commit 82f3c816d5e69042771df8d2799e7343ce835667 Author: ModelHub XC Date: Wed Jun 24 18:07:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/intelligence-cod-rag-7b-v3.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..037051b --- /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 +intelligence-cod-rag-7b-v3.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +intelligence-cod-rag-7b-v3.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +intelligence-cod-rag-7b-v3.1.f16.gguf filter=lfs diff=lfs merge=lfs -text +intelligence-cod-rag-7b-v3.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +intelligence-cod-rag-7b-v3.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +intelligence-cod-rag-7b-v3.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +intelligence-cod-rag-7b-v3.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +intelligence-cod-rag-7b-v3.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +intelligence-cod-rag-7b-v3.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +intelligence-cod-rag-7b-v3.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +intelligence-cod-rag-7b-v3.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +intelligence-cod-rag-7b-v3.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +intelligence-cod-rag-7b-v3.1.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..d8338e4 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: ClaudioItaly/intelligence-cod-rag-7b-v3.1 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/ClaudioItaly/intelligence-cod-rag-7b-v3.1 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/intelligence-cod-rag-7b-v3.1-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/intelligence-cod-rag-7b-v3.1-GGUF/resolve/main/intelligence-cod-rag-7b-v3.1.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/intelligence-cod-rag-7b-v3.1-GGUF/resolve/main/intelligence-cod-rag-7b-v3.1.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/intelligence-cod-rag-7b-v3.1-GGUF/resolve/main/intelligence-cod-rag-7b-v3.1.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/intelligence-cod-rag-7b-v3.1-GGUF/resolve/main/intelligence-cod-rag-7b-v3.1.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/intelligence-cod-rag-7b-v3.1-GGUF/resolve/main/intelligence-cod-rag-7b-v3.1.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/intelligence-cod-rag-7b-v3.1-GGUF/resolve/main/intelligence-cod-rag-7b-v3.1.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.5 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/intelligence-cod-rag-7b-v3.1-GGUF/resolve/main/intelligence-cod-rag-7b-v3.1.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/intelligence-cod-rag-7b-v3.1-GGUF/resolve/main/intelligence-cod-rag-7b-v3.1.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/intelligence-cod-rag-7b-v3.1-GGUF/resolve/main/intelligence-cod-rag-7b-v3.1.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/intelligence-cod-rag-7b-v3.1-GGUF/resolve/main/intelligence-cod-rag-7b-v3.1.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/intelligence-cod-rag-7b-v3.1-GGUF/resolve/main/intelligence-cod-rag-7b-v3.1.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/intelligence-cod-rag-7b-v3.1-GGUF/resolve/main/intelligence-cod-rag-7b-v3.1.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/intelligence-cod-rag-7b-v3.1-GGUF/resolve/main/intelligence-cod-rag-7b-v3.1.f16.gguf) | f16 | 15.3 | 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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/intelligence-cod-rag-7b-v3.1.IQ4_XS.gguf b/intelligence-cod-rag-7b-v3.1.IQ4_XS.gguf new file mode 100644 index 0000000..5867e2c --- /dev/null +++ b/intelligence-cod-rag-7b-v3.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b925ecf802143d922f450e5ff59a8bc4b39e38d3f454dac2d3a5e4052cbfa00b +size 4250297536 diff --git a/intelligence-cod-rag-7b-v3.1.Q2_K.gguf b/intelligence-cod-rag-7b-v3.1.Q2_K.gguf new file mode 100644 index 0000000..762caf1 --- /dev/null +++ b/intelligence-cod-rag-7b-v3.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bf92af98307d0200d36c75eb9a3592b5c8e4ccdc3daa250bee9b118aad3a906 +size 3015939264 diff --git a/intelligence-cod-rag-7b-v3.1.Q3_K_L.gguf b/intelligence-cod-rag-7b-v3.1.Q3_K_L.gguf new file mode 100644 index 0000000..407ae1f --- /dev/null +++ b/intelligence-cod-rag-7b-v3.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15afd3334aa7fa97b6624f2c0e56f233ef16339db77bc061f4a2531c248a6210 +size 4088458432 diff --git a/intelligence-cod-rag-7b-v3.1.Q3_K_M.gguf b/intelligence-cod-rag-7b-v3.1.Q3_K_M.gguf new file mode 100644 index 0000000..22d157c --- /dev/null +++ b/intelligence-cod-rag-7b-v3.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdf02188f5c8c67f70d72f1f263217c8fab2df3ba703c78bf9d00e5067f928ff +size 3808390336 diff --git a/intelligence-cod-rag-7b-v3.1.Q3_K_S.gguf b/intelligence-cod-rag-7b-v3.1.Q3_K_S.gguf new file mode 100644 index 0000000..062d3ab --- /dev/null +++ b/intelligence-cod-rag-7b-v3.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea3727f4b1e2f90850ef529a1fa8631709ebab3337b80bf84e4514c909938429 +size 3492367552 diff --git a/intelligence-cod-rag-7b-v3.1.Q4_0_4_4.gguf b/intelligence-cod-rag-7b-v3.1.Q4_0_4_4.gguf new file mode 100644 index 0000000..3a8cc98 --- /dev/null +++ b/intelligence-cod-rag-7b-v3.1.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5817190c4afc760ec62c0465242c71a77325a960a05aee5588bac6adddc5c7fb +size 4431389888 diff --git a/intelligence-cod-rag-7b-v3.1.Q4_K_M.gguf b/intelligence-cod-rag-7b-v3.1.Q4_K_M.gguf new file mode 100644 index 0000000..3cb985d --- /dev/null +++ b/intelligence-cod-rag-7b-v3.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16be3e68cb8540ff8d9edae1f5c56f6309f8f4d36b34c74722bde88aa4cfb3c9 +size 4683072704 diff --git a/intelligence-cod-rag-7b-v3.1.Q4_K_S.gguf b/intelligence-cod-rag-7b-v3.1.Q4_K_S.gguf new file mode 100644 index 0000000..80b73ae --- /dev/null +++ b/intelligence-cod-rag-7b-v3.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aee04eaf2cf17e6b43b678e8df1f388f4df2d9e7ac7165059d4e3979a0591e3c +size 4457768128 diff --git a/intelligence-cod-rag-7b-v3.1.Q5_K_M.gguf b/intelligence-cod-rag-7b-v3.1.Q5_K_M.gguf new file mode 100644 index 0000000..d2e2022 --- /dev/null +++ b/intelligence-cod-rag-7b-v3.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26285f5defbcf81d64b0f90d1cfdd66c8dc7ae89b003c49f479b703bfa953933 +size 5444830400 diff --git a/intelligence-cod-rag-7b-v3.1.Q5_K_S.gguf b/intelligence-cod-rag-7b-v3.1.Q5_K_S.gguf new file mode 100644 index 0000000..df5b268 --- /dev/null +++ b/intelligence-cod-rag-7b-v3.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0084621952c7c6073da9fe02737e78b81cd8e6e09d073ac429873224bc36bf61 +size 5315175616 diff --git a/intelligence-cod-rag-7b-v3.1.Q6_K.gguf b/intelligence-cod-rag-7b-v3.1.Q6_K.gguf new file mode 100644 index 0000000..5e58a19 --- /dev/null +++ b/intelligence-cod-rag-7b-v3.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fa00fc68bb15281a42602f721fdd3a8b53e247b13f7f9342693c2c4491facc3 +size 6254197952 diff --git a/intelligence-cod-rag-7b-v3.1.Q8_0.gguf b/intelligence-cod-rag-7b-v3.1.Q8_0.gguf new file mode 100644 index 0000000..ca78af3 --- /dev/null +++ b/intelligence-cod-rag-7b-v3.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61b180ce74f56444f3b089f4e477a1c2a326d7dd93885d32b46d18ea844ec940 +size 8098524352 diff --git a/intelligence-cod-rag-7b-v3.1.f16.gguf b/intelligence-cod-rag-7b-v3.1.f16.gguf new file mode 100644 index 0000000..62e7f12 --- /dev/null +++ b/intelligence-cod-rag-7b-v3.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a20261f61d147f83159881217570b691d94c973c2fdff1c996e0d6c7dbd717f +size 15237852352