-8B-Instruct-Coder-v2.Q4_K_M.gguf new file mode 100644 index 0000000..acea33c --- /dev/null +++ b/Llama-3-8B-Instruct-Coder-v2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2be0c027210e980671b31de68c614ab4cb02f7c32e825c86629d7a613d6b06e +size 4920734496 diff --git a/Llama-3-8B-Instruct-Coder-v2.Q4_K_S.gguf b/Llama-3-8B-Instruct-Coder-v2.Q4_K_S.gguf new file mode 100644 index 0000000..7eebba7 --- /dev/null +++ b/Llama-3-8B-Instruct-Coder-v2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5ec7d96fc9503da7022fa756315fe72b83e8b8d6cea89675ad3af21213b1e68 +size 4692669216 diff --git a/Llama-3-8B-Instruct-Coder-v2.Q5_K_M.gguf b/Llama-3-8B-Instruct-Coder-v2.Q5_K_M.gguf new file mode 100644 index 0000000..cd21fad --- /dev/null +++ b/Llama-3-8B-Instruct-Coder-v2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ce5f730139d12496f57a7117ea64dc26f01e6a676a7e55e5ae470767124b33c +size 5732987680 diff --git a/Llama-3-8B-Instruct-Coder-v2.Q5_K_S.gguf b/Llama-3-8B-Instruct-Coder-v2.Q5_K_S.gguf new file mode 100644 index 0000000..2d1886e --- /dev/null +++ b/Llama-3-8B-Instruct-Coder-v2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88e5f77bbe82ccbe75e6bf98e0313eb99461ab756dae9feebd6fe3a0a71771f8 +size 5599294240 diff --git a/Llama-3-8B-Instruct-Coder-v2.Q6_K.gguf b/Llama-3-8B-Instruct-Coder-v2.Q6_K.gguf new file mode 100644 index 0000000..fe6efd9 --- /dev/null +++ b/Llama-3-8B-Instruct-Coder-v2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5944cac71e9f70a1ec09910bc999e038462e6e68e7e6ff6c438b51e25e23a8ce +size 6596006688 diff --git a/Llama-3-8B-Instruct-Coder-v2.Q8_0.gguf b/Llama-3-8B-Instruct-Coder-v2.Q8_0.gguf new file mode 100644 index 0000000..e94099c --- /dev/null +++ b/Llama-3-8B-Instruct-Coder-v2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5de69290d980a5ddc1997b442cec212402e7077a825565e731bb36c0d17f9877 +size 8540771104 diff --git a/Llama-3-8B-Instruct-Coder-v2.f16.gguf b/Llama-3-8B-Instruct-Coder-v2.f16.gguf new file mode 100644 index 0000000..449e984 --- /dev/null +++ b/Llama-3-8B-Instruct-Coder-v2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c46df301f92c71a4e66c476a9bb9c0603390c9c25d671a502089039770ca6eca +size 16068891424 diff --git a/README.md b/README.md new file mode 100644 index 0000000..da5e11d --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: rombodawg/Llama-3-8B-Instruct-Coder-v2 +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/rombodawg/Llama-3-8B-Instruct-Coder-v2 + + +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/Llama-3-8B-Instruct-Coder-v2-GGUF/resolve/main/Llama-3-8B-Instruct-Coder-v2.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-v2-GGUF/resolve/main/Llama-3-8B-Instruct-Coder-v2.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-v2-GGUF/resolve/main/Llama-3-8B-Instruct-Coder-v2.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-v2-GGUF/resolve/main/Llama-3-8B-Instruct-Coder-v2.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-v2-GGUF/resolve/main/Llama-3-8B-Instruct-Coder-v2.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-v2-GGUF/resolve/main/Llama-3-8B-Instruct-Coder-v2.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-v2-GGUF/resolve/main/Llama-3-8B-Instruct-Coder-v2.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-v2-GGUF/resolve/main/Llama-3-8B-Instruct-Coder-v2.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-v2-GGUF/resolve/main/Llama-3-8B-Instruct-Coder-v2.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-v2-GGUF/resolve/main/Llama-3-8B-Instruct-Coder-v2.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-v2-GGUF/resolve/main/Llama-3-8B-Instruct-Coder-v2.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-v2-GGUF/resolve/main/Llama-3-8B-Instruct-Coder-v2.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-v2-GGUF/resolve/main/Llama-3-8B-Instruct-Coder-v2.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-v2-GGUF/resolve/main/Llama-3-8B-Instruct-Coder-v2.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-v2-GGUF/resolve/main/Llama-3-8B-Instruct-Coder-v2.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. + +