commit 837d611cf89aeb8edab44a312182f4f8e3139e39 Author: ModelHub XC Date: Sat Aug 15 10:49:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3-8b-chat-sarcasm-merged-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..762326b --- /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-3-8b-chat-sarcasm-merged.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-chat-sarcasm-merged.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-chat-sarcasm-merged.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-chat-sarcasm-merged.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-chat-sarcasm-merged.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-chat-sarcasm-merged.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-chat-sarcasm-merged.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-chat-sarcasm-merged.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-chat-sarcasm-merged.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-chat-sarcasm-merged.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-chat-sarcasm-merged.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-chat-sarcasm-merged.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-chat-sarcasm-merged.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-chat-sarcasm-merged.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-chat-sarcasm-merged.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..4a96be3 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: rnrlla/llama-3-8b-chat-sarcasm-merged +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/rnrlla/llama-3-8b-chat-sarcasm-merged + + +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-3-8b-chat-sarcasm-merged-GGUF/resolve/main/llama-3-8b-chat-sarcasm-merged.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-chat-sarcasm-merged-GGUF/resolve/main/llama-3-8b-chat-sarcasm-merged.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-chat-sarcasm-merged-GGUF/resolve/main/llama-3-8b-chat-sarcasm-merged.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-chat-sarcasm-merged-GGUF/resolve/main/llama-3-8b-chat-sarcasm-merged.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-chat-sarcasm-merged-GGUF/resolve/main/llama-3-8b-chat-sarcasm-merged.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-chat-sarcasm-merged-GGUF/resolve/main/llama-3-8b-chat-sarcasm-merged.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-chat-sarcasm-merged-GGUF/resolve/main/llama-3-8b-chat-sarcasm-merged.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-chat-sarcasm-merged-GGUF/resolve/main/llama-3-8b-chat-sarcasm-merged.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-chat-sarcasm-merged-GGUF/resolve/main/llama-3-8b-chat-sarcasm-merged.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-chat-sarcasm-merged-GGUF/resolve/main/llama-3-8b-chat-sarcasm-merged.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-chat-sarcasm-merged-GGUF/resolve/main/llama-3-8b-chat-sarcasm-merged.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-chat-sarcasm-merged-GGUF/resolve/main/llama-3-8b-chat-sarcasm-merged.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-chat-sarcasm-merged-GGUF/resolve/main/llama-3-8b-chat-sarcasm-merged.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-chat-sarcasm-merged-GGUF/resolve/main/llama-3-8b-chat-sarcasm-merged.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-8b-chat-sarcasm-merged-GGUF/resolve/main/llama-3-8b-chat-sarcasm-merged.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/llama-3-8b-chat-sarcasm-merged.IQ3_M.gguf b/llama-3-8b-chat-sarcasm-merged.IQ3_M.gguf new file mode 100644 index 0000000..9291d38 --- /dev/null +++ b/llama-3-8b-chat-sarcasm-merged.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b436618967d9aa7284cdf8e5a27b63be3374aad241f0550bd25310aabde5271 +size 3784833856 diff --git a/llama-3-8b-chat-sarcasm-merged.IQ3_S.gguf b/llama-3-8b-chat-sarcasm-merged.IQ3_S.gguf new file mode 100644 index 0000000..0b6e70b --- /dev/null +++ b/llama-3-8b-chat-sarcasm-merged.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:258d0b20904b292d5c20faa0bb08a06412d41a5a45d3756d74d842243d5b7985 +size 3682335552 diff --git a/llama-3-8b-chat-sarcasm-merged.IQ3_XS.gguf b/llama-3-8b-chat-sarcasm-merged.IQ3_XS.gguf new file mode 100644 index 0000000..d43c200 --- /dev/null +++ b/llama-3-8b-chat-sarcasm-merged.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eafa34ea52e2861c8db2cdd4c3b634b24fa0f87ec69298cff7e71dbd62171fe5 +size 3518757696 diff --git a/llama-3-8b-chat-sarcasm-merged.IQ4_XS.gguf b/llama-3-8b-chat-sarcasm-merged.IQ4_XS.gguf new file mode 100644 index 0000000..0a8b58f --- /dev/null +++ b/llama-3-8b-chat-sarcasm-merged.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e9faa52bfc271c02da04298c275346ba2e1c88c80f62e3efb61e1d1a827c952 +size 4484374144 diff --git a/llama-3-8b-chat-sarcasm-merged.Q2_K.gguf b/llama-3-8b-chat-sarcasm-merged.Q2_K.gguf new file mode 100644 index 0000000..43328c3 --- /dev/null +++ b/llama-3-8b-chat-sarcasm-merged.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8af3d93a671f206668ec0a4b75a1ddcdcca5860f105ed267a291afe5245109a2 +size 3179141120 diff --git a/llama-3-8b-chat-sarcasm-merged.Q3_K_L.gguf b/llama-3-8b-chat-sarcasm-merged.Q3_K_L.gguf new file mode 100644 index 0000000..dbaa306 --- /dev/null +++ b/llama-3-8b-chat-sarcasm-merged.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e77f19d58c4addffe06148e3ad5e80100f6111116b39c1d0a6967e0223e9900e +size 4321966912 diff --git a/llama-3-8b-chat-sarcasm-merged.Q3_K_M.gguf b/llama-3-8b-chat-sarcasm-merged.Q3_K_M.gguf new file mode 100644 index 0000000..a1af12a --- /dev/null +++ b/llama-3-8b-chat-sarcasm-merged.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51e70d0be5654cfd4d827f3a3e440b06ff4008745ec1d18c6baf522e83df4054 +size 4018928448 diff --git a/llama-3-8b-chat-sarcasm-merged.Q3_K_S.gguf b/llama-3-8b-chat-sarcasm-merged.Q3_K_S.gguf new file mode 100644 index 0000000..1d636af --- /dev/null +++ b/llama-3-8b-chat-sarcasm-merged.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb92e4a1982eff1c15fa3962f6ac4046f619e41a5d61e79cd39f883b3f319c23 +size 3664509760 diff --git a/llama-3-8b-chat-sarcasm-merged.Q4_K_M.gguf b/llama-3-8b-chat-sarcasm-merged.Q4_K_M.gguf new file mode 100644 index 0000000..d496999 --- /dev/null +++ b/llama-3-8b-chat-sarcasm-merged.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bc98d69e8766bdaba3de0a0f8e63ba158baf7c4e840edc6fbd42e1cebb60f5d +size 4920745856 diff --git a/llama-3-8b-chat-sarcasm-merged.Q4_K_S.gguf b/llama-3-8b-chat-sarcasm-merged.Q4_K_S.gguf new file mode 100644 index 0000000..dc5be06 --- /dev/null +++ b/llama-3-8b-chat-sarcasm-merged.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ef3193bbd4bce954f9e1ca5cb180a756bae61b829b973feba5721083668da60 +size 4692680576 diff --git a/llama-3-8b-chat-sarcasm-merged.Q5_K_M.gguf b/llama-3-8b-chat-sarcasm-merged.Q5_K_M.gguf new file mode 100644 index 0000000..87ffb38 --- /dev/null +++ b/llama-3-8b-chat-sarcasm-merged.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57cf68cfaea18f53bc8f9b1b2c151b980fc4c84a4ab0f0b1e7dcd774ed7de923 +size 5733000064 diff --git a/llama-3-8b-chat-sarcasm-merged.Q5_K_S.gguf b/llama-3-8b-chat-sarcasm-merged.Q5_K_S.gguf new file mode 100644 index 0000000..6dd402e --- /dev/null +++ b/llama-3-8b-chat-sarcasm-merged.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:322b53db12963d41001edd1fae368ba6ce49ac5f6014bebfebb805d58eb048bf +size 5599306624 diff --git a/llama-3-8b-chat-sarcasm-merged.Q6_K.gguf b/llama-3-8b-chat-sarcasm-merged.Q6_K.gguf new file mode 100644 index 0000000..b96356f --- /dev/null +++ b/llama-3-8b-chat-sarcasm-merged.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aea78aae7acf9a926e493eb3d6314083e8fa59f4126de7c8f105847e3db63cda +size 6596020160 diff --git a/llama-3-8b-chat-sarcasm-merged.Q8_0.gguf b/llama-3-8b-chat-sarcasm-merged.Q8_0.gguf new file mode 100644 index 0000000..a7fc0d2 --- /dev/null +++ b/llama-3-8b-chat-sarcasm-merged.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5040c1b6448cf717b056b9d7f867ad703fb2baf4eb5717262a2a2591c32ba609 +size 8540788544 diff --git a/llama-3-8b-chat-sarcasm-merged.f16.gguf b/llama-3-8b-chat-sarcasm-merged.f16.gguf new file mode 100644 index 0000000..e86daa7 --- /dev/null +++ b/llama-3-8b-chat-sarcasm-merged.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cac1d3036a9c7b560a26a44f1ec5488291744011a0008e811caac876d86c48b0 +size 16068924224