commit fbd44c6315429892aadb9684d9e7b56a8add397b Author: ModelHub XC Date: Tue Oct 27 15:40:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/cerebras-256m-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e9b3120 --- /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 +cerebras-256m.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +cerebras-256m.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +cerebras-256m.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +cerebras-256m.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +cerebras-256m.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +cerebras-256m.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +cerebras-256m.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +cerebras-256m.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +cerebras-256m.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +cerebras-256m.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +cerebras-256m.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +cerebras-256m.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..91b839e --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: BeardedMonster/cerebras-256m +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/BeardedMonster/cerebras-256m + + +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/cerebras-256m-GGUF/resolve/main/cerebras-256m.Q2_K.gguf) | Q2_K | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/cerebras-256m-GGUF/resolve/main/cerebras-256m.Q3_K_S.gguf) | Q3_K_S | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/cerebras-256m-GGUF/resolve/main/cerebras-256m.IQ4_XS.gguf) | IQ4_XS | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/cerebras-256m-GGUF/resolve/main/cerebras-256m.Q3_K_M.gguf) | Q3_K_M | 0.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/cerebras-256m-GGUF/resolve/main/cerebras-256m.Q3_K_L.gguf) | Q3_K_L | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/cerebras-256m-GGUF/resolve/main/cerebras-256m.Q4_K_S.gguf) | Q4_K_S | 0.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/cerebras-256m-GGUF/resolve/main/cerebras-256m.Q4_K_M.gguf) | Q4_K_M | 0.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/cerebras-256m-GGUF/resolve/main/cerebras-256m.Q5_K_S.gguf) | Q5_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/cerebras-256m-GGUF/resolve/main/cerebras-256m.Q5_K_M.gguf) | Q5_K_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/cerebras-256m-GGUF/resolve/main/cerebras-256m.Q6_K.gguf) | Q6_K | 0.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/cerebras-256m-GGUF/resolve/main/cerebras-256m.Q8_0.gguf) | Q8_0 | 0.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/cerebras-256m-GGUF/resolve/main/cerebras-256m.f16.gguf) | f16 | 0.7 | 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. + + diff --git a/cerebras-256m.IQ4_XS.gguf b/cerebras-256m.IQ4_XS.gguf new file mode 100644 index 0000000..fdd3df8 --- /dev/null +++ b/cerebras-256m.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a53c19125b5074fd20eba18b9e2df2f739b950b89a7f2328a7ee30411587d133 +size 210877344 diff --git a/cerebras-256m.Q2_K.gguf b/cerebras-256m.Q2_K.gguf new file mode 100644 index 0000000..dfb9570 --- /dev/null +++ b/cerebras-256m.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17c822ce8012566d2dd024419bcc051219bf85443c7bbb855cf274e64549ae5e +size 203404960 diff --git a/cerebras-256m.Q3_K_L.gguf b/cerebras-256m.Q3_K_L.gguf new file mode 100644 index 0000000..cf93fbe --- /dev/null +++ b/cerebras-256m.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1d827858826dc98bed085902fc309b3875e693f97bea74245ffe6dae93d3329 +size 229817248 diff --git a/cerebras-256m.Q3_K_M.gguf b/cerebras-256m.Q3_K_M.gguf new file mode 100644 index 0000000..93f4cb1 --- /dev/null +++ b/cerebras-256m.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cd92e36fd79781ddafbcd774d7bbef84f25467cb206cb344dc1329dd0e4eaac +size 220495264 diff --git a/cerebras-256m.Q3_K_S.gguf b/cerebras-256m.Q3_K_S.gguf new file mode 100644 index 0000000..70360bf --- /dev/null +++ b/cerebras-256m.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca7e5b95fd193fdb6da48e36d65ae06a70b0945ab20f3251b2f768b7d764d8c5 +size 203404960 diff --git a/cerebras-256m.Q4_K_M.gguf b/cerebras-256m.Q4_K_M.gguf new file mode 100644 index 0000000..73594b7 --- /dev/null +++ b/cerebras-256m.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3520be8df3b394a0ad795c582c7497906c78f4de83ba869a29950928213f554f +size 246048160 diff --git a/cerebras-256m.Q4_K_S.gguf b/cerebras-256m.Q4_K_S.gguf new file mode 100644 index 0000000..a120767 --- /dev/null +++ b/cerebras-256m.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7087ca9dd6632f80222d5eecaf98a5056663c14becfa36c566a39872b7a28139 +size 236208288 diff --git a/cerebras-256m.Q5_K_M.gguf b/cerebras-256m.Q5_K_M.gguf new file mode 100644 index 0000000..3ebdd60 --- /dev/null +++ b/cerebras-256m.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12f54ffd7678e805c4df9f5835552e2cc0c8011d7f2b0e4353845625f9b86804 +size 274916128 diff --git a/cerebras-256m.Q5_K_S.gguf b/cerebras-256m.Q5_K_S.gguf new file mode 100644 index 0000000..eef6dbf --- /dev/null +++ b/cerebras-256m.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a34ddfb0eeb40decd07b91ae321e318ef59ddb6ae2821d0df90323acb22d74c +size 255606304 diff --git a/cerebras-256m.Q6_K.gguf b/cerebras-256m.Q6_K.gguf new file mode 100644 index 0000000..3703ae3 --- /dev/null +++ b/cerebras-256m.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e9eef981525ff4bcd14593bab61f151c9d9c16050516d0f33d687d56005aab2 +size 322928832 diff --git a/cerebras-256m.Q8_0.gguf b/cerebras-256m.Q8_0.gguf new file mode 100644 index 0000000..0aff92a --- /dev/null +++ b/cerebras-256m.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27d223935ffd5cd8c518fe2e31d0a7a8012638391ea9110df258a76664ce4e62 +size 338983360 diff --git a/cerebras-256m.f16.gguf b/cerebras-256m.f16.gguf new file mode 100644 index 0000000..bdef0e8 --- /dev/null +++ b/cerebras-256m.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:104ddbe1db5562b9789328443731ae60b822777e4c7a6bcdf78dbdc7c1cb41b8 +size 627947264