commit 3d3a5b868dc4af5d89fdf97b23689bb198146dd8 Author: ModelHub XC Date: Thu Jul 9 03:43:11 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Codellama-3-8B-Finetuned-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ea20cda --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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-3-8B-Finetuned-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B-Finetuned-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B-Finetuned-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B-Finetuned-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B-Finetuned-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B-Finetuned-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B-Finetuned-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B-Finetuned-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B-Finetuned-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B-Finetuned-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B-Finetuned-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B-Finetuned-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B-Finetuned-Instruct.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Codellama-3-8B-Finetuned-Instruct.IQ4_XS.gguf b/Codellama-3-8B-Finetuned-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..8a33619 --- /dev/null +++ b/Codellama-3-8B-Finetuned-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb1369091cf0d94c60dfb295a915f90f891bd6fc42e06e2c1c443b8a78eda572 +size 4484363808 diff --git a/Codellama-3-8B-Finetuned-Instruct.Q2_K.gguf b/Codellama-3-8B-Finetuned-Instruct.Q2_K.gguf new file mode 100644 index 0000000..34d0144 --- /dev/null +++ b/Codellama-3-8B-Finetuned-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6479220b8d8bb5ffd242bf915819a2c6f8de25612551ec6eaac37b8a9fc1f0c +size 3179132448 diff --git a/Codellama-3-8B-Finetuned-Instruct.Q3_K_L.gguf b/Codellama-3-8B-Finetuned-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..be964ac --- /dev/null +++ b/Codellama-3-8B-Finetuned-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dd5e4521d33a0792bd91c6410e2292e6ed2bec807c49faa817dd747173cfa2a +size 4321957408 diff --git a/Codellama-3-8B-Finetuned-Instruct.Q3_K_M.gguf b/Codellama-3-8B-Finetuned-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..d09364e --- /dev/null +++ b/Codellama-3-8B-Finetuned-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:401f0d1ff3261381395d9c9315e33dd609653dcd7ec394c1d9c1da4e4a7772b1 +size 4018918944 diff --git a/Codellama-3-8B-Finetuned-Instruct.Q3_K_S.gguf b/Codellama-3-8B-Finetuned-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..0824571 --- /dev/null +++ b/Codellama-3-8B-Finetuned-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c10a493df13c9df9b57a457b2be79417429019f03b549ca444ae2bfd5088332e +size 3664500256 diff --git a/Codellama-3-8B-Finetuned-Instruct.Q4_0_4_4.gguf b/Codellama-3-8B-Finetuned-Instruct.Q4_0_4_4.gguf new file mode 100644 index 0000000..32e3917 --- /dev/null +++ b/Codellama-3-8B-Finetuned-Instruct.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b10ed0195228445d443fbc1a05445a840a2b31a4d7e1bde05603d8fdbebe2f75 +size 4661212704 diff --git a/Codellama-3-8B-Finetuned-Instruct.Q4_K_M.gguf b/Codellama-3-8B-Finetuned-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..a2d7c6a --- /dev/null +++ b/Codellama-3-8B-Finetuned-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fad836fa6c3df4df31a52b108f54a35aa5b25d750e4291415016138899251fa1 +size 4920735264 diff --git a/Codellama-3-8B-Finetuned-Instruct.Q4_K_S.gguf b/Codellama-3-8B-Finetuned-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..a402428 --- /dev/null +++ b/Codellama-3-8B-Finetuned-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:828205ae1d88ab1df8cf3cc37283e73fd62084bef97420a807c49f0c7f4677a1 +size 4692669984 diff --git a/Codellama-3-8B-Finetuned-Instruct.Q5_K_M.gguf b/Codellama-3-8B-Finetuned-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..7a8f1b4 --- /dev/null +++ b/Codellama-3-8B-Finetuned-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0dfbcc817d05b9a586aa4f95528adcc09eb6d6c77772dd6984661a74836cc8f +size 5732988448 diff --git a/Codellama-3-8B-Finetuned-Instruct.Q5_K_S.gguf b/Codellama-3-8B-Finetuned-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..a35047c --- /dev/null +++ b/Codellama-3-8B-Finetuned-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61bedf7fa3656061a154941a1b3c5414906271918bc9d0b9a96c3bf0cdd43914 +size 5599295008 diff --git a/Codellama-3-8B-Finetuned-Instruct.Q6_K.gguf b/Codellama-3-8B-Finetuned-Instruct.Q6_K.gguf new file mode 100644 index 0000000..4effc2b --- /dev/null +++ b/Codellama-3-8B-Finetuned-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:747e327bdf750c1505a267809261e3d94569baf043282d576d0deb94e05ee2e3 +size 6596007456 diff --git a/Codellama-3-8B-Finetuned-Instruct.Q8_0.gguf b/Codellama-3-8B-Finetuned-Instruct.Q8_0.gguf new file mode 100644 index 0000000..8a8e781 --- /dev/null +++ b/Codellama-3-8B-Finetuned-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b89e228d780e264bae4dafbf3c50a117ce08d4cb1d89c892f4b38b39c04189cc +size 8540771872 diff --git a/Codellama-3-8B-Finetuned-Instruct.f16.gguf b/Codellama-3-8B-Finetuned-Instruct.f16.gguf new file mode 100644 index 0000000..47f1bb3 --- /dev/null +++ b/Codellama-3-8B-Finetuned-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5938b152bc4a51a778d441e3e5c32e0a63877d05e69b2cdce845ccb779b6dee7 +size 16068892192 diff --git a/README.md b/README.md new file mode 100644 index 0000000..745b135 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: rombodawg/Llama-3-8B-Instruct-Coder +language: +- en +library_name: transformers +license: llama3 +mradermacher: + readme_rev: 1 +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 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Codellama-3-8B-Finetuned-Instruct-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Codellama-3-8B-Finetuned-Instruct-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/Codellama-3-8B-Finetuned-Instruct-GGUF/resolve/main/Codellama-3-8B-Finetuned-Instruct.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-Finetuned-Instruct-GGUF/resolve/main/Codellama-3-8B-Finetuned-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-Finetuned-Instruct-GGUF/resolve/main/Codellama-3-8B-Finetuned-Instruct.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-Finetuned-Instruct-GGUF/resolve/main/Codellama-3-8B-Finetuned-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-Finetuned-Instruct-GGUF/resolve/main/Codellama-3-8B-Finetuned-Instruct.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-Finetuned-Instruct-GGUF/resolve/main/Codellama-3-8B-Finetuned-Instruct.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-Finetuned-Instruct-GGUF/resolve/main/Codellama-3-8B-Finetuned-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-Finetuned-Instruct-GGUF/resolve/main/Codellama-3-8B-Finetuned-Instruct.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-Finetuned-Instruct-GGUF/resolve/main/Codellama-3-8B-Finetuned-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-Finetuned-Instruct-GGUF/resolve/main/Codellama-3-8B-Finetuned-Instruct.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-Finetuned-Instruct-GGUF/resolve/main/Codellama-3-8B-Finetuned-Instruct.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-Finetuned-Instruct-GGUF/resolve/main/Codellama-3-8B-Finetuned-Instruct.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-Finetuned-Instruct-GGUF/resolve/main/Codellama-3-8B-Finetuned-Instruct.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. + +