commit a88eff71be70f3d856bc4852fb843d11b504dd80 Author: ModelHub XC Date: Thu Aug 6 02:55:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3-8B-senator-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8241837 --- /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 +Llama3-8B-senator.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-senator.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-senator.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-senator.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-senator.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-senator.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-senator.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-senator.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-senator.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-senator.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-senator.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-senator.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3-8B-senator.IQ4_XS.gguf b/Llama3-8B-senator.IQ4_XS.gguf new file mode 100644 index 0000000..f21c981 --- /dev/null +++ b/Llama3-8B-senator.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77ede849dec39226fb1712dc5e8c439b0c9610c27d177bac83efa5728778ad14 +size 4484363488 diff --git a/Llama3-8B-senator.Q2_K.gguf b/Llama3-8B-senator.Q2_K.gguf new file mode 100644 index 0000000..186e638 --- /dev/null +++ b/Llama3-8B-senator.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31e43d546b44c111f71b2b130886213c737de789770312217e7fd1aa574cbaae +size 3179132128 diff --git a/Llama3-8B-senator.Q3_K_L.gguf b/Llama3-8B-senator.Q3_K_L.gguf new file mode 100644 index 0000000..c8a7521 --- /dev/null +++ b/Llama3-8B-senator.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4d3f518c1b1367eb80cbfef7ffa0bcfabaeac9fc6d62a076c054b0cf0036568 +size 4321957088 diff --git a/Llama3-8B-senator.Q3_K_M.gguf b/Llama3-8B-senator.Q3_K_M.gguf new file mode 100644 index 0000000..fb977ec --- /dev/null +++ b/Llama3-8B-senator.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4b88860e4caf07e6d4a0832d5e1d531da85e9ecb058c616e721edaccd93029f +size 4018918624 diff --git a/Llama3-8B-senator.Q3_K_S.gguf b/Llama3-8B-senator.Q3_K_S.gguf new file mode 100644 index 0000000..93bcbdc --- /dev/null +++ b/Llama3-8B-senator.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:417435f35bd410caea76cdfb04cbd50ee6b3a6902b79440249a07484d185198d +size 3664499936 diff --git a/Llama3-8B-senator.Q4_K_M.gguf b/Llama3-8B-senator.Q4_K_M.gguf new file mode 100644 index 0000000..7d1b699 --- /dev/null +++ b/Llama3-8B-senator.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c5cc468f54d31a9a4fbf046e12d4be6dee4128e78d8724cb5c48d28b532bdf5 +size 4920734944 diff --git a/Llama3-8B-senator.Q4_K_S.gguf b/Llama3-8B-senator.Q4_K_S.gguf new file mode 100644 index 0000000..a238a53 --- /dev/null +++ b/Llama3-8B-senator.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1bb6f36c6996fec50518ba723c6825aa0de9686d28a3b2d38ead9977c42eb35 +size 4692669664 diff --git a/Llama3-8B-senator.Q5_K_M.gguf b/Llama3-8B-senator.Q5_K_M.gguf new file mode 100644 index 0000000..f93e976 --- /dev/null +++ b/Llama3-8B-senator.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d54d7dbdc43b302f317569419f6ab4e7e3997079044d62e35a6e254f8c9b4922 +size 5732988128 diff --git a/Llama3-8B-senator.Q5_K_S.gguf b/Llama3-8B-senator.Q5_K_S.gguf new file mode 100644 index 0000000..14e1c88 --- /dev/null +++ b/Llama3-8B-senator.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:475f67f31e3247543e261bfbaeb49be89d1607d0270822d8677edba8cbeb53a6 +size 5599294688 diff --git a/Llama3-8B-senator.Q6_K.gguf b/Llama3-8B-senator.Q6_K.gguf new file mode 100644 index 0000000..53230d5 --- /dev/null +++ b/Llama3-8B-senator.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4faca4b4bb66a957125779d6a2bc13c8009b2f1e9e0ac495d39aad8ad311e940 +size 6596007136 diff --git a/Llama3-8B-senator.Q8_0.gguf b/Llama3-8B-senator.Q8_0.gguf new file mode 100644 index 0000000..4aadde2 --- /dev/null +++ b/Llama3-8B-senator.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9fbfa5f588c9c0d1bff0ee0dcad9b43db429e143ee1a5a805530f75a3761cbb +size 8540771552 diff --git a/Llama3-8B-senator.f16.gguf b/Llama3-8B-senator.f16.gguf new file mode 100644 index 0000000..8bb6d71 --- /dev/null +++ b/Llama3-8B-senator.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:025e8baa6c622dc16c59b29a7a4e2e4cac3404cbe2482d6f34d9b302444cdf1e +size 16068891872 diff --git a/README.md b/README.md new file mode 100644 index 0000000..82f3746 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: Weiyifan/Llama3-8B-senator +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Weiyifan/Llama3-8B-senator + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama3-8B-senator-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama3-8B-senator-i1-GGUF +## 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/Llama3-8B-senator-GGUF/resolve/main/Llama3-8B-senator.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-senator-GGUF/resolve/main/Llama3-8B-senator.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-senator-GGUF/resolve/main/Llama3-8B-senator.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-senator-GGUF/resolve/main/Llama3-8B-senator.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-senator-GGUF/resolve/main/Llama3-8B-senator.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-senator-GGUF/resolve/main/Llama3-8B-senator.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-senator-GGUF/resolve/main/Llama3-8B-senator.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-senator-GGUF/resolve/main/Llama3-8B-senator.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-senator-GGUF/resolve/main/Llama3-8B-senator.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-senator-GGUF/resolve/main/Llama3-8B-senator.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-senator-GGUF/resolve/main/Llama3-8B-senator.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-senator-GGUF/resolve/main/Llama3-8B-senator.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. + +