commit 2e925b68bf77e548171914d1236d8b0e7e9a5567 Author: ModelHub XC Date: Wed Sep 30 10:05:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama3.1-8b-kowiki-instruct-lora-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..67fdf52 --- /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 +llama3.1-8b-kowiki-instruct-lora.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8b-kowiki-instruct-lora.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8b-kowiki-instruct-lora.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8b-kowiki-instruct-lora.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8b-kowiki-instruct-lora.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8b-kowiki-instruct-lora.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8b-kowiki-instruct-lora.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8b-kowiki-instruct-lora.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8b-kowiki-instruct-lora.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8b-kowiki-instruct-lora.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8b-kowiki-instruct-lora.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8b-kowiki-instruct-lora.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..a31f72f --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: aidenjamie/llama3.1-8b-kowiki-instruct-lora +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/aidenjamie/llama3.1-8b-kowiki-instruct-lora + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llama3.1-8b-kowiki-instruct-lora-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/llama3.1-8b-kowiki-instruct-lora-GGUF/resolve/main/llama3.1-8b-kowiki-instruct-lora.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8b-kowiki-instruct-lora-GGUF/resolve/main/llama3.1-8b-kowiki-instruct-lora.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8b-kowiki-instruct-lora-GGUF/resolve/main/llama3.1-8b-kowiki-instruct-lora.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8b-kowiki-instruct-lora-GGUF/resolve/main/llama3.1-8b-kowiki-instruct-lora.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8b-kowiki-instruct-lora-GGUF/resolve/main/llama3.1-8b-kowiki-instruct-lora.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8b-kowiki-instruct-lora-GGUF/resolve/main/llama3.1-8b-kowiki-instruct-lora.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8b-kowiki-instruct-lora-GGUF/resolve/main/llama3.1-8b-kowiki-instruct-lora.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8b-kowiki-instruct-lora-GGUF/resolve/main/llama3.1-8b-kowiki-instruct-lora.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8b-kowiki-instruct-lora-GGUF/resolve/main/llama3.1-8b-kowiki-instruct-lora.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8b-kowiki-instruct-lora-GGUF/resolve/main/llama3.1-8b-kowiki-instruct-lora.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8b-kowiki-instruct-lora-GGUF/resolve/main/llama3.1-8b-kowiki-instruct-lora.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8b-kowiki-instruct-lora-GGUF/resolve/main/llama3.1-8b-kowiki-instruct-lora.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. + + diff --git a/llama3.1-8b-kowiki-instruct-lora.IQ4_XS.gguf b/llama3.1-8b-kowiki-instruct-lora.IQ4_XS.gguf new file mode 100644 index 0000000..8458c1b --- /dev/null +++ b/llama3.1-8b-kowiki-instruct-lora.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b51e09cbd9593a8191dbd6680d8299148f8038792c8bbc96b4a2a4dc66d0c1c0 +size 4484363680 diff --git a/llama3.1-8b-kowiki-instruct-lora.Q2_K.gguf b/llama3.1-8b-kowiki-instruct-lora.Q2_K.gguf new file mode 100644 index 0000000..97092d7 --- /dev/null +++ b/llama3.1-8b-kowiki-instruct-lora.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec3ad53b133e2523e5d524f6af50714d0530f59f4e52a7ebf3bf5395dfda20a4 +size 3179132320 diff --git a/llama3.1-8b-kowiki-instruct-lora.Q3_K_L.gguf b/llama3.1-8b-kowiki-instruct-lora.Q3_K_L.gguf new file mode 100644 index 0000000..0576c62 --- /dev/null +++ b/llama3.1-8b-kowiki-instruct-lora.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e630902e852a5a58044c6d41efc95f11469efeaa5ee50b490d7b0f0fbe8c3a7 +size 4321957280 diff --git a/llama3.1-8b-kowiki-instruct-lora.Q3_K_M.gguf b/llama3.1-8b-kowiki-instruct-lora.Q3_K_M.gguf new file mode 100644 index 0000000..75db315 --- /dev/null +++ b/llama3.1-8b-kowiki-instruct-lora.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae60b2c7bd6bfeeed3b8d4c2bd0c6697c11bc25521ee679a7f10be915ce22487 +size 4018918816 diff --git a/llama3.1-8b-kowiki-instruct-lora.Q3_K_S.gguf b/llama3.1-8b-kowiki-instruct-lora.Q3_K_S.gguf new file mode 100644 index 0000000..48c2989 --- /dev/null +++ b/llama3.1-8b-kowiki-instruct-lora.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a24f35f4302e8fc25b1464fd436a4b96c684af9f393056fd22afbb769aad421 +size 3664500128 diff --git a/llama3.1-8b-kowiki-instruct-lora.Q4_K_M.gguf b/llama3.1-8b-kowiki-instruct-lora.Q4_K_M.gguf new file mode 100644 index 0000000..3812c4b --- /dev/null +++ b/llama3.1-8b-kowiki-instruct-lora.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:776426fca3dbf8bbf8c9dd4065205a2cc2b01f77a87f55b124601d3dd86c5a45 +size 4920735136 diff --git a/llama3.1-8b-kowiki-instruct-lora.Q4_K_S.gguf b/llama3.1-8b-kowiki-instruct-lora.Q4_K_S.gguf new file mode 100644 index 0000000..071b1eb --- /dev/null +++ b/llama3.1-8b-kowiki-instruct-lora.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:027ca85c11ca0bd0c479f9f517fd7258dd32f9b29308827c4a22f3d88f4b5ba8 +size 4692669856 diff --git a/llama3.1-8b-kowiki-instruct-lora.Q5_K_M.gguf b/llama3.1-8b-kowiki-instruct-lora.Q5_K_M.gguf new file mode 100644 index 0000000..139c508 --- /dev/null +++ b/llama3.1-8b-kowiki-instruct-lora.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c54325ac1ed619d66d42b0b28d4994726eaf31607671befec30832834434b81 +size 5732988320 diff --git a/llama3.1-8b-kowiki-instruct-lora.Q5_K_S.gguf b/llama3.1-8b-kowiki-instruct-lora.Q5_K_S.gguf new file mode 100644 index 0000000..9736f20 --- /dev/null +++ b/llama3.1-8b-kowiki-instruct-lora.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:459b167263d7e3524db473e6f52deec201affab3d200ae31ab4c2ae4a94fa6c0 +size 5599294880 diff --git a/llama3.1-8b-kowiki-instruct-lora.Q6_K.gguf b/llama3.1-8b-kowiki-instruct-lora.Q6_K.gguf new file mode 100644 index 0000000..1bc5d1c --- /dev/null +++ b/llama3.1-8b-kowiki-instruct-lora.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d655f107f73df3bc137fce6bc3088d885d8422455353dfaf4af4ca502a37723e +size 6596007328 diff --git a/llama3.1-8b-kowiki-instruct-lora.Q8_0.gguf b/llama3.1-8b-kowiki-instruct-lora.Q8_0.gguf new file mode 100644 index 0000000..9105bc0 --- /dev/null +++ b/llama3.1-8b-kowiki-instruct-lora.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e30ea027bb115cf00fbb9708d3a3a257d4db94bcc3928c4e49e74f1a17213ae +size 8540771744 diff --git a/llama3.1-8b-kowiki-instruct-lora.f16.gguf b/llama3.1-8b-kowiki-instruct-lora.f16.gguf new file mode 100644 index 0000000..a11d4bb --- /dev/null +++ b/llama3.1-8b-kowiki-instruct-lora.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55177c3b05418c0b5b89997a2a2d488b5fc3ae493e1da28151b60502fc579f48 +size 16068892064