commit 8b0e6c2551a476254dd309e15ab44a1a1ba9cadc Author: ModelHub XC Date: Tue May 26 09:22:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/DeciLM-6b-instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9ff96f6 --- /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 +DeciLM-6b-instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeciLM-6b-instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DeciLM-6b-instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeciLM-6b-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +DeciLM-6b-instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DeciLM-6b-instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeciLM-6b-instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +DeciLM-6b-instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DeciLM-6b-instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeciLM-6b-instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeciLM-6b-instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeciLM-6b-instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DeciLM-6b-instruct.IQ4_XS.gguf b/DeciLM-6b-instruct.IQ4_XS.gguf new file mode 100644 index 0000000..056e8dc --- /dev/null +++ b/DeciLM-6b-instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1cd6cf94ded8fd31f8995f4bb01fec68c6b4bc51ba3f09be1f914b828743763 +size 3109041344 diff --git a/DeciLM-6b-instruct.Q2_K.gguf b/DeciLM-6b-instruct.Q2_K.gguf new file mode 100644 index 0000000..11bfc12 --- /dev/null +++ b/DeciLM-6b-instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc3045fa8cb8e4ca2c80a4010b7903e20e59928c448f317f9b4e91e7494a2949 +size 2149364928 diff --git a/DeciLM-6b-instruct.Q3_K_L.gguf b/DeciLM-6b-instruct.Q3_K_L.gguf new file mode 100644 index 0000000..8faf067 --- /dev/null +++ b/DeciLM-6b-instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbeec3c0d66fe8028e734a02ebedb0e275e02e550f7fa7c1fa82194c48b4a19a +size 3026613440 diff --git a/DeciLM-6b-instruct.Q3_K_M.gguf b/DeciLM-6b-instruct.Q3_K_M.gguf new file mode 100644 index 0000000..df1c980 --- /dev/null +++ b/DeciLM-6b-instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8f4246f2d3e824bce4a0c042b1fc70b66b3f77808d98d9540cd6be857593876 +size 2787538112 diff --git a/DeciLM-6b-instruct.Q3_K_S.gguf b/DeciLM-6b-instruct.Q3_K_S.gguf new file mode 100644 index 0000000..5d069f9 --- /dev/null +++ b/DeciLM-6b-instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:467f898cdeb1e215c83dbea6dbfdeec9d1aaf13548003c1fe902e2268cfa99dc +size 2509460672 diff --git a/DeciLM-6b-instruct.Q4_K_M.gguf b/DeciLM-6b-instruct.Q4_K_M.gguf new file mode 100644 index 0000000..362ce03 --- /dev/null +++ b/DeciLM-6b-instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13ca1243c8a3391aa230b3dd04856746a66bc3d8b31780087020ca4ef680d878 +size 3441366208 diff --git a/DeciLM-6b-instruct.Q4_K_S.gguf b/DeciLM-6b-instruct.Q4_K_S.gguf new file mode 100644 index 0000000..54f97a0 --- /dev/null +++ b/DeciLM-6b-instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:003ae733261e6b6365b5dc7cbf749b7874687c0d20a157280cf31df7b63c4805 +size 3274519744 diff --git a/DeciLM-6b-instruct.Q5_K_M.gguf b/DeciLM-6b-instruct.Q5_K_M.gguf new file mode 100644 index 0000000..069ab1e --- /dev/null +++ b/DeciLM-6b-instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb28eed03827338789489a45e131169ff4c34d43ed14b662502e870637e055e5 +size 4047443136 diff --git a/DeciLM-6b-instruct.Q5_K_S.gguf b/DeciLM-6b-instruct.Q5_K_S.gguf new file mode 100644 index 0000000..894a522 --- /dev/null +++ b/DeciLM-6b-instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67eab590e5a37c2923af2a00960644725cbfe5d6a960600d93b88d72d2e86efa +size 3949540544 diff --git a/DeciLM-6b-instruct.Q6_K.gguf b/DeciLM-6b-instruct.Q6_K.gguf new file mode 100644 index 0000000..67764f0 --- /dev/null +++ b/DeciLM-6b-instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1183f741017b7923e1a385660ee1b5ae7f191b468b0f04dcf3f471c6faadcbb +size 4691399872 diff --git a/DeciLM-6b-instruct.Q8_0.gguf b/DeciLM-6b-instruct.Q8_0.gguf new file mode 100644 index 0000000..4cb279d --- /dev/null +++ b/DeciLM-6b-instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:547e278cdad4af7d8f9303c091ad726cc2dfc6b6cd6dd42a2302130348eaa2a0 +size 6075946176 diff --git a/DeciLM-6b-instruct.f16.gguf b/DeciLM-6b-instruct.f16.gguf new file mode 100644 index 0000000..d88fae9 --- /dev/null +++ b/DeciLM-6b-instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e446305236ccf76b9856b342bb17d7207b81dae34f3c342d74ddf7cd46be7d4 +size 11435480256 diff --git a/README.md b/README.md new file mode 100644 index 0000000..13bd5c4 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: Deci/DeciLM-6b-instruct +datasets: +- cerebras/SlimPajama-627B +- Open-Orca/OpenOrca +language: +- en +library_name: transformers +license: +- llama2 +- other +quantized_by: mradermacher +tags: +- Deci AI +- DeciLM +- Instruction +--- +## About + + + + + + +static quants of https://huggingface.co/Deci/DeciLM-6b-instruct + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/DeciLM-6b-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/DeciLM-6b-instruct-GGUF/resolve/main/DeciLM-6b-instruct.Q2_K.gguf) | Q2_K | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/DeciLM-6b-instruct-GGUF/resolve/main/DeciLM-6b-instruct.Q3_K_S.gguf) | Q3_K_S | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/DeciLM-6b-instruct-GGUF/resolve/main/DeciLM-6b-instruct.Q3_K_M.gguf) | Q3_K_M | 2.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DeciLM-6b-instruct-GGUF/resolve/main/DeciLM-6b-instruct.Q3_K_L.gguf) | Q3_K_L | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/DeciLM-6b-instruct-GGUF/resolve/main/DeciLM-6b-instruct.IQ4_XS.gguf) | IQ4_XS | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/DeciLM-6b-instruct-GGUF/resolve/main/DeciLM-6b-instruct.Q4_K_S.gguf) | Q4_K_S | 3.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeciLM-6b-instruct-GGUF/resolve/main/DeciLM-6b-instruct.Q4_K_M.gguf) | Q4_K_M | 3.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeciLM-6b-instruct-GGUF/resolve/main/DeciLM-6b-instruct.Q5_K_S.gguf) | Q5_K_S | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/DeciLM-6b-instruct-GGUF/resolve/main/DeciLM-6b-instruct.Q5_K_M.gguf) | Q5_K_M | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/DeciLM-6b-instruct-GGUF/resolve/main/DeciLM-6b-instruct.Q6_K.gguf) | Q6_K | 4.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/DeciLM-6b-instruct-GGUF/resolve/main/DeciLM-6b-instruct.Q8_0.gguf) | Q8_0 | 6.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/DeciLM-6b-instruct-GGUF/resolve/main/DeciLM-6b-instruct.f16.gguf) | f16 | 11.5 | 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. + +