commit 516af40534af7019fe7242f50c3b64f7cd434a4a Author: ModelHub XC Date: Tue Sep 1 19:30:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LLAMA-3_8B_Unaligned_BETA-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..876f870 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +LLAMA-3_8B_Unaligned_BETA.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA-3_8B_Unaligned_BETA.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA-3_8B_Unaligned_BETA.f16.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA-3_8B_Unaligned_BETA.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA-3_8B_Unaligned_BETA.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA-3_8B_Unaligned_BETA.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA-3_8B_Unaligned_BETA.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA-3_8B_Unaligned_BETA.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA-3_8B_Unaligned_BETA.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA-3_8B_Unaligned_BETA.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA-3_8B_Unaligned_BETA.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA-3_8B_Unaligned_BETA.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA-3_8B_Unaligned_BETA.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LLAMA-3_8B_Unaligned_BETA.IQ4_XS.gguf b/LLAMA-3_8B_Unaligned_BETA.IQ4_XS.gguf new file mode 100644 index 0000000..890a3e7 --- /dev/null +++ b/LLAMA-3_8B_Unaligned_BETA.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f31a6ce003810ae4233d6b1cc5063690011f8d5e88fcd12625e5d5044b9c510 +size 4484374400 diff --git a/LLAMA-3_8B_Unaligned_BETA.Q2_K.gguf b/LLAMA-3_8B_Unaligned_BETA.Q2_K.gguf new file mode 100644 index 0000000..7efcbb4 --- /dev/null +++ b/LLAMA-3_8B_Unaligned_BETA.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f25b1538895e07d950757d0133715a00aede266b55b84f4209ba62d5432f100d +size 3179141376 diff --git a/LLAMA-3_8B_Unaligned_BETA.Q3_K_L.gguf b/LLAMA-3_8B_Unaligned_BETA.Q3_K_L.gguf new file mode 100644 index 0000000..ac2891f --- /dev/null +++ b/LLAMA-3_8B_Unaligned_BETA.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89a1d3d21a84cdf7c638f880e91a1c6da478a34d433c3b4400922b3a895d9343 +size 4321967168 diff --git a/LLAMA-3_8B_Unaligned_BETA.Q3_K_M.gguf b/LLAMA-3_8B_Unaligned_BETA.Q3_K_M.gguf new file mode 100644 index 0000000..ba0b629 --- /dev/null +++ b/LLAMA-3_8B_Unaligned_BETA.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:751acf4059aa34aa1071b02d8d04f5608cc06e81e22a8f0b4308acca3114a8b4 +size 4018928704 diff --git a/LLAMA-3_8B_Unaligned_BETA.Q3_K_S.gguf b/LLAMA-3_8B_Unaligned_BETA.Q3_K_S.gguf new file mode 100644 index 0000000..c6bd5d0 --- /dev/null +++ b/LLAMA-3_8B_Unaligned_BETA.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e969d862e31762471ecdfbf23896b6e1b306402c5934336bdd9fb4363f633ed1 +size 3664510016 diff --git a/LLAMA-3_8B_Unaligned_BETA.Q4_0_4_4.gguf b/LLAMA-3_8B_Unaligned_BETA.Q4_0_4_4.gguf new file mode 100644 index 0000000..56ae628 --- /dev/null +++ b/LLAMA-3_8B_Unaligned_BETA.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebf2b1aaade4998ef675484bffabbae25061708bd253cfbf860305d43f1c92c8 +size 4661223552 diff --git a/LLAMA-3_8B_Unaligned_BETA.Q4_K_M.gguf b/LLAMA-3_8B_Unaligned_BETA.Q4_K_M.gguf new file mode 100644 index 0000000..352b693 --- /dev/null +++ b/LLAMA-3_8B_Unaligned_BETA.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3dd5735a5f19fde439442da6520f17c69428dc0b0ba35d2ea01feaaeadbc546 +size 4920746112 diff --git a/LLAMA-3_8B_Unaligned_BETA.Q4_K_S.gguf b/LLAMA-3_8B_Unaligned_BETA.Q4_K_S.gguf new file mode 100644 index 0000000..07973eb --- /dev/null +++ b/LLAMA-3_8B_Unaligned_BETA.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3744c1ffc6aa1a5b593e85d3f264f15200677647cbd6e7dc8cfa6974f4515c6 +size 4692680832 diff --git a/LLAMA-3_8B_Unaligned_BETA.Q5_K_M.gguf b/LLAMA-3_8B_Unaligned_BETA.Q5_K_M.gguf new file mode 100644 index 0000000..4c943cc --- /dev/null +++ b/LLAMA-3_8B_Unaligned_BETA.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20f8751af0a1a6f6706bce51a94d6c5053a88822f981cf731bd8ca5f04cc53de +size 5733000320 diff --git a/LLAMA-3_8B_Unaligned_BETA.Q5_K_S.gguf b/LLAMA-3_8B_Unaligned_BETA.Q5_K_S.gguf new file mode 100644 index 0000000..d7ddc57 --- /dev/null +++ b/LLAMA-3_8B_Unaligned_BETA.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66a3eaa4db51b0fefba8b6534efd20b8aa52fd900c5a32a954998c377655907c +size 5599306880 diff --git a/LLAMA-3_8B_Unaligned_BETA.Q6_K.gguf b/LLAMA-3_8B_Unaligned_BETA.Q6_K.gguf new file mode 100644 index 0000000..b76d8d8 --- /dev/null +++ b/LLAMA-3_8B_Unaligned_BETA.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ade0c3ff0e1eedcf8740d32a61aa098f59f286b69fc361fdd3c680a4918897d1 +size 6596020416 diff --git a/LLAMA-3_8B_Unaligned_BETA.Q8_0.gguf b/LLAMA-3_8B_Unaligned_BETA.Q8_0.gguf new file mode 100644 index 0000000..188a7e3 --- /dev/null +++ b/LLAMA-3_8B_Unaligned_BETA.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8632ac623b17c1bce6148b2e9d1f1a35df51275cd7b9c60d47bacdd8b184e78b +size 8540788800 diff --git a/LLAMA-3_8B_Unaligned_BETA.f16.gguf b/LLAMA-3_8B_Unaligned_BETA.f16.gguf new file mode 100644 index 0000000..f591fd8 --- /dev/null +++ b/LLAMA-3_8B_Unaligned_BETA.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25ce4a74d95a988e9d7f90013e3cf0a3c5530afc0c2e2079e17b85c19a4821ab +size 16068924480 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4f7d40a --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: SicariusSicariiStuff/LLAMA-3_8B_Unaligned_BETA +language: +- en +library_name: transformers +license: llama3.1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/SicariusSicariiStuff/LLAMA-3_8B_Unaligned_BETA + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/LLAMA-3_8B_Unaligned_BETA-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/LLAMA-3_8B_Unaligned_BETA-GGUF/resolve/main/LLAMA-3_8B_Unaligned_BETA.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA-3_8B_Unaligned_BETA-GGUF/resolve/main/LLAMA-3_8B_Unaligned_BETA.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA-3_8B_Unaligned_BETA-GGUF/resolve/main/LLAMA-3_8B_Unaligned_BETA.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LLAMA-3_8B_Unaligned_BETA-GGUF/resolve/main/LLAMA-3_8B_Unaligned_BETA.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA-3_8B_Unaligned_BETA-GGUF/resolve/main/LLAMA-3_8B_Unaligned_BETA.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA-3_8B_Unaligned_BETA-GGUF/resolve/main/LLAMA-3_8B_Unaligned_BETA.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/LLAMA-3_8B_Unaligned_BETA-GGUF/resolve/main/LLAMA-3_8B_Unaligned_BETA.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLAMA-3_8B_Unaligned_BETA-GGUF/resolve/main/LLAMA-3_8B_Unaligned_BETA.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLAMA-3_8B_Unaligned_BETA-GGUF/resolve/main/LLAMA-3_8B_Unaligned_BETA.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA-3_8B_Unaligned_BETA-GGUF/resolve/main/LLAMA-3_8B_Unaligned_BETA.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA-3_8B_Unaligned_BETA-GGUF/resolve/main/LLAMA-3_8B_Unaligned_BETA.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LLAMA-3_8B_Unaligned_BETA-GGUF/resolve/main/LLAMA-3_8B_Unaligned_BETA.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LLAMA-3_8B_Unaligned_BETA-GGUF/resolve/main/LLAMA-3_8B_Unaligned_BETA.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. + +