commit 46a60041be54f86a4c9f5a4d89210b9188aeabc8 Author: ModelHub XC Date: Sun Aug 2 03:45:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-1b-ws-8-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7d69fb3 --- /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-1b-ws-8.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-1b-ws-8.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-1b-ws-8.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-1b-ws-8.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-1b-ws-8.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-1b-ws-8.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-1b-ws-8.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-1b-ws-8.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-1b-ws-8.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-1b-ws-8.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-1b-ws-8.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-1b-ws-8.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..a3eb0a0 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: distributed/llama-1b-ws-8 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/distributed/llama-1b-ws-8 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llama-1b-ws-8-GGUF).*** + +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/llama-1b-ws-8-GGUF/resolve/main/llama-1b-ws-8.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/llama-1b-ws-8-GGUF/resolve/main/llama-1b-ws-8.Q3_K_S.gguf) | Q3_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-1b-ws-8-GGUF/resolve/main/llama-1b-ws-8.Q3_K_M.gguf) | Q3_K_M | 0.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-1b-ws-8-GGUF/resolve/main/llama-1b-ws-8.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-1b-ws-8-GGUF/resolve/main/llama-1b-ws-8.IQ4_XS.gguf) | IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-1b-ws-8-GGUF/resolve/main/llama-1b-ws-8.Q4_K_S.gguf) | Q4_K_S | 0.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-1b-ws-8-GGUF/resolve/main/llama-1b-ws-8.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-1b-ws-8-GGUF/resolve/main/llama-1b-ws-8.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-1b-ws-8-GGUF/resolve/main/llama-1b-ws-8.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-1b-ws-8-GGUF/resolve/main/llama-1b-ws-8.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-1b-ws-8-GGUF/resolve/main/llama-1b-ws-8.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-1b-ws-8-GGUF/resolve/main/llama-1b-ws-8.f16.gguf) | f16 | 2.3 | 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. + + diff --git a/llama-1b-ws-8.IQ4_XS.gguf b/llama-1b-ws-8.IQ4_XS.gguf new file mode 100644 index 0000000..063db0a --- /dev/null +++ b/llama-1b-ws-8.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c889cf41942de8009c3039a15b5d9e3e6a30f003f9335d31f3c9ef01569902a +size 609801504 diff --git a/llama-1b-ws-8.Q2_K.gguf b/llama-1b-ws-8.Q2_K.gguf new file mode 100644 index 0000000..b75b491 --- /dev/null +++ b/llama-1b-ws-8.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9df93e3e5ade02d8e587c31df97ca1216f8543fcaba07ebda35b4294b01867ed +size 432125216 diff --git a/llama-1b-ws-8.Q3_K_L.gguf b/llama-1b-ws-8.Q3_K_L.gguf new file mode 100644 index 0000000..bf4a6c4 --- /dev/null +++ b/llama-1b-ws-8.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ccf83e1433b0822bcc4d3e0d60bf3899ebc4aa7b0a2b3a5fff43535716b6e43 +size 591521056 diff --git a/llama-1b-ws-8.Q3_K_M.gguf b/llama-1b-ws-8.Q3_K_M.gguf new file mode 100644 index 0000000..0c9391f --- /dev/null +++ b/llama-1b-ws-8.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2381c6d2aa1720063588810934b31dcd1c75495f403ef52573b57edf687ac24d +size 548398368 diff --git a/llama-1b-ws-8.Q3_K_S.gguf b/llama-1b-ws-8.Q3_K_S.gguf new file mode 100644 index 0000000..0eaab6c --- /dev/null +++ b/llama-1b-ws-8.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63f69c12338218f53367faafa82c9256b64b79cbea837b04a2b9164b571ace5c +size 499336480 diff --git a/llama-1b-ws-8.Q4_K_M.gguf b/llama-1b-ws-8.Q4_K_M.gguf new file mode 100644 index 0000000..4e48e45 --- /dev/null +++ b/llama-1b-ws-8.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f952233d517f2609762639d3bb66d466afb473e6f419ccf8d1ee61d1c07c4829 +size 667809056 diff --git a/llama-1b-ws-8.Q4_K_S.gguf b/llama-1b-ws-8.Q4_K_S.gguf new file mode 100644 index 0000000..b759558 --- /dev/null +++ b/llama-1b-ws-8.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73a8188a88962a4fd36b6f855f1eaf40105fb9e44a7d5ee011f1b1e200753046 +size 639866144 diff --git a/llama-1b-ws-8.Q5_K_M.gguf b/llama-1b-ws-8.Q5_K_M.gguf new file mode 100644 index 0000000..c8e4583 --- /dev/null +++ b/llama-1b-ws-8.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae9f5de7bf39862d88a1cd6935068d15222133be733ec4ad3d21876c438aa26d +size 782038304 diff --git a/llama-1b-ws-8.Q5_K_S.gguf b/llama-1b-ws-8.Q5_K_S.gguf new file mode 100644 index 0000000..3123c61 --- /dev/null +++ b/llama-1b-ws-8.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:040147e2bee973efda7b6de602d6c688b15fbaf6ba7a07ed7eabfd8705cbbb6d +size 766022944 diff --git a/llama-1b-ws-8.Q6_K.gguf b/llama-1b-ws-8.Q6_K.gguf new file mode 100644 index 0000000..7d7ef51 --- /dev/null +++ b/llama-1b-ws-8.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a97560fe32d4d2b3f0af08a58e5ceef8779142bfa1d0806f4ce00511994451a5 +size 903406880 diff --git a/llama-1b-ws-8.Q8_0.gguf b/llama-1b-ws-8.Q8_0.gguf new file mode 100644 index 0000000..803bce2 --- /dev/null +++ b/llama-1b-ws-8.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:205b1fe2b8d4836089671bc77997bfd4577f7698b36f3ff1c72209483aabf679 +size 1169802528 diff --git a/llama-1b-ws-8.f16.gguf b/llama-1b-ws-8.f16.gguf new file mode 100644 index 0000000..7349ef1 --- /dev/null +++ b/llama-1b-ws-8.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4885b8699204f93417df9d1f77ca76378c4c417c8c6ee07fb788b9c957701afd +size 2201011488