commit f99ca58be9f5a9e5079ca082b7d539b6c99ee87c Author: ModelHub XC Date: Sun Jul 5 10:07:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LITTLEBIT-7.8B-Summary-v1.0-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..91e9e7c --- /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 +LITTLEBIT-7.8B-Summary-v1.0.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LITTLEBIT-7.8B-Summary-v1.0.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LITTLEBIT-7.8B-Summary-v1.0.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LITTLEBIT-7.8B-Summary-v1.0.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LITTLEBIT-7.8B-Summary-v1.0.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LITTLEBIT-7.8B-Summary-v1.0.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LITTLEBIT-7.8B-Summary-v1.0.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LITTLEBIT-7.8B-Summary-v1.0.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LITTLEBIT-7.8B-Summary-v1.0.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LITTLEBIT-7.8B-Summary-v1.0.f16.gguf filter=lfs diff=lfs merge=lfs -text +LITTLEBIT-7.8B-Summary-v1.0.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +LITTLEBIT-7.8B-Summary-v1.0.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LITTLEBIT-7.8B-Summary-v1.0.IQ4_XS.gguf b/LITTLEBIT-7.8B-Summary-v1.0.IQ4_XS.gguf new file mode 100644 index 0000000..1aaf9a0 --- /dev/null +++ b/LITTLEBIT-7.8B-Summary-v1.0.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33ad1cd414348188852f3efc315a767a27777f6f4d84f8e2cf6b558357b7528d +size 4337588448 diff --git a/LITTLEBIT-7.8B-Summary-v1.0.Q2_K.gguf b/LITTLEBIT-7.8B-Summary-v1.0.Q2_K.gguf new file mode 100644 index 0000000..630ac58 --- /dev/null +++ b/LITTLEBIT-7.8B-Summary-v1.0.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44d5646084bef6114e85ed614ab6524ce60a756e6464328900db49e550ac170a +size 3053869280 diff --git a/LITTLEBIT-7.8B-Summary-v1.0.Q3_K_L.gguf b/LITTLEBIT-7.8B-Summary-v1.0.Q3_K_L.gguf new file mode 100644 index 0000000..ac3d538 --- /dev/null +++ b/LITTLEBIT-7.8B-Summary-v1.0.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:749d39a4749dce1200556a259fdb3b83f4df1ea046c8e289ae4097d61f5de3bc +size 4185938144 diff --git a/LITTLEBIT-7.8B-Summary-v1.0.Q3_K_M.gguf b/LITTLEBIT-7.8B-Summary-v1.0.Q3_K_M.gguf new file mode 100644 index 0000000..5f79efb --- /dev/null +++ b/LITTLEBIT-7.8B-Summary-v1.0.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f88e2613c5b50a43a5fdbdce1366a682efe037c893909c289e52ba10d5bd060a +size 3882899680 diff --git a/LITTLEBIT-7.8B-Summary-v1.0.Q3_K_S.gguf b/LITTLEBIT-7.8B-Summary-v1.0.Q3_K_S.gguf new file mode 100644 index 0000000..1a3f3e8 --- /dev/null +++ b/LITTLEBIT-7.8B-Summary-v1.0.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e3b5af115f044185864fb7d368d051f306981706605800b3243b66ce8c684c6 +size 3528480992 diff --git a/LITTLEBIT-7.8B-Summary-v1.0.Q4_K_M.gguf b/LITTLEBIT-7.8B-Summary-v1.0.Q4_K_M.gguf new file mode 100644 index 0000000..995b0dd --- /dev/null +++ b/LITTLEBIT-7.8B-Summary-v1.0.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efe2222b8b6251c8cc0427fbdc2c5f2b7ae7c9587072cd8ffa7a09310c130bee +size 4770650336 diff --git a/LITTLEBIT-7.8B-Summary-v1.0.Q4_K_S.gguf b/LITTLEBIT-7.8B-Summary-v1.0.Q4_K_S.gguf new file mode 100644 index 0000000..73492c7 --- /dev/null +++ b/LITTLEBIT-7.8B-Summary-v1.0.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2ce14159541133b27bc4d004b9a952a8f43fd04766a618c3f15a42aac2ec269 +size 4542585056 diff --git a/LITTLEBIT-7.8B-Summary-v1.0.Q5_K_M.gguf b/LITTLEBIT-7.8B-Summary-v1.0.Q5_K_M.gguf new file mode 100644 index 0000000..728632d --- /dev/null +++ b/LITTLEBIT-7.8B-Summary-v1.0.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3cdb322cc4a9614c4b9a7c4440b08ba6d4d66d05fdb6fbaae591e8c9b411d13 +size 5569665248 diff --git a/LITTLEBIT-7.8B-Summary-v1.0.Q5_K_S.gguf b/LITTLEBIT-7.8B-Summary-v1.0.Q5_K_S.gguf new file mode 100644 index 0000000..f59dfc9 --- /dev/null +++ b/LITTLEBIT-7.8B-Summary-v1.0.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c50482126f5ce09976343e3b9327f593f4edb3a4a871b3d22c557d4e1049b8da +size 5435971808 diff --git a/LITTLEBIT-7.8B-Summary-v1.0.Q6_K.gguf b/LITTLEBIT-7.8B-Summary-v1.0.Q6_K.gguf new file mode 100644 index 0000000..a38405e --- /dev/null +++ b/LITTLEBIT-7.8B-Summary-v1.0.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:422e43260229285ce9555ac5af4e150d6c40a04f5d21a63a54fc06cee1d97ea6 +size 6418618592 diff --git a/LITTLEBIT-7.8B-Summary-v1.0.Q8_0.gguf b/LITTLEBIT-7.8B-Summary-v1.0.Q8_0.gguf new file mode 100644 index 0000000..d439b71 --- /dev/null +++ b/LITTLEBIT-7.8B-Summary-v1.0.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d4eaf3850fa066f5846b356faa3ceea0a96911fda7c53b8ccc67df4967d687f +size 8312084704 diff --git a/LITTLEBIT-7.8B-Summary-v1.0.f16.gguf b/LITTLEBIT-7.8B-Summary-v1.0.f16.gguf new file mode 100644 index 0000000..ddc13ac --- /dev/null +++ b/LITTLEBIT-7.8B-Summary-v1.0.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d455e27a438ad0fd8baca70ac756b786e2c08111b5e61e2f984397ec02ca2ea2 +size 15641630944 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b17ac54 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: ByteCompany/LITTLEBIT-7.8B-Summary-v1.0 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/ByteCompany/LITTLEBIT-7.8B-Summary-v1.0 + + +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/LITTLEBIT-7.8B-Summary-v1.0-GGUF/resolve/main/LITTLEBIT-7.8B-Summary-v1.0.Q2_K.gguf) | Q2_K | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/LITTLEBIT-7.8B-Summary-v1.0-GGUF/resolve/main/LITTLEBIT-7.8B-Summary-v1.0.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/LITTLEBIT-7.8B-Summary-v1.0-GGUF/resolve/main/LITTLEBIT-7.8B-Summary-v1.0.Q3_K_M.gguf) | Q3_K_M | 4.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LITTLEBIT-7.8B-Summary-v1.0-GGUF/resolve/main/LITTLEBIT-7.8B-Summary-v1.0.Q3_K_L.gguf) | Q3_K_L | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/LITTLEBIT-7.8B-Summary-v1.0-GGUF/resolve/main/LITTLEBIT-7.8B-Summary-v1.0.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/LITTLEBIT-7.8B-Summary-v1.0-GGUF/resolve/main/LITTLEBIT-7.8B-Summary-v1.0.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LITTLEBIT-7.8B-Summary-v1.0-GGUF/resolve/main/LITTLEBIT-7.8B-Summary-v1.0.Q4_K_M.gguf) | Q4_K_M | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LITTLEBIT-7.8B-Summary-v1.0-GGUF/resolve/main/LITTLEBIT-7.8B-Summary-v1.0.Q5_K_S.gguf) | Q5_K_S | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/LITTLEBIT-7.8B-Summary-v1.0-GGUF/resolve/main/LITTLEBIT-7.8B-Summary-v1.0.Q5_K_M.gguf) | Q5_K_M | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/LITTLEBIT-7.8B-Summary-v1.0-GGUF/resolve/main/LITTLEBIT-7.8B-Summary-v1.0.Q6_K.gguf) | Q6_K | 6.5 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LITTLEBIT-7.8B-Summary-v1.0-GGUF/resolve/main/LITTLEBIT-7.8B-Summary-v1.0.Q8_0.gguf) | Q8_0 | 8.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LITTLEBIT-7.8B-Summary-v1.0-GGUF/resolve/main/LITTLEBIT-7.8B-Summary-v1.0.f16.gguf) | f16 | 15.7 | 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. + +