commit b348c4c14d4a9c042e42d15a33d6db61af2e1142 Author: ModelHub XC Date: Tue Sep 22 00:07:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/nessie-v26-llama-3.1-8b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e88f622 --- /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 +nessie-v26-llama-3.1-8b.f16.gguf filter=lfs diff=lfs merge=lfs -text +nessie-v26-llama-3.1-8b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +nessie-v26-llama-3.1-8b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +nessie-v26-llama-3.1-8b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +nessie-v26-llama-3.1-8b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +nessie-v26-llama-3.1-8b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +nessie-v26-llama-3.1-8b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +nessie-v26-llama-3.1-8b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +nessie-v26-llama-3.1-8b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +nessie-v26-llama-3.1-8b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +nessie-v26-llama-3.1-8b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +nessie-v26-llama-3.1-8b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..a1989fd --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: carsonarkova/nessie-v26-llama-3.1-8b +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/carsonarkova/nessie-v26-llama-3.1-8b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#nessie-v26-llama-3.1-8b-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/nessie-v26-llama-3.1-8b-GGUF/resolve/main/nessie-v26-llama-3.1-8b.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/nessie-v26-llama-3.1-8b-GGUF/resolve/main/nessie-v26-llama-3.1-8b.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/nessie-v26-llama-3.1-8b-GGUF/resolve/main/nessie-v26-llama-3.1-8b.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/nessie-v26-llama-3.1-8b-GGUF/resolve/main/nessie-v26-llama-3.1-8b.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/nessie-v26-llama-3.1-8b-GGUF/resolve/main/nessie-v26-llama-3.1-8b.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/nessie-v26-llama-3.1-8b-GGUF/resolve/main/nessie-v26-llama-3.1-8b.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/nessie-v26-llama-3.1-8b-GGUF/resolve/main/nessie-v26-llama-3.1-8b.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/nessie-v26-llama-3.1-8b-GGUF/resolve/main/nessie-v26-llama-3.1-8b.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/nessie-v26-llama-3.1-8b-GGUF/resolve/main/nessie-v26-llama-3.1-8b.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/nessie-v26-llama-3.1-8b-GGUF/resolve/main/nessie-v26-llama-3.1-8b.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/nessie-v26-llama-3.1-8b-GGUF/resolve/main/nessie-v26-llama-3.1-8b.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/nessie-v26-llama-3.1-8b-GGUF/resolve/main/nessie-v26-llama-3.1-8b.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/nessie-v26-llama-3.1-8b.IQ4_XS.gguf b/nessie-v26-llama-3.1-8b.IQ4_XS.gguf new file mode 100644 index 0000000..f1e143b --- /dev/null +++ b/nessie-v26-llama-3.1-8b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:541b927b15b74f40310d2e16869942daad9b9e494d1e155103b5efd83c13fed0 +size 4484367840 diff --git a/nessie-v26-llama-3.1-8b.Q2_K.gguf b/nessie-v26-llama-3.1-8b.Q2_K.gguf new file mode 100644 index 0000000..49d8d59 --- /dev/null +++ b/nessie-v26-llama-3.1-8b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34eededce7f4f0cee2f25d52ae6e9dd849ed32d5ae48d9a36aa4d9c7356dcdaa +size 3179136480 diff --git a/nessie-v26-llama-3.1-8b.Q3_K_L.gguf b/nessie-v26-llama-3.1-8b.Q3_K_L.gguf new file mode 100644 index 0000000..e337f44 --- /dev/null +++ b/nessie-v26-llama-3.1-8b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39473f5f652b53efd5f0a1dc300b78ee60f9dc39116d6192d0f124cca8c4ed64 +size 4321961440 diff --git a/nessie-v26-llama-3.1-8b.Q3_K_M.gguf b/nessie-v26-llama-3.1-8b.Q3_K_M.gguf new file mode 100644 index 0000000..33ca0b7 --- /dev/null +++ b/nessie-v26-llama-3.1-8b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e80d7485c0497815a5f5847525b09014a26d46461b09f019f7c4a7d823e68d5d +size 4018922976 diff --git a/nessie-v26-llama-3.1-8b.Q3_K_S.gguf b/nessie-v26-llama-3.1-8b.Q3_K_S.gguf new file mode 100644 index 0000000..1281a1a --- /dev/null +++ b/nessie-v26-llama-3.1-8b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c983788288d657304f966b04d1925a84affc46bbc63e13480ec384257d4690d +size 3664504288 diff --git a/nessie-v26-llama-3.1-8b.Q4_K_M.gguf b/nessie-v26-llama-3.1-8b.Q4_K_M.gguf new file mode 100644 index 0000000..0403f5c --- /dev/null +++ b/nessie-v26-llama-3.1-8b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60eaf069745b84bde6fca0600a6c378fef9c2584a99b2c20d5c6ef2dfa234ed6 +size 4920739296 diff --git a/nessie-v26-llama-3.1-8b.Q4_K_S.gguf b/nessie-v26-llama-3.1-8b.Q4_K_S.gguf new file mode 100644 index 0000000..3597ec9 --- /dev/null +++ b/nessie-v26-llama-3.1-8b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4551208c5ed4724ca6cf7d0a3acd6303cffde0b8b49af497861730a2c63805f3 +size 4692674016 diff --git a/nessie-v26-llama-3.1-8b.Q5_K_M.gguf b/nessie-v26-llama-3.1-8b.Q5_K_M.gguf new file mode 100644 index 0000000..6c0dc3e --- /dev/null +++ b/nessie-v26-llama-3.1-8b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaeb2aea97adf3c14b6e33f9f20bcddd13b1a42fb4f682515d39af06f6fa3ba3 +size 5732992480 diff --git a/nessie-v26-llama-3.1-8b.Q5_K_S.gguf b/nessie-v26-llama-3.1-8b.Q5_K_S.gguf new file mode 100644 index 0000000..49c95da --- /dev/null +++ b/nessie-v26-llama-3.1-8b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75dcbba3712f8d6d4260b6f7756c925163a09657b5211dc9507a85dd9b13f167 +size 5599299040 diff --git a/nessie-v26-llama-3.1-8b.Q6_K.gguf b/nessie-v26-llama-3.1-8b.Q6_K.gguf new file mode 100644 index 0000000..12c6285 --- /dev/null +++ b/nessie-v26-llama-3.1-8b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4204f50d6d26cb679561259c6381f55d3a7e115e2182e0b55e0920713292034d +size 6596011488 diff --git a/nessie-v26-llama-3.1-8b.Q8_0.gguf b/nessie-v26-llama-3.1-8b.Q8_0.gguf new file mode 100644 index 0000000..fc38896 --- /dev/null +++ b/nessie-v26-llama-3.1-8b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcf9f0fc002482f500e78e5f6e39578d157ba02aeb5811139f487c5c8009391c +size 8540775904 diff --git a/nessie-v26-llama-3.1-8b.f16.gguf b/nessie-v26-llama-3.1-8b.f16.gguf new file mode 100644 index 0000000..19d6312 --- /dev/null +++ b/nessie-v26-llama-3.1-8b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55169281d130f2236b77f723116b10dc19af60badfe2203115dd573f932be118 +size 16068896224