commit f6479e23a91fc234854d161a54793458b05b9c06 Author: ModelHub XC Date: Fri Jul 31 10:55:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-8b.UNLEASHED-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..94903f2 --- /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 +Llama-3-8b.UNLEASHED.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8b.UNLEASHED.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8b.UNLEASHED.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8b.UNLEASHED.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8b.UNLEASHED.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8b.UNLEASHED.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8b.UNLEASHED.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8b.UNLEASHED.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8b.UNLEASHED.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8b.UNLEASHED.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8b.UNLEASHED.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8b.UNLEASHED.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-8b.UNLEASHED.IQ4_XS.gguf b/Llama-3-8b.UNLEASHED.IQ4_XS.gguf new file mode 100644 index 0000000..a2a5130 --- /dev/null +++ b/Llama-3-8b.UNLEASHED.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a33dd8de85ce0c616ffaaa258728d5d1c4a96059bffd57d3306cfd3df9d2d90c +size 4484363872 diff --git a/Llama-3-8b.UNLEASHED.Q2_K.gguf b/Llama-3-8b.UNLEASHED.Q2_K.gguf new file mode 100644 index 0000000..2e2fad4 --- /dev/null +++ b/Llama-3-8b.UNLEASHED.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13c8290847d54dad66477687101c0d6199385d5c13f7ae9c9c25af257390f8cd +size 3179132512 diff --git a/Llama-3-8b.UNLEASHED.Q3_K_L.gguf b/Llama-3-8b.UNLEASHED.Q3_K_L.gguf new file mode 100644 index 0000000..4da0586 --- /dev/null +++ b/Llama-3-8b.UNLEASHED.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47ec531a9dab8c08df1c56c21d1206ada9f840d61effbfbe02caac07b44b611c +size 4321957472 diff --git a/Llama-3-8b.UNLEASHED.Q3_K_M.gguf b/Llama-3-8b.UNLEASHED.Q3_K_M.gguf new file mode 100644 index 0000000..52c59b4 --- /dev/null +++ b/Llama-3-8b.UNLEASHED.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b190c159bc291c15fe2aa0f218d16d299730005152e0e0b555c8902772545d0b +size 4018919008 diff --git a/Llama-3-8b.UNLEASHED.Q3_K_S.gguf b/Llama-3-8b.UNLEASHED.Q3_K_S.gguf new file mode 100644 index 0000000..0552167 --- /dev/null +++ b/Llama-3-8b.UNLEASHED.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb2e44c025c31756247e3ea9e39227ab9786cc2fafb5177ee84bd6949d3d72fc +size 3664500320 diff --git a/Llama-3-8b.UNLEASHED.Q4_K_M.gguf b/Llama-3-8b.UNLEASHED.Q4_K_M.gguf new file mode 100644 index 0000000..269f538 --- /dev/null +++ b/Llama-3-8b.UNLEASHED.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ba8bd04ea52a1cc7de12d90a8cbd6a88d6b50f5fac9ef8c8bcffebbe60077f8 +size 4920735328 diff --git a/Llama-3-8b.UNLEASHED.Q4_K_S.gguf b/Llama-3-8b.UNLEASHED.Q4_K_S.gguf new file mode 100644 index 0000000..26d3c9b --- /dev/null +++ b/Llama-3-8b.UNLEASHED.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bb2ea15c801aafd51be019af65ed041206192c22a773b879b285cd9cea5d436 +size 4692670048 diff --git a/Llama-3-8b.UNLEASHED.Q5_K_M.gguf b/Llama-3-8b.UNLEASHED.Q5_K_M.gguf new file mode 100644 index 0000000..44e0486 --- /dev/null +++ b/Llama-3-8b.UNLEASHED.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9682f996b77bf70312934567da6a4046d805041f6da06fef6ee446255c0d9110 +size 5732988512 diff --git a/Llama-3-8b.UNLEASHED.Q5_K_S.gguf b/Llama-3-8b.UNLEASHED.Q5_K_S.gguf new file mode 100644 index 0000000..73fd2ef --- /dev/null +++ b/Llama-3-8b.UNLEASHED.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65d8584918d38196bd7c00efdfc9e2381039c97ed6aac181379601e326c585ab +size 5599295072 diff --git a/Llama-3-8b.UNLEASHED.Q6_K.gguf b/Llama-3-8b.UNLEASHED.Q6_K.gguf new file mode 100644 index 0000000..466cd95 --- /dev/null +++ b/Llama-3-8b.UNLEASHED.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94718a244d164d829d8e1717c3b1ae8c184b621025422b81d5c6abb2647daa5b +size 6596007520 diff --git a/Llama-3-8b.UNLEASHED.Q8_0.gguf b/Llama-3-8b.UNLEASHED.Q8_0.gguf new file mode 100644 index 0000000..38cf4cc --- /dev/null +++ b/Llama-3-8b.UNLEASHED.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36aa786c51efc81d735266ba94e88b6153bd9a2486c04684f5113c4a6423e55b +size 8540771936 diff --git a/Llama-3-8b.UNLEASHED.f16.gguf b/Llama-3-8b.UNLEASHED.f16.gguf new file mode 100644 index 0000000..61b0477 --- /dev/null +++ b/Llama-3-8b.UNLEASHED.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:136e89818bbaa23f79cde2b96052900e0795e3bf5bf29bc247e3828c4dee63c0 +size 16068892256 diff --git a/README.md b/README.md new file mode 100644 index 0000000..497923f --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: raincandy-u/Llama-3-8b.UNLEASHED +datasets: +- unalignment/toxic-dpo-v0.2 +language: +- en +library_name: transformers +license: other +license_link: LICENSE +license_name: llama3 +quantized_by: mradermacher +tags: +- facebook +- meta +- pytorch +- llama +- llama-3 +--- +## About + + + + + + +static quants of https://huggingface.co/raincandy-u/Llama-3-8b.UNLEASHED + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3-8b.UNLEASHED-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.UNLEASHED-GGUF/resolve/main/Llama-3-8b.UNLEASHED.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8b.UNLEASHED-GGUF/resolve/main/Llama-3-8b.UNLEASHED.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8b.UNLEASHED-GGUF/resolve/main/Llama-3-8b.UNLEASHED.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8b.UNLEASHED-GGUF/resolve/main/Llama-3-8b.UNLEASHED.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8b.UNLEASHED-GGUF/resolve/main/Llama-3-8b.UNLEASHED.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8b.UNLEASHED-GGUF/resolve/main/Llama-3-8b.UNLEASHED.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8b.UNLEASHED-GGUF/resolve/main/Llama-3-8b.UNLEASHED.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8b.UNLEASHED-GGUF/resolve/main/Llama-3-8b.UNLEASHED.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8b.UNLEASHED-GGUF/resolve/main/Llama-3-8b.UNLEASHED.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8b.UNLEASHED-GGUF/resolve/main/Llama-3-8b.UNLEASHED.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8b.UNLEASHED-GGUF/resolve/main/Llama-3-8b.UNLEASHED.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8b.UNLEASHED-GGUF/resolve/main/Llama-3-8b.UNLEASHED.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. + +