commit 5908d9f7f42d884f85ab7b0562ade89186691d44 Author: ModelHub XC Date: Mon Jul 13 20:21:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-2-7b-sarcasm-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5a0b2c9 --- /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-2-7b-sarcasm.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sarcasm.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sarcasm.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sarcasm.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sarcasm.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sarcasm.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sarcasm.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sarcasm.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sarcasm.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sarcasm.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sarcasm.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-sarcasm.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-2-7b-sarcasm.IQ4_XS.gguf b/Llama-2-7b-sarcasm.IQ4_XS.gguf new file mode 100644 index 0000000..8bbc918 --- /dev/null +++ b/Llama-2-7b-sarcasm.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58994fa7473622a5532ee6bd34976b7bc1c0d45b7c27e7619e0896980c0f8167 +size 3647518208 diff --git a/Llama-2-7b-sarcasm.Q2_K.gguf b/Llama-2-7b-sarcasm.Q2_K.gguf new file mode 100644 index 0000000..2388a49 --- /dev/null +++ b/Llama-2-7b-sarcasm.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3c66849c42e88d8149ec4557307d1e5a479dc0ed4fa9a70359b3ea1d1fe8c2d +size 2532865536 diff --git a/Llama-2-7b-sarcasm.Q3_K_L.gguf b/Llama-2-7b-sarcasm.Q3_K_L.gguf new file mode 100644 index 0000000..73f7762 --- /dev/null +++ b/Llama-2-7b-sarcasm.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90905ff29b2e1044cff5d66eb46e2730ad704bfa0a9c325dd46829af3ac53688 +size 3597112832 diff --git a/Llama-2-7b-sarcasm.Q3_K_M.gguf b/Llama-2-7b-sarcasm.Q3_K_M.gguf new file mode 100644 index 0000000..81c023f --- /dev/null +++ b/Llama-2-7b-sarcasm.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9b6fb78002903d282f2613cf0d7dd420f1e91bb800780f4ab84da4def0ceb6f +size 3298006528 diff --git a/Llama-2-7b-sarcasm.Q3_K_S.gguf b/Llama-2-7b-sarcasm.Q3_K_S.gguf new file mode 100644 index 0000000..0e9524a --- /dev/null +++ b/Llama-2-7b-sarcasm.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:966027396b49e132e5d32270e58c8265fb0614bbcd9d34995e206412d7dbca58 +size 2948306432 diff --git a/Llama-2-7b-sarcasm.Q4_K_M.gguf b/Llama-2-7b-sarcasm.Q4_K_M.gguf new file mode 100644 index 0000000..c724927 --- /dev/null +++ b/Llama-2-7b-sarcasm.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:794429d8db27ea8af0b2f3d440cc1a7deabc6dae828afd8f3d583d6a6bbfbaaf +size 4081006080 diff --git a/Llama-2-7b-sarcasm.Q4_K_S.gguf b/Llama-2-7b-sarcasm.Q4_K_S.gguf new file mode 100644 index 0000000..504b54e --- /dev/null +++ b/Llama-2-7b-sarcasm.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d39a71a1158c20bb59d7825cb0a0a99ba7cafaf47bdddb1d1a85d8e1fe62b73 +size 3856741888 diff --git a/Llama-2-7b-sarcasm.Q5_K_M.gguf b/Llama-2-7b-sarcasm.Q5_K_M.gguf new file mode 100644 index 0000000..964d64d --- /dev/null +++ b/Llama-2-7b-sarcasm.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:571dfe06b83dc24d5fd58692058906accc17b86050dfa8b35faebe64b0bbf65b +size 4783158784 diff --git a/Llama-2-7b-sarcasm.Q5_K_S.gguf b/Llama-2-7b-sarcasm.Q5_K_S.gguf new file mode 100644 index 0000000..f0ef700 --- /dev/null +++ b/Llama-2-7b-sarcasm.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:797657f348a0ba50e374fc3f0365893ae10d773ff4e4327e0ec838f5e8da4c59 +size 4651693568 diff --git a/Llama-2-7b-sarcasm.Q6_K.gguf b/Llama-2-7b-sarcasm.Q6_K.gguf new file mode 100644 index 0000000..d76aced --- /dev/null +++ b/Llama-2-7b-sarcasm.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7dc1b7019969991de9ebe42a44f23d75250f124cfb4b2b2ab7015a7c17ef149 +size 5529196032 diff --git a/Llama-2-7b-sarcasm.Q8_0.gguf b/Llama-2-7b-sarcasm.Q8_0.gguf new file mode 100644 index 0000000..451598d --- /dev/null +++ b/Llama-2-7b-sarcasm.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ed3c658854d0dfe0c34099c6582ad26c2fcd07b3965797d7f05732d44039440 +size 7161091584 diff --git a/Llama-2-7b-sarcasm.f16.gguf b/Llama-2-7b-sarcasm.f16.gguf new file mode 100644 index 0000000..8df9e43 --- /dev/null +++ b/Llama-2-7b-sarcasm.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5444ad418aad5fde906660de9b41362ca5be4f88988cc06b70b26d100d8e0d8 +size 13478106624 diff --git a/README.md b/README.md new file mode 100644 index 0000000..302d236 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: bharatiyabytes/Llama-2-7b-sarcasm +datasets: +- stanfordnlp/imdb +- bharatiyabytes/sentimentWithSarcasm +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- sarcasm +- gen-ai +- llama-2 +- llms +--- +## About + + + + + + +static quants of https://huggingface.co/bharatiyabytes/Llama-2-7b-sarcasm + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-2-7b-sarcasm-GGUF).*** + +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-2-7b-sarcasm-GGUF/resolve/main/Llama-2-7b-sarcasm.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sarcasm-GGUF/resolve/main/Llama-2-7b-sarcasm.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sarcasm-GGUF/resolve/main/Llama-2-7b-sarcasm.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sarcasm-GGUF/resolve/main/Llama-2-7b-sarcasm.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sarcasm-GGUF/resolve/main/Llama-2-7b-sarcasm.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sarcasm-GGUF/resolve/main/Llama-2-7b-sarcasm.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sarcasm-GGUF/resolve/main/Llama-2-7b-sarcasm.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sarcasm-GGUF/resolve/main/Llama-2-7b-sarcasm.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sarcasm-GGUF/resolve/main/Llama-2-7b-sarcasm.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sarcasm-GGUF/resolve/main/Llama-2-7b-sarcasm.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sarcasm-GGUF/resolve/main/Llama-2-7b-sarcasm.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-sarcasm-GGUF/resolve/main/Llama-2-7b-sarcasm.f16.gguf) | f16 | 13.6 | 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. + +