commit fa407a5fed17884ab2b1f33be71e033803508d21 Author: ModelHub XC Date: Wed Oct 21 16:50:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9757789 --- /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 +Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..f4a2b0d --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: VaidikML0508/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1 +datasets: +- VaidikML0508/SharkTank-Offer-V1 +language: +- en +library_name: transformers +license: llama3.2 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- shark-tank +- SFT +- RL +- GRPO +--- +## About + + + + + + +static quants of https://huggingface.co/VaidikML0508/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1-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/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1-GGUF/resolve/main/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1-GGUF/resolve/main/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1-GGUF/resolve/main/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1-GGUF/resolve/main/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1-GGUF/resolve/main/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1-GGUF/resolve/main/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1-GGUF/resolve/main/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1-GGUF/resolve/main/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1-GGUF/resolve/main/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1-GGUF/resolve/main/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1-GGUF/resolve/main/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1-GGUF/resolve/main/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.f16.gguf) | f16 | 6.5 | 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/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.IQ4_XS.gguf b/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.IQ4_XS.gguf new file mode 100644 index 0000000..102ce4b --- /dev/null +++ b/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:577602b32295bf782220fa4466944f975adf4a4b7da9e3b9ec2365da2547f941 +size 1840907744 diff --git a/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q2_K.gguf b/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q2_K.gguf new file mode 100644 index 0000000..2b0c27a --- /dev/null +++ b/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21cc4951f83498f2b8794c8dd79661ee81e880711cb7d0d8b0be22a45ec3caed +size 1363936736 diff --git a/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q3_K_L.gguf b/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q3_K_L.gguf new file mode 100644 index 0000000..82f3e53 --- /dev/null +++ b/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22d6834514d16384626a146656b75299acd2c32ce708fa5eac8afd22c96be224 +size 1815348704 diff --git a/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q3_K_M.gguf b/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q3_K_M.gguf new file mode 100644 index 0000000..a1867a7 --- /dev/null +++ b/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfa9e89e67935cf646cfa89ecdb202bc1057cbee4e02abaa203bd082df6a2c06 +size 1687160288 diff --git a/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q3_K_S.gguf b/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q3_K_S.gguf new file mode 100644 index 0000000..5f09926 --- /dev/null +++ b/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:952da300302806dd3a229f68686f848e56e0ea061457d6bfc091a3fe56985ab0 +size 1542850016 diff --git a/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q4_K_M.gguf b/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q4_K_M.gguf new file mode 100644 index 0000000..7cb1396 --- /dev/null +++ b/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f398750b74f1909a09cd89d7df7d0bf0f086ec5a509f520d0389d9297855df6 +size 2019378656 diff --git a/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q4_K_S.gguf b/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q4_K_S.gguf new file mode 100644 index 0000000..db9c724 --- /dev/null +++ b/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6e2bb946932265c6d8a74ad16d267a600c134eca3d848042b458301334fb2ba +size 1928201696 diff --git a/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q5_K_M.gguf b/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q5_K_M.gguf new file mode 100644 index 0000000..a579812 --- /dev/null +++ b/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7bac6cd12b33f1baced3ea4ade8547b291af7a16496fd8d965665b3edc93a80 +size 2322154976 diff --git a/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q5_K_S.gguf b/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q5_K_S.gguf new file mode 100644 index 0000000..34fb6ce --- /dev/null +++ b/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:952272893155f0e306fed259f3c88df27a5f09e4de00ce620dae5743e5d5676f +size 2269513184 diff --git a/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q6_K.gguf b/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q6_K.gguf new file mode 100644 index 0000000..933ce8e --- /dev/null +++ b/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16023d27389b0f8481a010892464c44d77e15da287206f8fac543a5ecb4e8266 +size 2643854816 diff --git a/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q8_0.gguf b/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q8_0.gguf new file mode 100644 index 0000000..55bad10 --- /dev/null +++ b/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbc960026da163512da130c164cfb5dac548ee26a7d971f39b8ae8952a727a88 +size 3421900256 diff --git a/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.f16.gguf b/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.f16.gguf new file mode 100644 index 0000000..3460d9c --- /dev/null +++ b/Shark-Tank-Offer-Evaluator-llama3.2-3B-Instruct-GRPO-16bits-V1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e247e24bec1b848046408b905eb2639bde53cff415a4ae725fd308d35a9bbe2 +size 6433689056