commit db7a499f3a2c7f90c20680ee8061047c7b85f72a Author: ModelHub XC Date: Mon Sep 28 06:41:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-bllossom-8B-PM1-finetuned-v1-30-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..005cd16 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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-bllossom-8B-PM1-finetuned-v1-30.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-bllossom-8B-PM1-finetuned-v1-30.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-bllossom-8B-PM1-finetuned-v1-30.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-bllossom-8B-PM1-finetuned-v1-30.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-bllossom-8B-PM1-finetuned-v1-30.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-bllossom-8B-PM1-finetuned-v1-30.IQ3_M.gguf b/Llama-3-bllossom-8B-PM1-finetuned-v1-30.IQ3_M.gguf new file mode 100644 index 0000000..9d943f1 --- /dev/null +++ b/Llama-3-bllossom-8B-PM1-finetuned-v1-30.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77c474871d8980e77034dcd41ac97d2e1bc54117bbe5ca3e9cd29a3235423740 +size 3784824480 diff --git a/Llama-3-bllossom-8B-PM1-finetuned-v1-30.IQ3_S.gguf b/Llama-3-bllossom-8B-PM1-finetuned-v1-30.IQ3_S.gguf new file mode 100644 index 0000000..5de51e7 --- /dev/null +++ b/Llama-3-bllossom-8B-PM1-finetuned-v1-30.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72c920192f663bcea09e6f163bde70ed347ba340a2ee3051f5340bd248313d29 +size 3682326176 diff --git a/Llama-3-bllossom-8B-PM1-finetuned-v1-30.IQ3_XS.gguf b/Llama-3-bllossom-8B-PM1-finetuned-v1-30.IQ3_XS.gguf new file mode 100644 index 0000000..b40a891 --- /dev/null +++ b/Llama-3-bllossom-8B-PM1-finetuned-v1-30.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdbf3d51fa253972b9191004ca99f1fc55db0bf17cb6fdc7d3d4df71c621113c +size 3518748320 diff --git a/Llama-3-bllossom-8B-PM1-finetuned-v1-30.IQ4_XS.gguf b/Llama-3-bllossom-8B-PM1-finetuned-v1-30.IQ4_XS.gguf new file mode 100644 index 0000000..72f339c --- /dev/null +++ b/Llama-3-bllossom-8B-PM1-finetuned-v1-30.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b1b67d6e647298cb02c1abdcaaaef19671e08c0bec7932a93a27bd2b2b44c78 +size 4484363936 diff --git a/Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q2_K.gguf b/Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q2_K.gguf new file mode 100644 index 0000000..743329f --- /dev/null +++ b/Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e07197d153311463cad055bed33747c900dc625e28d5d00e3d15068cb3fbc5a +size 3179132576 diff --git a/Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q3_K_L.gguf b/Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q3_K_L.gguf new file mode 100644 index 0000000..84cbf10 --- /dev/null +++ b/Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:025e79fc45c1e18e9a0d690431bc5c4c57ba3c5b0be48e5415d00e921f790a0c +size 4321957536 diff --git a/Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q3_K_M.gguf b/Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q3_K_M.gguf new file mode 100644 index 0000000..fc08921 --- /dev/null +++ b/Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:200bb74b60e47147a7bafc4aa8815d338c8e86c19e8031b90bfa48ca6d9146ca +size 4018919072 diff --git a/Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q3_K_S.gguf b/Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q3_K_S.gguf new file mode 100644 index 0000000..2fa08a0 --- /dev/null +++ b/Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80456cbdd1b3454fdb9448fa573e5974ad6c9d40600bd8696c4420c686b84e92 +size 3664500384 diff --git a/Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q4_K_M.gguf b/Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q4_K_M.gguf new file mode 100644 index 0000000..f5875de --- /dev/null +++ b/Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1ddbc72f83ec25d21ee52ffe5aa53eeea15a3046e19b0ad72c5cb4fbb22f6bb +size 4920735392 diff --git a/Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q4_K_S.gguf b/Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q4_K_S.gguf new file mode 100644 index 0000000..fdf08d6 --- /dev/null +++ b/Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61d1e221308d3021674a3b539ed3eea85c18eab8f05a722a04c5e0277fca4d7e +size 4692670112 diff --git a/Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q5_K_M.gguf b/Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q5_K_M.gguf new file mode 100644 index 0000000..7a96946 --- /dev/null +++ b/Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebf228251d16d62230dfe5cb9e42abee8f2590934663570e6fb17afe444ead5b +size 5732988576 diff --git a/Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q5_K_S.gguf b/Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q5_K_S.gguf new file mode 100644 index 0000000..6a83b5c --- /dev/null +++ b/Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5c6c480b8fd3005f227cda9100f6c37ad187600c1aa135eac23bf08701dfb2c +size 5599295136 diff --git a/Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q6_K.gguf b/Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q6_K.gguf new file mode 100644 index 0000000..b1157c2 --- /dev/null +++ b/Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d670e76e6161401b8219b2146ae30ebbbe988324cce6b908ce44cd67a14548b1 +size 6596007584 diff --git a/Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q8_0.gguf b/Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q8_0.gguf new file mode 100644 index 0000000..a601ca0 --- /dev/null +++ b/Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e7b9e395df5e225f0e123e07397e161b3175fb6ce8cec8d5f169acc2734ecbd +size 8540772000 diff --git a/Llama-3-bllossom-8B-PM1-finetuned-v1-30.f16.gguf b/Llama-3-bllossom-8B-PM1-finetuned-v1-30.f16.gguf new file mode 100644 index 0000000..0e00bdc --- /dev/null +++ b/Llama-3-bllossom-8B-PM1-finetuned-v1-30.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f81867c2f766914ac17d756b0d729f3203a733e6aa50de8b3eecf3e22dcb160 +size 16068892320 diff --git a/README.md b/README.md new file mode 100644 index 0000000..29ac07b --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: passionMan/Llama-3-bllossom-8B-PM1-finetuned-v1-30 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/passionMan/Llama-3-bllossom-8B-PM1-finetuned-v1-30 + + +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/Llama-3-bllossom-8B-PM1-finetuned-v1-30-GGUF/resolve/main/Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-bllossom-8B-PM1-finetuned-v1-30-GGUF/resolve/main/Llama-3-bllossom-8B-PM1-finetuned-v1-30.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-bllossom-8B-PM1-finetuned-v1-30-GGUF/resolve/main/Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-bllossom-8B-PM1-finetuned-v1-30-GGUF/resolve/main/Llama-3-bllossom-8B-PM1-finetuned-v1-30.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-bllossom-8B-PM1-finetuned-v1-30-GGUF/resolve/main/Llama-3-bllossom-8B-PM1-finetuned-v1-30.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-bllossom-8B-PM1-finetuned-v1-30-GGUF/resolve/main/Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-bllossom-8B-PM1-finetuned-v1-30-GGUF/resolve/main/Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-bllossom-8B-PM1-finetuned-v1-30-GGUF/resolve/main/Llama-3-bllossom-8B-PM1-finetuned-v1-30.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-bllossom-8B-PM1-finetuned-v1-30-GGUF/resolve/main/Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-bllossom-8B-PM1-finetuned-v1-30-GGUF/resolve/main/Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-bllossom-8B-PM1-finetuned-v1-30-GGUF/resolve/main/Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-bllossom-8B-PM1-finetuned-v1-30-GGUF/resolve/main/Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-bllossom-8B-PM1-finetuned-v1-30-GGUF/resolve/main/Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-bllossom-8B-PM1-finetuned-v1-30-GGUF/resolve/main/Llama-3-bllossom-8B-PM1-finetuned-v1-30.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-bllossom-8B-PM1-finetuned-v1-30-GGUF/resolve/main/Llama-3-bllossom-8B-PM1-finetuned-v1-30.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. + +