commit c0c7fe7b8a79f8f8291c71aacaf869eb0ee5bd41 Author: ModelHub XC Date: Mon Jun 15 20:50:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.3-8B-Instruct-MPOA-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..eea066f --- /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-3.3-8B-Instruct-MPOA.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-MPOA.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-MPOA.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-MPOA.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-MPOA.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-MPOA.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-MPOA.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-MPOA.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-MPOA.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-MPOA.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-MPOA.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Instruct-MPOA.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.3-8B-Instruct-MPOA.IQ4_XS.gguf b/Llama-3.3-8B-Instruct-MPOA.IQ4_XS.gguf new file mode 100644 index 0000000..b669459 --- /dev/null +++ b/Llama-3.3-8B-Instruct-MPOA.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fb07319cf4add5e5352e5dc70e8afd997d976c6d1e84fd28266ad5806615a4f +size 4484368320 diff --git a/Llama-3.3-8B-Instruct-MPOA.Q2_K.gguf b/Llama-3.3-8B-Instruct-MPOA.Q2_K.gguf new file mode 100644 index 0000000..6924c2d --- /dev/null +++ b/Llama-3.3-8B-Instruct-MPOA.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fddc621f7f48e8abb44c587868dcea122f202037c596f8b36ec10471953f3501 +size 3179136960 diff --git a/Llama-3.3-8B-Instruct-MPOA.Q3_K_L.gguf b/Llama-3.3-8B-Instruct-MPOA.Q3_K_L.gguf new file mode 100644 index 0000000..fc4bb6e --- /dev/null +++ b/Llama-3.3-8B-Instruct-MPOA.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35a8916897331252b6df6e6e358a1c38e5e5a7962cc1029426949bfb67056f99 +size 4321961920 diff --git a/Llama-3.3-8B-Instruct-MPOA.Q3_K_M.gguf b/Llama-3.3-8B-Instruct-MPOA.Q3_K_M.gguf new file mode 100644 index 0000000..bf7c67d --- /dev/null +++ b/Llama-3.3-8B-Instruct-MPOA.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:449ee09adf4eacd2ca0c1de83ab9ad358ec282fe5d6ab5e360cdfa7477b8b39f +size 4018923456 diff --git a/Llama-3.3-8B-Instruct-MPOA.Q3_K_S.gguf b/Llama-3.3-8B-Instruct-MPOA.Q3_K_S.gguf new file mode 100644 index 0000000..5ffb128 --- /dev/null +++ b/Llama-3.3-8B-Instruct-MPOA.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26d963ae4bdaba9b85a1b69fb7ff38c1149e644e36e85d09ef920e87b6901d04 +size 3664504768 diff --git a/Llama-3.3-8B-Instruct-MPOA.Q4_K_M.gguf b/Llama-3.3-8B-Instruct-MPOA.Q4_K_M.gguf new file mode 100644 index 0000000..661eb92 --- /dev/null +++ b/Llama-3.3-8B-Instruct-MPOA.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee542c656416a9d3f588a5b6973f0b9aabffcec138f148e86f22f21a83c80288 +size 4920739776 diff --git a/Llama-3.3-8B-Instruct-MPOA.Q4_K_S.gguf b/Llama-3.3-8B-Instruct-MPOA.Q4_K_S.gguf new file mode 100644 index 0000000..b53abc6 --- /dev/null +++ b/Llama-3.3-8B-Instruct-MPOA.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c02cb8a2c5c06e283bf8f757420bd1f8f8c840ffafc501ef377a23706212d83 +size 4692674496 diff --git a/Llama-3.3-8B-Instruct-MPOA.Q5_K_M.gguf b/Llama-3.3-8B-Instruct-MPOA.Q5_K_M.gguf new file mode 100644 index 0000000..03ae575 --- /dev/null +++ b/Llama-3.3-8B-Instruct-MPOA.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45004d284ca7a0e1a5c809db4a57aa56553d6ea5af4da7aa15380195c10ae59e +size 5732992960 diff --git a/Llama-3.3-8B-Instruct-MPOA.Q5_K_S.gguf b/Llama-3.3-8B-Instruct-MPOA.Q5_K_S.gguf new file mode 100644 index 0000000..c5127d9 --- /dev/null +++ b/Llama-3.3-8B-Instruct-MPOA.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c5b825a66c1ca1413169f3cd155964478c80ebdd959160ec97417f7823aab40 +size 5599299520 diff --git a/Llama-3.3-8B-Instruct-MPOA.Q6_K.gguf b/Llama-3.3-8B-Instruct-MPOA.Q6_K.gguf new file mode 100644 index 0000000..0c032c4 --- /dev/null +++ b/Llama-3.3-8B-Instruct-MPOA.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6d8e594c9dfa4987a7dd18bcb7fc9808cf0613bd9fcc5281449a597281776d6 +size 6596011968 diff --git a/Llama-3.3-8B-Instruct-MPOA.Q8_0.gguf b/Llama-3.3-8B-Instruct-MPOA.Q8_0.gguf new file mode 100644 index 0000000..a45f5e6 --- /dev/null +++ b/Llama-3.3-8B-Instruct-MPOA.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db6fa7b9267c25ea4ab79036ff54582e22d53c5634f843723f75089742e4b667 +size 8540776384 diff --git a/Llama-3.3-8B-Instruct-MPOA.f16.gguf b/Llama-3.3-8B-Instruct-MPOA.f16.gguf new file mode 100644 index 0000000..4ccf0f8 --- /dev/null +++ b/Llama-3.3-8B-Instruct-MPOA.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7328d61d621589f68c404227c9ab2e37f19c48dbe83a5c75f440cce2e470cfc1 +size 16068896704 diff --git a/README.md b/README.md new file mode 100644 index 0000000..af30785 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: YanLabs/Llama-3.3-8B-Instruct-MPOA +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/YanLabs/Llama-3.3-8B-Instruct-MPOA + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.3-8B-Instruct-MPOA-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-MPOA-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-3.3-8B-Instruct-MPOA-GGUF/resolve/main/Llama-3.3-8B-Instruct-MPOA.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-MPOA-GGUF/resolve/main/Llama-3.3-8B-Instruct-MPOA.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-MPOA-GGUF/resolve/main/Llama-3.3-8B-Instruct-MPOA.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-MPOA-GGUF/resolve/main/Llama-3.3-8B-Instruct-MPOA.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-MPOA-GGUF/resolve/main/Llama-3.3-8B-Instruct-MPOA.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-MPOA-GGUF/resolve/main/Llama-3.3-8B-Instruct-MPOA.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-MPOA-GGUF/resolve/main/Llama-3.3-8B-Instruct-MPOA.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-MPOA-GGUF/resolve/main/Llama-3.3-8B-Instruct-MPOA.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-MPOA-GGUF/resolve/main/Llama-3.3-8B-Instruct-MPOA.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-MPOA-GGUF/resolve/main/Llama-3.3-8B-Instruct-MPOA.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-MPOA-GGUF/resolve/main/Llama-3.3-8B-Instruct-MPOA.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Instruct-MPOA-GGUF/resolve/main/Llama-3.3-8B-Instruct-MPOA.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. + +