commit a7f2395022c6858b6bcea34c52f02b3df2a774f8 Author: ModelHub XC Date: Fri Jun 26 12:57:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/CodeLlama-7B-KStack-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c34174f --- /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-7B-KStack.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7B-KStack.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7B-KStack.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7B-KStack.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7B-KStack.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7B-KStack.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7B-KStack.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7B-KStack.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7B-KStack.f16.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7B-KStack.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7B-KStack.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7B-KStack.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7B-KStack.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/CodeLlama-7B-KStack.IQ4_XS.gguf b/CodeLlama-7B-KStack.IQ4_XS.gguf new file mode 100644 index 0000000..f8e465e --- /dev/null +++ b/CodeLlama-7B-KStack.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8b9cd0ae71d53f3b98f76369874818e87c7e2acf0933d07a7eeff83580e3d73 +size 3647606560 diff --git a/CodeLlama-7B-KStack.Q2_K.gguf b/CodeLlama-7B-KStack.Q2_K.gguf new file mode 100644 index 0000000..075cbe2 --- /dev/null +++ b/CodeLlama-7B-KStack.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b120d048fcf02c603f673846e2f91cd7e3885cb677a413cbd5052d3478ccc8c1 +size 2532940576 diff --git a/CodeLlama-7B-KStack.Q3_K_L.gguf b/CodeLlama-7B-KStack.Q3_K_L.gguf new file mode 100644 index 0000000..fcfa83a --- /dev/null +++ b/CodeLlama-7B-KStack.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c5a1739b07bb15b8d7f9f4b4df3b8df4dc069c692d3d60b295b2a1ef17b6bcd +size 3597194528 diff --git a/CodeLlama-7B-KStack.Q3_K_M.gguf b/CodeLlama-7B-KStack.Q3_K_M.gguf new file mode 100644 index 0000000..b688eb7 --- /dev/null +++ b/CodeLlama-7B-KStack.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:025f37eb8b36692d4179ccad60f0e85e0dd35bed6e1471ed6c4f46d7cde34f82 +size 3298088224 diff --git a/CodeLlama-7B-KStack.Q3_K_S.gguf b/CodeLlama-7B-KStack.Q3_K_S.gguf new file mode 100644 index 0000000..c599191 --- /dev/null +++ b/CodeLlama-7B-KStack.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21a61ffa95f53dec023b317f20ee467cb762ca10c0afe9b024460aa6983e0e38 +size 2948388128 diff --git a/CodeLlama-7B-KStack.Q4_0_4_4.gguf b/CodeLlama-7B-KStack.Q4_0_4_4.gguf new file mode 100644 index 0000000..0bdf764 --- /dev/null +++ b/CodeLlama-7B-KStack.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a960a591b64c1c4a580d757b4a11f370c477e4300a7a1673aa40ce56e445efe7 +size 3825899296 diff --git a/CodeLlama-7B-KStack.Q4_K_M.gguf b/CodeLlama-7B-KStack.Q4_K_M.gguf new file mode 100644 index 0000000..8e4a936 --- /dev/null +++ b/CodeLlama-7B-KStack.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:becdadf03ead032aeec15ed69579cd639deaa383ec84354dfa25d4d48688ed36 +size 4081096480 diff --git a/CodeLlama-7B-KStack.Q4_K_S.gguf b/CodeLlama-7B-KStack.Q4_K_S.gguf new file mode 100644 index 0000000..d3e61c0 --- /dev/null +++ b/CodeLlama-7B-KStack.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6695ca91115df1aba4c9bdc33c23b5b67d84c7d11c94c8f086f7443900c540b6 +size 3856832288 diff --git a/CodeLlama-7B-KStack.Q5_K_M.gguf b/CodeLlama-7B-KStack.Q5_K_M.gguf new file mode 100644 index 0000000..34094a9 --- /dev/null +++ b/CodeLlama-7B-KStack.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1bab5769e05842c9781519044542dc612b7edc43d65ecc4e8171bf6282f6073 +size 4783257376 diff --git a/CodeLlama-7B-KStack.Q5_K_S.gguf b/CodeLlama-7B-KStack.Q5_K_S.gguf new file mode 100644 index 0000000..69ed239 --- /dev/null +++ b/CodeLlama-7B-KStack.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a47917556ad6561369be484da70c55f702c830c61f572a352ed6eb2049b0b915 +size 4651792160 diff --git a/CodeLlama-7B-KStack.Q6_K.gguf b/CodeLlama-7B-KStack.Q6_K.gguf new file mode 100644 index 0000000..009c117 --- /dev/null +++ b/CodeLlama-7B-KStack.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2271b17c8c8fd51fbf0dfd18efaad82729da0667239a053e4c492a8d15ddc983 +size 5529303328 diff --git a/CodeLlama-7B-KStack.Q8_0.gguf b/CodeLlama-7B-KStack.Q8_0.gguf new file mode 100644 index 0000000..38b079e --- /dev/null +++ b/CodeLlama-7B-KStack.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9552c780112b83def8b5366d2614d7f1d8764f48b16c5c47e015534fd30bf933 +size 7161230624 diff --git a/CodeLlama-7B-KStack.f16.gguf b/CodeLlama-7B-KStack.f16.gguf new file mode 100644 index 0000000..f67938f --- /dev/null +++ b/CodeLlama-7B-KStack.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:800a05f239bee83d6f13a549fcc8ab13f16d2bcef29c983682d4bc1c5f15e452 +size 13478368544 diff --git a/README.md b/README.md new file mode 100644 index 0000000..59570d2 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: JetBrains/CodeLlama-7B-KStack +datasets: +- JetBrains/KStack +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- code +--- +## About + + + + + + +static quants of https://huggingface.co/JetBrains/CodeLlama-7B-KStack + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/CodeLlama-7B-KStack-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-7B-KStack-GGUF/resolve/main/CodeLlama-7B-KStack.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7B-KStack-GGUF/resolve/main/CodeLlama-7B-KStack.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7B-KStack-GGUF/resolve/main/CodeLlama-7B-KStack.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7B-KStack-GGUF/resolve/main/CodeLlama-7B-KStack.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7B-KStack-GGUF/resolve/main/CodeLlama-7B-KStack.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7B-KStack-GGUF/resolve/main/CodeLlama-7B-KStack.Q4_0_4_4.gguf) | Q4_0_4_4 | 3.9 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7B-KStack-GGUF/resolve/main/CodeLlama-7B-KStack.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7B-KStack-GGUF/resolve/main/CodeLlama-7B-KStack.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7B-KStack-GGUF/resolve/main/CodeLlama-7B-KStack.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7B-KStack-GGUF/resolve/main/CodeLlama-7B-KStack.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7B-KStack-GGUF/resolve/main/CodeLlama-7B-KStack.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7B-KStack-GGUF/resolve/main/CodeLlama-7B-KStack.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7B-KStack-GGUF/resolve/main/CodeLlama-7B-KStack.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. + +