commit bc5243c7564a963f29e758f9e5a14ec766903033 Author: ModelHub XC Date: Mon Aug 3 14:03:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama3-1_8b_mlfoundations-dev-stackexchange_scifi-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..47481da --- /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 +llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-1_8b_mlfoundations-dev-stackexchange_scifi.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama3-1_8b_mlfoundations-dev-stackexchange_scifi.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..cf58550 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: mlfoundations-dev/llama3-1_8b_mlfoundations-dev-stackexchange_scifi +language: +- en +library_name: transformers +license: llama3.1 +quantized_by: mradermacher +tags: +- llama-factory +- full +- generated_from_trainer +--- +## About + + + + + + +static quants of https://huggingface.co/mlfoundations-dev/llama3-1_8b_mlfoundations-dev-stackexchange_scifi + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/llama3-1_8b_mlfoundations-dev-stackexchange_scifi-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/llama3-1_8b_mlfoundations-dev-stackexchange_scifi-GGUF/resolve/main/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-1_8b_mlfoundations-dev-stackexchange_scifi-GGUF/resolve/main/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-1_8b_mlfoundations-dev-stackexchange_scifi-GGUF/resolve/main/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-1_8b_mlfoundations-dev-stackexchange_scifi-GGUF/resolve/main/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-1_8b_mlfoundations-dev-stackexchange_scifi-GGUF/resolve/main/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-1_8b_mlfoundations-dev-stackexchange_scifi-GGUF/resolve/main/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3-1_8b_mlfoundations-dev-stackexchange_scifi-GGUF/resolve/main/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3-1_8b_mlfoundations-dev-stackexchange_scifi-GGUF/resolve/main/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-1_8b_mlfoundations-dev-stackexchange_scifi-GGUF/resolve/main/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-1_8b_mlfoundations-dev-stackexchange_scifi-GGUF/resolve/main/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-1_8b_mlfoundations-dev-stackexchange_scifi-GGUF/resolve/main/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-1_8b_mlfoundations-dev-stackexchange_scifi-GGUF/resolve/main/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.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/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.IQ4_XS.gguf b/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.IQ4_XS.gguf new file mode 100644 index 0000000..d6a538c --- /dev/null +++ b/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b0a6657157cd8567ed144e645036a4affcf27e61c0a6ca006cf0d27991e7bf2 +size 4484364352 diff --git a/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q2_K.gguf b/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q2_K.gguf new file mode 100644 index 0000000..c006fbb --- /dev/null +++ b/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19f9da869e114c5805d443b6deb8189c4b3455382111acdd57878943129d078e +size 3179132992 diff --git a/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q3_K_L.gguf b/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q3_K_L.gguf new file mode 100644 index 0000000..2d51207 --- /dev/null +++ b/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a496b528aa9299218731ec6a741a0e3c37dd7c1c439e20375c876b6e5164f9f +size 4321957952 diff --git a/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q3_K_M.gguf b/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q3_K_M.gguf new file mode 100644 index 0000000..e21d1cd --- /dev/null +++ b/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45f03f16c199a0e144df18be37f99b85cb1512e1b048a924457716da24c9003a +size 4018919488 diff --git a/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q3_K_S.gguf b/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q3_K_S.gguf new file mode 100644 index 0000000..bc42965 --- /dev/null +++ b/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d7fbf64842e8dba9d71af8a4ed91c91978bc5aaf8fc654550ddfbab87e11af1 +size 3664500800 diff --git a/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q4_K_M.gguf b/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q4_K_M.gguf new file mode 100644 index 0000000..91239ef --- /dev/null +++ b/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db30a70f25a8098f42dfb7183cb85ee6bd55de8be0e4d3ecef0bade368450e56 +size 4920735808 diff --git a/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q4_K_S.gguf b/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q4_K_S.gguf new file mode 100644 index 0000000..ec74de9 --- /dev/null +++ b/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98d7f06ecdbec3c4f34247ff96bba54783718bba18608b0a0540433a828df8da +size 4692670528 diff --git a/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q5_K_M.gguf b/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q5_K_M.gguf new file mode 100644 index 0000000..1ec7d95 --- /dev/null +++ b/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfc47d9e00a377f2e0e66a6c019301b0c01df73c8ddf705088eb5454d5bf8cbc +size 5732988992 diff --git a/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q5_K_S.gguf b/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q5_K_S.gguf new file mode 100644 index 0000000..c173c0a --- /dev/null +++ b/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:259aeef3051d4e89027ee546524001a79e0006269031842ff6a19e5147a265d9 +size 5599295552 diff --git a/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q6_K.gguf b/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q6_K.gguf new file mode 100644 index 0000000..af5c4da --- /dev/null +++ b/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3e067a319de0033df4bcd98d7f4772a4fe374d354e1368fcc6b71b0debf8513 +size 6596008000 diff --git a/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q8_0.gguf b/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q8_0.gguf new file mode 100644 index 0000000..0e01598 --- /dev/null +++ b/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bb190a5ce3e3ea46053236e98bed3ccba9d87777ed2eb3bc5d7b39b629bb894 +size 8540772416 diff --git a/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.f16.gguf b/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.f16.gguf new file mode 100644 index 0000000..b437707 --- /dev/null +++ b/llama3-1_8b_mlfoundations-dev-stackexchange_scifi.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08adc4fe91352b2185b007a38b028edc8ce89366b4b5465e85dc07c599706509 +size 16068892736