commit c6998523d9471d62e090d48ce0a24c47e4794ca6 Author: ModelHub XC Date: Sun Jul 19 18:23:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/FineLlama-3.1-8B-v5-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3db82c5 --- /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 +FineLlama-3.1-8B-v5.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +FineLlama-3.1-8B-v5.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FineLlama-3.1-8B-v5.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FineLlama-3.1-8B-v5.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FineLlama-3.1-8B-v5.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +FineLlama-3.1-8B-v5.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +FineLlama-3.1-8B-v5.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +FineLlama-3.1-8B-v5.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FineLlama-3.1-8B-v5.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FineLlama-3.1-8B-v5.f16.gguf filter=lfs diff=lfs merge=lfs -text +FineLlama-3.1-8B-v5.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FineLlama-3.1-8B-v5.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/FineLlama-3.1-8B-v5.IQ4_XS.gguf b/FineLlama-3.1-8B-v5.IQ4_XS.gguf new file mode 100644 index 0000000..e075dff --- /dev/null +++ b/FineLlama-3.1-8B-v5.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:077553a093580525b351d1d7f8536e3b75062316c9f8f6dda13b9d99814e42dc +size 4484364576 diff --git a/FineLlama-3.1-8B-v5.Q2_K.gguf b/FineLlama-3.1-8B-v5.Q2_K.gguf new file mode 100644 index 0000000..1cd08e9 --- /dev/null +++ b/FineLlama-3.1-8B-v5.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61ea98da7f8394e6077242c416a2c81a84629a4c528a19b96d75448a42497ccc +size 3179133216 diff --git a/FineLlama-3.1-8B-v5.Q3_K_L.gguf b/FineLlama-3.1-8B-v5.Q3_K_L.gguf new file mode 100644 index 0000000..ce86f67 --- /dev/null +++ b/FineLlama-3.1-8B-v5.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44327aa5926cc327eb097e54c64b5f38a745fd50a579508b47acb084e4d7ca69 +size 4321958176 diff --git a/FineLlama-3.1-8B-v5.Q3_K_M.gguf b/FineLlama-3.1-8B-v5.Q3_K_M.gguf new file mode 100644 index 0000000..b4267d9 --- /dev/null +++ b/FineLlama-3.1-8B-v5.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cb5acecebe0a546564416cfc4d9477251dd252dc19268c1a79af6a4ed002981 +size 4018919712 diff --git a/FineLlama-3.1-8B-v5.Q3_K_S.gguf b/FineLlama-3.1-8B-v5.Q3_K_S.gguf new file mode 100644 index 0000000..cc22998 --- /dev/null +++ b/FineLlama-3.1-8B-v5.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74d4890f79e796af5eeabd82cd3308c7286425707c3e4fd2c3f7472e6aa34f4c +size 3664501024 diff --git a/FineLlama-3.1-8B-v5.Q4_K_M.gguf b/FineLlama-3.1-8B-v5.Q4_K_M.gguf new file mode 100644 index 0000000..49b31c5 --- /dev/null +++ b/FineLlama-3.1-8B-v5.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfe6d5561c84c145d50436d82f9dbc6c5b94d63dd9c726b13b59b2f3c77ab906 +size 4920736032 diff --git a/FineLlama-3.1-8B-v5.Q4_K_S.gguf b/FineLlama-3.1-8B-v5.Q4_K_S.gguf new file mode 100644 index 0000000..3a11947 --- /dev/null +++ b/FineLlama-3.1-8B-v5.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:511f1171ff62a7e7c59d6a8f1e284dfd5258378952107ef835fbfa18a5b7ec7e +size 4692670752 diff --git a/FineLlama-3.1-8B-v5.Q5_K_M.gguf b/FineLlama-3.1-8B-v5.Q5_K_M.gguf new file mode 100644 index 0000000..a3844ce --- /dev/null +++ b/FineLlama-3.1-8B-v5.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e5c5a73d41617058e736a3fe87e57ef7cad120445ea76b673a3021026e3eca8 +size 5732989216 diff --git a/FineLlama-3.1-8B-v5.Q5_K_S.gguf b/FineLlama-3.1-8B-v5.Q5_K_S.gguf new file mode 100644 index 0000000..9ce2857 --- /dev/null +++ b/FineLlama-3.1-8B-v5.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e17000b74fbe43f19e7eddcb62e9d38f0985dd7b55d3b4ecd683903147d6ccb0 +size 5599295776 diff --git a/FineLlama-3.1-8B-v5.Q6_K.gguf b/FineLlama-3.1-8B-v5.Q6_K.gguf new file mode 100644 index 0000000..a3ab999 --- /dev/null +++ b/FineLlama-3.1-8B-v5.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eba653d4bec387b1e02e1af2a67990c378db9d44047c2fdf604e7c3a8d56f004 +size 6596008224 diff --git a/FineLlama-3.1-8B-v5.Q8_0.gguf b/FineLlama-3.1-8B-v5.Q8_0.gguf new file mode 100644 index 0000000..0fc1b85 --- /dev/null +++ b/FineLlama-3.1-8B-v5.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8945770d5b0d1b37b1f317479225ca3ee543c71e6a64e1d64a95d7e74191652a +size 8540772640 diff --git a/FineLlama-3.1-8B-v5.f16.gguf b/FineLlama-3.1-8B-v5.f16.gguf new file mode 100644 index 0000000..77fe07d --- /dev/null +++ b/FineLlama-3.1-8B-v5.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c142cffc4faf1f04d84be7607ab92b47f2d766358a3fdb6eb710b5ae2ac0ef95 +size 16068892960 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b588682 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: lucashns/FineLlama-3.1-8B-v5 +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/lucashns/FineLlama-3.1-8B-v5 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#FineLlama-3.1-8B-v5-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/FineLlama-3.1-8B-v5-GGUF/resolve/main/FineLlama-3.1-8B-v5.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/FineLlama-3.1-8B-v5-GGUF/resolve/main/FineLlama-3.1-8B-v5.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/FineLlama-3.1-8B-v5-GGUF/resolve/main/FineLlama-3.1-8B-v5.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/FineLlama-3.1-8B-v5-GGUF/resolve/main/FineLlama-3.1-8B-v5.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/FineLlama-3.1-8B-v5-GGUF/resolve/main/FineLlama-3.1-8B-v5.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/FineLlama-3.1-8B-v5-GGUF/resolve/main/FineLlama-3.1-8B-v5.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/FineLlama-3.1-8B-v5-GGUF/resolve/main/FineLlama-3.1-8B-v5.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/FineLlama-3.1-8B-v5-GGUF/resolve/main/FineLlama-3.1-8B-v5.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/FineLlama-3.1-8B-v5-GGUF/resolve/main/FineLlama-3.1-8B-v5.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/FineLlama-3.1-8B-v5-GGUF/resolve/main/FineLlama-3.1-8B-v5.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/FineLlama-3.1-8B-v5-GGUF/resolve/main/FineLlama-3.1-8B-v5.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/FineLlama-3.1-8B-v5-GGUF/resolve/main/FineLlama-3.1-8B-v5.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. + +