commit 1271515b277b3d860fdd316a2faec65205529374 Author: ModelHub XC Date: Sun May 10 21:17:29 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-8B-Bespoke-H4-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9a14d51 --- /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 +Llama-8B-Bespoke-H4.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-8B-Bespoke-H4.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-8B-Bespoke-H4.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-8B-Bespoke-H4.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-8B-Bespoke-H4.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-8B-Bespoke-H4.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-8B-Bespoke-H4.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-8B-Bespoke-H4.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-8B-Bespoke-H4.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-8B-Bespoke-H4.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-8B-Bespoke-H4.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-8B-Bespoke-H4.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-8B-Bespoke-H4.IQ4_XS.gguf b/Llama-8B-Bespoke-H4.IQ4_XS.gguf new file mode 100644 index 0000000..ccd50fa --- /dev/null +++ b/Llama-8B-Bespoke-H4.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c92a3b97d83e7321a9500a68e8dea08204db8e3678e4e0b6402b7b125362b879 +size 4484368416 diff --git a/Llama-8B-Bespoke-H4.Q2_K.gguf b/Llama-8B-Bespoke-H4.Q2_K.gguf new file mode 100644 index 0000000..38fd0d8 --- /dev/null +++ b/Llama-8B-Bespoke-H4.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4f95e4e3bde626e2558c7d3897c56b8433a1b4ee0ecf6d2dd48790a4c82b0d1 +size 3179137056 diff --git a/Llama-8B-Bespoke-H4.Q3_K_L.gguf b/Llama-8B-Bespoke-H4.Q3_K_L.gguf new file mode 100644 index 0000000..e5ed372 --- /dev/null +++ b/Llama-8B-Bespoke-H4.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36b9133f1dcec207fc63b19577192a82f8ea72ad1f77ddfa1a6c85e35344b744 +size 4321962016 diff --git a/Llama-8B-Bespoke-H4.Q3_K_M.gguf b/Llama-8B-Bespoke-H4.Q3_K_M.gguf new file mode 100644 index 0000000..f9bf7f3 --- /dev/null +++ b/Llama-8B-Bespoke-H4.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16c18d19509810fb5a6b620f747ad4f536d81840fb0646b95c648285e2bf233f +size 4018923552 diff --git a/Llama-8B-Bespoke-H4.Q3_K_S.gguf b/Llama-8B-Bespoke-H4.Q3_K_S.gguf new file mode 100644 index 0000000..79f7f2a --- /dev/null +++ b/Llama-8B-Bespoke-H4.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b20cc292d94b0dd8e37886b3d9a1bc2cc4b9a7a6ede0f9371e30105db55c1225 +size 3664504864 diff --git a/Llama-8B-Bespoke-H4.Q4_K_M.gguf b/Llama-8B-Bespoke-H4.Q4_K_M.gguf new file mode 100644 index 0000000..c9e070f --- /dev/null +++ b/Llama-8B-Bespoke-H4.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a32b54655a78780796c76f66fcb2172b87f689de4e8dfe75369e853c8e4dd5b +size 4920739872 diff --git a/Llama-8B-Bespoke-H4.Q4_K_S.gguf b/Llama-8B-Bespoke-H4.Q4_K_S.gguf new file mode 100644 index 0000000..40f021b --- /dev/null +++ b/Llama-8B-Bespoke-H4.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7885a87db3876250e7f21468f60906268bd60def536887106346fa64eae9017e +size 4692674592 diff --git a/Llama-8B-Bespoke-H4.Q5_K_M.gguf b/Llama-8B-Bespoke-H4.Q5_K_M.gguf new file mode 100644 index 0000000..9976902 --- /dev/null +++ b/Llama-8B-Bespoke-H4.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec53658425d08a44b6eb70a794d99a15c3f9530b99a2aaa13dec99f1f2ea2524 +size 5732993056 diff --git a/Llama-8B-Bespoke-H4.Q5_K_S.gguf b/Llama-8B-Bespoke-H4.Q5_K_S.gguf new file mode 100644 index 0000000..64d20d4 --- /dev/null +++ b/Llama-8B-Bespoke-H4.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6f015fe72bcbd9f1123fcb46634e9b17700eb330684fa19c2f6ac07f2bf7e66 +size 5599299616 diff --git a/Llama-8B-Bespoke-H4.Q6_K.gguf b/Llama-8B-Bespoke-H4.Q6_K.gguf new file mode 100644 index 0000000..53a4b2f --- /dev/null +++ b/Llama-8B-Bespoke-H4.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc3e2c59b95429514968471cb819208b341ef4143578077be169de4fe42c3209 +size 6596012064 diff --git a/Llama-8B-Bespoke-H4.Q8_0.gguf b/Llama-8B-Bespoke-H4.Q8_0.gguf new file mode 100644 index 0000000..cabf8bb --- /dev/null +++ b/Llama-8B-Bespoke-H4.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:010811764989c46a2796e6c06e26ae4b52169559ead8bf65ec68c26e04c919d7 +size 8540776480 diff --git a/Llama-8B-Bespoke-H4.f16.gguf b/Llama-8B-Bespoke-H4.f16.gguf new file mode 100644 index 0000000..4a5b86d --- /dev/null +++ b/Llama-8B-Bespoke-H4.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd7969aace7530668621c4ce98bb512d666ad012d993f0c8e700fa3841df4c3d +size 16068896800 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9fc0531 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: loubnabnl/Llama-8B-Bespoke-H4 +datasets: HuggingFaceH4/Bespoke-Stratos-17k +language: +- en +library_name: transformers +model_name: Llama-8B-Bespoke-H4 +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/loubnabnl/Llama-8B-Bespoke-H4 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-8B-Bespoke-H4-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/Llama-8B-Bespoke-H4-GGUF/resolve/main/Llama-8B-Bespoke-H4.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-8B-Bespoke-H4-GGUF/resolve/main/Llama-8B-Bespoke-H4.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-8B-Bespoke-H4-GGUF/resolve/main/Llama-8B-Bespoke-H4.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-8B-Bespoke-H4-GGUF/resolve/main/Llama-8B-Bespoke-H4.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-8B-Bespoke-H4-GGUF/resolve/main/Llama-8B-Bespoke-H4.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-8B-Bespoke-H4-GGUF/resolve/main/Llama-8B-Bespoke-H4.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-8B-Bespoke-H4-GGUF/resolve/main/Llama-8B-Bespoke-H4.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-8B-Bespoke-H4-GGUF/resolve/main/Llama-8B-Bespoke-H4.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-8B-Bespoke-H4-GGUF/resolve/main/Llama-8B-Bespoke-H4.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-8B-Bespoke-H4-GGUF/resolve/main/Llama-8B-Bespoke-H4.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-8B-Bespoke-H4-GGUF/resolve/main/Llama-8B-Bespoke-H4.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-8B-Bespoke-H4-GGUF/resolve/main/Llama-8B-Bespoke-H4.f16.gguf) | f16 | 16.2 | 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. + +