commit 376d750c16d4c6623d48137561c5309ffb9f8319 Author: ModelHub XC Date: Fri Sep 4 16:35:04 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Novi-Delhi-Llama-3.1-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7f24b95 --- /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 +Novi-Delhi-Llama-3.1-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Novi-Delhi-Llama-3.1-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Novi-Delhi-Llama-3.1-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Novi-Delhi-Llama-3.1-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Novi-Delhi-Llama-3.1-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Novi-Delhi-Llama-3.1-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Novi-Delhi-Llama-3.1-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Novi-Delhi-Llama-3.1-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Novi-Delhi-Llama-3.1-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Novi-Delhi-Llama-3.1-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Novi-Delhi-Llama-3.1-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Novi-Delhi-Llama-3.1-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Novi-Delhi-Llama-3.1-8B.IQ4_XS.gguf b/Novi-Delhi-Llama-3.1-8B.IQ4_XS.gguf new file mode 100644 index 0000000..8a010eb --- /dev/null +++ b/Novi-Delhi-Llama-3.1-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6022d7cf7d1fd4081b899837fe2b5b43ad8936c8d1566c5722657a759841a4ab +size 609809216 diff --git a/Novi-Delhi-Llama-3.1-8B.Q2_K.gguf b/Novi-Delhi-Llama-3.1-8B.Q2_K.gguf new file mode 100644 index 0000000..e2215d2 --- /dev/null +++ b/Novi-Delhi-Llama-3.1-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7238ba494486f272677c43f27813bce7486bc650918491166d380533a236b6af +size 432132928 diff --git a/Novi-Delhi-Llama-3.1-8B.Q3_K_L.gguf b/Novi-Delhi-Llama-3.1-8B.Q3_K_L.gguf new file mode 100644 index 0000000..a8bde5f --- /dev/null +++ b/Novi-Delhi-Llama-3.1-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc371a4c10eb31e5d1eda07b03e0ff1e39d7884ce19f989851b424df116a4053 +size 591528768 diff --git a/Novi-Delhi-Llama-3.1-8B.Q3_K_M.gguf b/Novi-Delhi-Llama-3.1-8B.Q3_K_M.gguf new file mode 100644 index 0000000..9de4548 --- /dev/null +++ b/Novi-Delhi-Llama-3.1-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68179b8ac24205e467a075d45ede5340b3ce97a6e0d8fe36929a7ca38fee783c +size 548406080 diff --git a/Novi-Delhi-Llama-3.1-8B.Q3_K_S.gguf b/Novi-Delhi-Llama-3.1-8B.Q3_K_S.gguf new file mode 100644 index 0000000..dc75817 --- /dev/null +++ b/Novi-Delhi-Llama-3.1-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b5af636b6c002f2f271719ed648ccfd10ec464ffcda043e1629c4ca569b14fa +size 499344192 diff --git a/Novi-Delhi-Llama-3.1-8B.Q4_K_M.gguf b/Novi-Delhi-Llama-3.1-8B.Q4_K_M.gguf new file mode 100644 index 0000000..a6a1798 --- /dev/null +++ b/Novi-Delhi-Llama-3.1-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb76167d931dbec078ccccc4baf6c6cae3652f826c0b6ae9b91beee9e0e7e02 +size 667816768 diff --git a/Novi-Delhi-Llama-3.1-8B.Q4_K_S.gguf b/Novi-Delhi-Llama-3.1-8B.Q4_K_S.gguf new file mode 100644 index 0000000..00a7ba0 --- /dev/null +++ b/Novi-Delhi-Llama-3.1-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d252b895dbfa80a5eae9af429a0a3695502772b354f08cbc42173dc6165ec57 +size 639873856 diff --git a/Novi-Delhi-Llama-3.1-8B.Q5_K_M.gguf b/Novi-Delhi-Llama-3.1-8B.Q5_K_M.gguf new file mode 100644 index 0000000..811f2ac --- /dev/null +++ b/Novi-Delhi-Llama-3.1-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2b63a65acc2d538e0a6cb737069bf236cffd403910b193177e59532b4127a31 +size 782046016 diff --git a/Novi-Delhi-Llama-3.1-8B.Q5_K_S.gguf b/Novi-Delhi-Llama-3.1-8B.Q5_K_S.gguf new file mode 100644 index 0000000..e719044 --- /dev/null +++ b/Novi-Delhi-Llama-3.1-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24140c3545f32aa9160d1913b4be6c9231f21f7657dae0fdbac8bce2f61a6158 +size 766030656 diff --git a/Novi-Delhi-Llama-3.1-8B.Q6_K.gguf b/Novi-Delhi-Llama-3.1-8B.Q6_K.gguf new file mode 100644 index 0000000..42f61b0 --- /dev/null +++ b/Novi-Delhi-Llama-3.1-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a38e1dbe2eaeb8c9ba37a51cb85a383fe7e3b0cc46ad0b3a8b7b6f7cb8197dd0 +size 903414592 diff --git a/Novi-Delhi-Llama-3.1-8B.Q8_0.gguf b/Novi-Delhi-Llama-3.1-8B.Q8_0.gguf new file mode 100644 index 0000000..73e8f86 --- /dev/null +++ b/Novi-Delhi-Llama-3.1-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fefeb6f062cb3dfd7a76d571111e1c08c43a9f66a3c6a5256b6c96184c334af2 +size 1169810240 diff --git a/Novi-Delhi-Llama-3.1-8B.f16.gguf b/Novi-Delhi-Llama-3.1-8B.f16.gguf new file mode 100644 index 0000000..ecb11dd --- /dev/null +++ b/Novi-Delhi-Llama-3.1-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5148bc7d794926a14afeefb26ea4c65049adc195ad06faf68cf5eb19f67c0b0a +size 2201019200 diff --git a/README.md b/README.md new file mode 100644 index 0000000..93d0a19 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: IVentureISB/Novi-Delhi-Llama-3.1-8B +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/IVentureISB/Novi-Delhi-Llama-3.1-8B + + +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/Novi-Delhi-Llama-3.1-8B-GGUF/resolve/main/Novi-Delhi-Llama-3.1-8B.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Novi-Delhi-Llama-3.1-8B-GGUF/resolve/main/Novi-Delhi-Llama-3.1-8B.Q3_K_S.gguf) | Q3_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Novi-Delhi-Llama-3.1-8B-GGUF/resolve/main/Novi-Delhi-Llama-3.1-8B.Q3_K_M.gguf) | Q3_K_M | 0.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Novi-Delhi-Llama-3.1-8B-GGUF/resolve/main/Novi-Delhi-Llama-3.1-8B.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Novi-Delhi-Llama-3.1-8B-GGUF/resolve/main/Novi-Delhi-Llama-3.1-8B.IQ4_XS.gguf) | IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Novi-Delhi-Llama-3.1-8B-GGUF/resolve/main/Novi-Delhi-Llama-3.1-8B.Q4_K_S.gguf) | Q4_K_S | 0.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Novi-Delhi-Llama-3.1-8B-GGUF/resolve/main/Novi-Delhi-Llama-3.1-8B.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Novi-Delhi-Llama-3.1-8B-GGUF/resolve/main/Novi-Delhi-Llama-3.1-8B.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Novi-Delhi-Llama-3.1-8B-GGUF/resolve/main/Novi-Delhi-Llama-3.1-8B.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Novi-Delhi-Llama-3.1-8B-GGUF/resolve/main/Novi-Delhi-Llama-3.1-8B.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Novi-Delhi-Llama-3.1-8B-GGUF/resolve/main/Novi-Delhi-Llama-3.1-8B.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Novi-Delhi-Llama-3.1-8B-GGUF/resolve/main/Novi-Delhi-Llama-3.1-8B.f16.gguf) | f16 | 2.3 | 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. + +