commit a1d36f236f850a642a87cddb50030eedaa3fb08d Author: ModelHub XC Date: Tue Oct 27 13:06:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/numfalm-chat-full-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4ff01b9 --- /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 +numfalm-chat-full.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +numfalm-chat-full.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +numfalm-chat-full.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +numfalm-chat-full.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +numfalm-chat-full.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +numfalm-chat-full.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +numfalm-chat-full.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +numfalm-chat-full.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +numfalm-chat-full.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +numfalm-chat-full.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +numfalm-chat-full.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +numfalm-chat-full.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..0d11931 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: wannaphong/numfalm-chat-full +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/wannaphong/numfalm-chat-full + + +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/numfalm-chat-full-GGUF/resolve/main/numfalm-chat-full.Q2_K.gguf) | Q2_K | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/numfalm-chat-full-GGUF/resolve/main/numfalm-chat-full.Q3_K_S.gguf) | Q3_K_S | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/numfalm-chat-full-GGUF/resolve/main/numfalm-chat-full.IQ4_XS.gguf) | IQ4_XS | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/numfalm-chat-full-GGUF/resolve/main/numfalm-chat-full.Q3_K_M.gguf) | Q3_K_M | 2.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/numfalm-chat-full-GGUF/resolve/main/numfalm-chat-full.Q3_K_L.gguf) | Q3_K_L | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/numfalm-chat-full-GGUF/resolve/main/numfalm-chat-full.Q4_K_S.gguf) | Q4_K_S | 2.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/numfalm-chat-full-GGUF/resolve/main/numfalm-chat-full.Q4_K_M.gguf) | Q4_K_M | 2.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/numfalm-chat-full-GGUF/resolve/main/numfalm-chat-full.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/numfalm-chat-full-GGUF/resolve/main/numfalm-chat-full.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/numfalm-chat-full-GGUF/resolve/main/numfalm-chat-full.Q6_K.gguf) | Q6_K | 4.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/numfalm-chat-full-GGUF/resolve/main/numfalm-chat-full.Q8_0.gguf) | Q8_0 | 4.0 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/numfalm-chat-full-GGUF/resolve/main/numfalm-chat-full.f16.gguf) | f16 | 7.4 | 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/numfalm-chat-full.IQ4_XS.gguf b/numfalm-chat-full.IQ4_XS.gguf new file mode 100644 index 0000000..6a35d91 --- /dev/null +++ b/numfalm-chat-full.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:252e1bc967fda4dbd65eb0ff82fa607ad97e509a2c5434b4226c0a2e83b6db52 +size 2164037568 diff --git a/numfalm-chat-full.Q2_K.gguf b/numfalm-chat-full.Q2_K.gguf new file mode 100644 index 0000000..1ced744 --- /dev/null +++ b/numfalm-chat-full.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20a45f348867292a0220dba06006595a760a8eb12020db0cd91c789f301006a8 +size 2148485568 diff --git a/numfalm-chat-full.Q3_K_L.gguf b/numfalm-chat-full.Q3_K_L.gguf new file mode 100644 index 0000000..dd54285 --- /dev/null +++ b/numfalm-chat-full.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25947cec4034820a11a70b423b890a40771f6a9e12208146f06236c623d57cad +size 2383109568 diff --git a/numfalm-chat-full.Q3_K_M.gguf b/numfalm-chat-full.Q3_K_M.gguf new file mode 100644 index 0000000..9063379 --- /dev/null +++ b/numfalm-chat-full.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:051972eabbca75af7b767cc8869df470f834483e7264cf0cf4c2039337ed9985 +size 2307909568 diff --git a/numfalm-chat-full.Q3_K_S.gguf b/numfalm-chat-full.Q3_K_S.gguf new file mode 100644 index 0000000..0e828d5 --- /dev/null +++ b/numfalm-chat-full.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7db63e6c6ca760fb5661bb55911c2641e4a4d72bc25dbc91772b359fba1ba0d4 +size 2148485568 diff --git a/numfalm-chat-full.Q4_K_M.gguf b/numfalm-chat-full.Q4_K_M.gguf new file mode 100644 index 0000000..4d0843a --- /dev/null +++ b/numfalm-chat-full.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6926d964ed2450e1b61a0d8efe88d98b243675790608a670a4f8aff6d9239390 +size 2761579968 diff --git a/numfalm-chat-full.Q4_K_S.gguf b/numfalm-chat-full.Q4_K_S.gguf new file mode 100644 index 0000000..fd19cf0 --- /dev/null +++ b/numfalm-chat-full.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33cf1e65239edd596abc13e05c732d970b2e1a5cc3aec5ba13d5eadf3d125bb3 +size 2584619968 diff --git a/numfalm-chat-full.Q5_K_M.gguf b/numfalm-chat-full.Q5_K_M.gguf new file mode 100644 index 0000000..e0ddab7 --- /dev/null +++ b/numfalm-chat-full.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0468763fea4804b0520163cb9fe7dbbac6971da4f28045344add9ebacbd710bb +size 2944991168 diff --git a/numfalm-chat-full.Q5_K_S.gguf b/numfalm-chat-full.Q5_K_S.gguf new file mode 100644 index 0000000..feadfe8 --- /dev/null +++ b/numfalm-chat-full.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81d91d99d35d7e91e3f9f3d834fbef964d61a3f13ae555263703c5b996a90d3c +size 2791071168 diff --git a/numfalm-chat-full.Q6_K.gguf b/numfalm-chat-full.Q6_K.gguf new file mode 100644 index 0000000..974e062 --- /dev/null +++ b/numfalm-chat-full.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f7dd57c6e87c8bc71753464f1c1db0225dcd09297ae8e2372ee45add9829442 +size 3862047168 diff --git a/numfalm-chat-full.Q8_0.gguf b/numfalm-chat-full.Q8_0.gguf new file mode 100644 index 0000000..22ce8b8 --- /dev/null +++ b/numfalm-chat-full.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca684245e5cb1f17d40d2204bc354293c1fd7774ccf503ad8a8aed3170c1ef4f +size 3862047168 diff --git a/numfalm-chat-full.f16.gguf b/numfalm-chat-full.f16.gguf new file mode 100644 index 0000000..d865711 --- /dev/null +++ b/numfalm-chat-full.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b53b5198ff73e3ee1d2a5b28678ec738c9776a251d6d8a2042bdb29c7f415861 +size 7267743168