commit 4cb1a12e8ac84de1d37996cfe8f55a3c705a3998 Author: ModelHub XC Date: Tue Oct 27 12:36:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/bling-sheared-llama-1.3b-0.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..75444e5 --- /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 +bling-sheared-llama-1.3b-0.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +bling-sheared-llama-1.3b-0.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +bling-sheared-llama-1.3b-0.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +bling-sheared-llama-1.3b-0.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +bling-sheared-llama-1.3b-0.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +bling-sheared-llama-1.3b-0.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +bling-sheared-llama-1.3b-0.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +bling-sheared-llama-1.3b-0.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +bling-sheared-llama-1.3b-0.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +bling-sheared-llama-1.3b-0.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +bling-sheared-llama-1.3b-0.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +bling-sheared-llama-1.3b-0.1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..7d06cd7 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: llmware/bling-sheared-llama-1.3b-0.1 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/llmware/bling-sheared-llama-1.3b-0.1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#bling-sheared-llama-1.3b-0.1-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/bling-sheared-llama-1.3b-0.1-GGUF/resolve/main/bling-sheared-llama-1.3b-0.1.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/bling-sheared-llama-1.3b-0.1-GGUF/resolve/main/bling-sheared-llama-1.3b-0.1.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/bling-sheared-llama-1.3b-0.1-GGUF/resolve/main/bling-sheared-llama-1.3b-0.1.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/bling-sheared-llama-1.3b-0.1-GGUF/resolve/main/bling-sheared-llama-1.3b-0.1.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/bling-sheared-llama-1.3b-0.1-GGUF/resolve/main/bling-sheared-llama-1.3b-0.1.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/bling-sheared-llama-1.3b-0.1-GGUF/resolve/main/bling-sheared-llama-1.3b-0.1.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/bling-sheared-llama-1.3b-0.1-GGUF/resolve/main/bling-sheared-llama-1.3b-0.1.Q4_K_M.gguf) | Q4_K_M | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/bling-sheared-llama-1.3b-0.1-GGUF/resolve/main/bling-sheared-llama-1.3b-0.1.Q5_K_S.gguf) | Q5_K_S | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/bling-sheared-llama-1.3b-0.1-GGUF/resolve/main/bling-sheared-llama-1.3b-0.1.Q5_K_M.gguf) | Q5_K_M | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/bling-sheared-llama-1.3b-0.1-GGUF/resolve/main/bling-sheared-llama-1.3b-0.1.Q6_K.gguf) | Q6_K | 1.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/bling-sheared-llama-1.3b-0.1-GGUF/resolve/main/bling-sheared-llama-1.3b-0.1.Q8_0.gguf) | Q8_0 | 1.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/bling-sheared-llama-1.3b-0.1-GGUF/resolve/main/bling-sheared-llama-1.3b-0.1.f16.gguf) | f16 | 2.8 | 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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/bling-sheared-llama-1.3b-0.1.IQ4_XS.gguf b/bling-sheared-llama-1.3b-0.1.IQ4_XS.gguf new file mode 100644 index 0000000..b74e2f7 --- /dev/null +++ b/bling-sheared-llama-1.3b-0.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f04367ddad10f66f7036bd68bac5639b885dd395fc5a13629dbecfc27ff4edf +size 749580672 diff --git a/bling-sheared-llama-1.3b-0.1.Q2_K.gguf b/bling-sheared-llama-1.3b-0.1.Q2_K.gguf new file mode 100644 index 0000000..845b95b --- /dev/null +++ b/bling-sheared-llama-1.3b-0.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:671d676e8309f53c8b6f95c2a4e49d1a4a3f87f9f45513a8571165f8fb0e70f9 +size 558682496 diff --git a/bling-sheared-llama-1.3b-0.1.Q3_K_L.gguf b/bling-sheared-llama-1.3b-0.1.Q3_K_L.gguf new file mode 100644 index 0000000..10697e8 --- /dev/null +++ b/bling-sheared-llama-1.3b-0.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1dc5043013c07e3da31340ec26682699de2c2e245abcbe8fc36e2383f362cc3 +size 743367040 diff --git a/bling-sheared-llama-1.3b-0.1.Q3_K_M.gguf b/bling-sheared-llama-1.3b-0.1.Q3_K_M.gguf new file mode 100644 index 0000000..bc3036f --- /dev/null +++ b/bling-sheared-llama-1.3b-0.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ebe9ca0fd60272a504b90660dd9d36131bb0a1086d0263e222514e80b417bb8 +size 703046016 diff --git a/bling-sheared-llama-1.3b-0.1.Q3_K_S.gguf b/bling-sheared-llama-1.3b-0.1.Q3_K_S.gguf new file mode 100644 index 0000000..f116c9e --- /dev/null +++ b/bling-sheared-llama-1.3b-0.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f511ac9510e22c9e7e23127caaadb7e8b3bc8e30bca3db3fd3cd27d078a440a +size 640737664 diff --git a/bling-sheared-llama-1.3b-0.1.Q4_K_M.gguf b/bling-sheared-llama-1.3b-0.1.Q4_K_M.gguf new file mode 100644 index 0000000..078a304 --- /dev/null +++ b/bling-sheared-llama-1.3b-0.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5c15a61081b5176659edbca4ed1a48a02dac7b5b63ab23109e35fd8680ce670 +size 872296832 diff --git a/bling-sheared-llama-1.3b-0.1.Q4_K_S.gguf b/bling-sheared-llama-1.3b-0.1.Q4_K_S.gguf new file mode 100644 index 0000000..9f99f54 --- /dev/null +++ b/bling-sheared-llama-1.3b-0.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92804eee676842cabb27bb91411e58779db7ca518c48f4a33d022f0167b620c0 +size 812806528 diff --git a/bling-sheared-llama-1.3b-0.1.Q5_K_M.gguf b/bling-sheared-llama-1.3b-0.1.Q5_K_M.gguf new file mode 100644 index 0000000..2ec5f08 --- /dev/null +++ b/bling-sheared-llama-1.3b-0.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7ab0798d9ba0dbc8b04186dae6665e08382783ef8239a22c05ce11cd32d5f3b +size 1000616320 diff --git a/bling-sheared-llama-1.3b-0.1.Q5_K_S.gguf b/bling-sheared-llama-1.3b-0.1.Q5_K_S.gguf new file mode 100644 index 0000000..f9e542f --- /dev/null +++ b/bling-sheared-llama-1.3b-0.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e601a09ad79e70e4265d51fe98ec19a7caa9f6439f51f3caf74e7e42cf8ad98 +size 951660928 diff --git a/bling-sheared-llama-1.3b-0.1.Q6_K.gguf b/bling-sheared-llama-1.3b-0.1.Q6_K.gguf new file mode 100644 index 0000000..a0c8992 --- /dev/null +++ b/bling-sheared-llama-1.3b-0.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f1b059834c55b640e28869ebb89af3841ccc14e24f245e6bf239aa31a635e6f +size 1170243968 diff --git a/bling-sheared-llama-1.3b-0.1.Q8_0.gguf b/bling-sheared-llama-1.3b-0.1.Q8_0.gguf new file mode 100644 index 0000000..50a6fac --- /dev/null +++ b/bling-sheared-llama-1.3b-0.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:982af3936fc20c4f7271355f24a004beedacafb57c0af2f509a8b999258195a0 +size 1430544768 diff --git a/bling-sheared-llama-1.3b-0.1.f16.gguf b/bling-sheared-llama-1.3b-0.1.f16.gguf new file mode 100644 index 0000000..8b8f125 --- /dev/null +++ b/bling-sheared-llama-1.3b-0.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:babfe7a5a9864485bb2a9198a3bf1f27faa836068a730f02f20f7fc7329b6fff +size 2691785088