commit 186cff4bec4b52262ca270f72066669da6369301 Author: ModelHub XC Date: Wed Sep 9 04:00:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/codellama-7b-chisel-bf16-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7dd3eb3 --- /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 +codellama-7b-chisel-bf16.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +codellama-7b-chisel-bf16.f16.gguf filter=lfs diff=lfs merge=lfs -text +codellama-7b-chisel-bf16.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +codellama-7b-chisel-bf16.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +codellama-7b-chisel-bf16.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +codellama-7b-chisel-bf16.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +codellama-7b-chisel-bf16.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +codellama-7b-chisel-bf16.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +codellama-7b-chisel-bf16.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +codellama-7b-chisel-bf16.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +codellama-7b-chisel-bf16.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +codellama-7b-chisel-bf16.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..2b3f3ad --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: rtl-llm/codellama-7b-chisel-bf16 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/rtl-llm/codellama-7b-chisel-bf16 + + +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-chisel-bf16-GGUF/resolve/main/codellama-7b-chisel-bf16.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/codellama-7b-chisel-bf16-GGUF/resolve/main/codellama-7b-chisel-bf16.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/codellama-7b-chisel-bf16-GGUF/resolve/main/codellama-7b-chisel-bf16.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/codellama-7b-chisel-bf16-GGUF/resolve/main/codellama-7b-chisel-bf16.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/codellama-7b-chisel-bf16-GGUF/resolve/main/codellama-7b-chisel-bf16.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/codellama-7b-chisel-bf16-GGUF/resolve/main/codellama-7b-chisel-bf16.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/codellama-7b-chisel-bf16-GGUF/resolve/main/codellama-7b-chisel-bf16.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/codellama-7b-chisel-bf16-GGUF/resolve/main/codellama-7b-chisel-bf16.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/codellama-7b-chisel-bf16-GGUF/resolve/main/codellama-7b-chisel-bf16.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/codellama-7b-chisel-bf16-GGUF/resolve/main/codellama-7b-chisel-bf16.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/codellama-7b-chisel-bf16-GGUF/resolve/main/codellama-7b-chisel-bf16.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/codellama-7b-chisel-bf16-GGUF/resolve/main/codellama-7b-chisel-bf16.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-chisel-bf16.IQ4_XS.gguf b/codellama-7b-chisel-bf16.IQ4_XS.gguf new file mode 100644 index 0000000..af50037 --- /dev/null +++ b/codellama-7b-chisel-bf16.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bd9a22ca85bede48e84a518f1580df684baf9e04dfa535be4f00a2d0e8bb63e +size 3647607232 diff --git a/codellama-7b-chisel-bf16.Q2_K.gguf b/codellama-7b-chisel-bf16.Q2_K.gguf new file mode 100644 index 0000000..ec601c3 --- /dev/null +++ b/codellama-7b-chisel-bf16.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f19c464094b9a41eda498e10a0235c68e920d703ac042dddf8fdc422b4f32a51 +size 2532941248 diff --git a/codellama-7b-chisel-bf16.Q3_K_L.gguf b/codellama-7b-chisel-bf16.Q3_K_L.gguf new file mode 100644 index 0000000..5a34139 --- /dev/null +++ b/codellama-7b-chisel-bf16.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:868e4a22635c108d9e0eca88bc00bedef69a203c362915b33fd206b040cae59e +size 3597195200 diff --git a/codellama-7b-chisel-bf16.Q3_K_M.gguf b/codellama-7b-chisel-bf16.Q3_K_M.gguf new file mode 100644 index 0000000..2c54f0c --- /dev/null +++ b/codellama-7b-chisel-bf16.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a181a5d3289c898d262898ea113d0c962773f204f9efabc04a6122fceca3d987 +size 3298088896 diff --git a/codellama-7b-chisel-bf16.Q3_K_S.gguf b/codellama-7b-chisel-bf16.Q3_K_S.gguf new file mode 100644 index 0000000..842eedb --- /dev/null +++ b/codellama-7b-chisel-bf16.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6a4cf96a7f14a9832cb352bad8ccdb6f4befcf05302dc41bf639dc3c84cd057 +size 2948388800 diff --git a/codellama-7b-chisel-bf16.Q4_K_M.gguf b/codellama-7b-chisel-bf16.Q4_K_M.gguf new file mode 100644 index 0000000..92616ca --- /dev/null +++ b/codellama-7b-chisel-bf16.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:791fda8dd2d69ebc7e3a6624ba070d38088f4c50f265e2c3159c80b27b5c237c +size 4081097152 diff --git a/codellama-7b-chisel-bf16.Q4_K_S.gguf b/codellama-7b-chisel-bf16.Q4_K_S.gguf new file mode 100644 index 0000000..ae6dbbd --- /dev/null +++ b/codellama-7b-chisel-bf16.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2724d2f6ca3f515cb59d64ed49a49ef5acdb98a9a1c1a81a6715eb6485f11408 +size 3856832960 diff --git a/codellama-7b-chisel-bf16.Q5_K_M.gguf b/codellama-7b-chisel-bf16.Q5_K_M.gguf new file mode 100644 index 0000000..078547e --- /dev/null +++ b/codellama-7b-chisel-bf16.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a53916383722b6c0c826bc08ffd990949c3919a37877dddcaa2620d3978ac98 +size 4783258048 diff --git a/codellama-7b-chisel-bf16.Q5_K_S.gguf b/codellama-7b-chisel-bf16.Q5_K_S.gguf new file mode 100644 index 0000000..4620acc --- /dev/null +++ b/codellama-7b-chisel-bf16.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e194aa4efdc69ed71a14903659ad007d4924e9a38451e18e545fdf5afda4014 +size 4651792832 diff --git a/codellama-7b-chisel-bf16.Q6_K.gguf b/codellama-7b-chisel-bf16.Q6_K.gguf new file mode 100644 index 0000000..bca128a --- /dev/null +++ b/codellama-7b-chisel-bf16.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad094e193575496b682efe769882a47c7aa29e4214f75395160ec0df0f57db50 +size 5529304000 diff --git a/codellama-7b-chisel-bf16.Q8_0.gguf b/codellama-7b-chisel-bf16.Q8_0.gguf new file mode 100644 index 0000000..52408b1 --- /dev/null +++ b/codellama-7b-chisel-bf16.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdf20ae1c6f09a681c9e6fd1f342db2cf68267e0947706e7b1b51227d5af18b4 +size 7161231296 diff --git a/codellama-7b-chisel-bf16.f16.gguf b/codellama-7b-chisel-bf16.f16.gguf new file mode 100644 index 0000000..b959f9c --- /dev/null +++ b/codellama-7b-chisel-bf16.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a6edcb502aabadb13a6be5a597c825e66299c01354bd4bf654994affab15e75 +size 13478369216