commit fd0b49a72ce69e9cc9c1b4d8ce955f7a3fd9a0d2 Author: ModelHub XC Date: Sat Jul 4 10:34:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Conllama8b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d88ad9a --- /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 +Conllama8b.f16.gguf filter=lfs diff=lfs merge=lfs -text +Conllama8b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Conllama8b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Conllama8b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Conllama8b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Conllama8b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Conllama8b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Conllama8b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Conllama8b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Conllama8b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Conllama8b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Conllama8b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Conllama8b.IQ4_XS.gguf b/Conllama8b.IQ4_XS.gguf new file mode 100644 index 0000000..3bb7e36 --- /dev/null +++ b/Conllama8b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f6a6c659266432f5e9a211c2aa2ee30ca3ec5986d11cdf94b53b69e681e8911 +size 4484364608 diff --git a/Conllama8b.Q2_K.gguf b/Conllama8b.Q2_K.gguf new file mode 100644 index 0000000..63439b1 --- /dev/null +++ b/Conllama8b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0989ff2f9f1e957b3a8f68219d1c27b99be9a8716e545062900d399ce554f146 +size 3179133248 diff --git a/Conllama8b.Q3_K_L.gguf b/Conllama8b.Q3_K_L.gguf new file mode 100644 index 0000000..db239cd --- /dev/null +++ b/Conllama8b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b2c7e17c494caad1e8ee2b651d24a4989edea5c251fe331b16520ea321e7e94 +size 4321958208 diff --git a/Conllama8b.Q3_K_M.gguf b/Conllama8b.Q3_K_M.gguf new file mode 100644 index 0000000..d2e1623 --- /dev/null +++ b/Conllama8b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9cf13bf8a9bcc0b2634547d9e1b28db26619e18202b2a10aa55e2cec6463f80 +size 4018919744 diff --git a/Conllama8b.Q3_K_S.gguf b/Conllama8b.Q3_K_S.gguf new file mode 100644 index 0000000..5bd5e5e --- /dev/null +++ b/Conllama8b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf7f27845667a79b7d56432bfb75c34bee7793c07662659c7b6b318075f2a7e0 +size 3664501056 diff --git a/Conllama8b.Q4_K_M.gguf b/Conllama8b.Q4_K_M.gguf new file mode 100644 index 0000000..67adfe3 --- /dev/null +++ b/Conllama8b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3679f4769a042d7ff80b721e7c2abbfc0fb7e133d835297d7598c540b5a8f5e +size 4920736064 diff --git a/Conllama8b.Q4_K_S.gguf b/Conllama8b.Q4_K_S.gguf new file mode 100644 index 0000000..eb68558 --- /dev/null +++ b/Conllama8b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e08b4f9436db2de087357d2b6e1ab432712038b010055ed68368941b0d42d72 +size 4692670784 diff --git a/Conllama8b.Q5_K_M.gguf b/Conllama8b.Q5_K_M.gguf new file mode 100644 index 0000000..e0b5ac4 --- /dev/null +++ b/Conllama8b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:016a77e212bf71d0abeb10cc1e0f5432d8115ca238c159032b08233775f3d202 +size 5732989248 diff --git a/Conllama8b.Q5_K_S.gguf b/Conllama8b.Q5_K_S.gguf new file mode 100644 index 0000000..fdaa86e --- /dev/null +++ b/Conllama8b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6cdbf6d58df733f42ac831140af0b0cbdd0aa59bfb1fbd13e995b2bb6169db9 +size 5599295808 diff --git a/Conllama8b.Q6_K.gguf b/Conllama8b.Q6_K.gguf new file mode 100644 index 0000000..40655d6 --- /dev/null +++ b/Conllama8b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be2ec369b29d0ecb9067e9aefad80da51dcb8ad182a176081375b5bc6c5ec7a9 +size 6596008256 diff --git a/Conllama8b.Q8_0.gguf b/Conllama8b.Q8_0.gguf new file mode 100644 index 0000000..486b110 --- /dev/null +++ b/Conllama8b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2087b91aef0663752db84de59d480da3b05028906f802bb2c9831f10c9f821b3 +size 8540772672 diff --git a/Conllama8b.f16.gguf b/Conllama8b.f16.gguf new file mode 100644 index 0000000..a2e4de3 --- /dev/null +++ b/Conllama8b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ddc93bd1649278167ea660dbf2c34e4e59d8969e949ebcdf250787705a74ffd +size 16068892992 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e5d86ff --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: xinyifang/Conllama8b +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + + + + +static quants of https://huggingface.co/xinyifang/Conllama8b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Conllama8b-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/Conllama8b-GGUF/resolve/main/Conllama8b.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Conllama8b-GGUF/resolve/main/Conllama8b.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Conllama8b-GGUF/resolve/main/Conllama8b.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Conllama8b-GGUF/resolve/main/Conllama8b.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Conllama8b-GGUF/resolve/main/Conllama8b.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Conllama8b-GGUF/resolve/main/Conllama8b.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Conllama8b-GGUF/resolve/main/Conllama8b.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Conllama8b-GGUF/resolve/main/Conllama8b.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Conllama8b-GGUF/resolve/main/Conllama8b.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Conllama8b-GGUF/resolve/main/Conllama8b.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Conllama8b-GGUF/resolve/main/Conllama8b.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Conllama8b-GGUF/resolve/main/Conllama8b.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. + +