commit fba2ab023bbac0fbd265dc96229dbebd4579cae2 Author: ModelHub XC Date: Wed Jun 3 13:44:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-Poro-2-8B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f6f4275 --- /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-Poro-2-8B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Poro-2-8B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Poro-2-8B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Poro-2-8B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Poro-2-8B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Poro-2-8B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Poro-2-8B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Poro-2-8B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Poro-2-8B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Poro-2-8B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Poro-2-8B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Poro-2-8B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-Poro-2-8B-Instruct.IQ4_XS.gguf b/Llama-Poro-2-8B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..2a3aabd --- /dev/null +++ b/Llama-Poro-2-8B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc0b2bc3540e5a95770fe1999e2a009482e95c8baaf18e5b0c3dfc41f7dda3e6 +size 4484368096 diff --git a/Llama-Poro-2-8B-Instruct.Q2_K.gguf b/Llama-Poro-2-8B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..30a3fa3 --- /dev/null +++ b/Llama-Poro-2-8B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e35c237d68f6518fcfc45c2301bd04b8df499fa2ed2f4d0cc3c3621b75e734cd +size 3179136736 diff --git a/Llama-Poro-2-8B-Instruct.Q3_K_L.gguf b/Llama-Poro-2-8B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..c46294b --- /dev/null +++ b/Llama-Poro-2-8B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:934bd063f363efb1bf2c6354b6f84d97f2fa4fcb715a0370d469143722635cad +size 4321961696 diff --git a/Llama-Poro-2-8B-Instruct.Q3_K_M.gguf b/Llama-Poro-2-8B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..b1e38a4 --- /dev/null +++ b/Llama-Poro-2-8B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2d41c316ce34e1d5cf2041d1a2723fa5f6315903ab68740787d39f40f5c695d +size 4018923232 diff --git a/Llama-Poro-2-8B-Instruct.Q3_K_S.gguf b/Llama-Poro-2-8B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..71bcdff --- /dev/null +++ b/Llama-Poro-2-8B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab3ed47949e1aa21384bdc145017b05942b7e6d69d6ebaf78806d2bd96e0a2e7 +size 3664504544 diff --git a/Llama-Poro-2-8B-Instruct.Q4_K_M.gguf b/Llama-Poro-2-8B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..ab74493 --- /dev/null +++ b/Llama-Poro-2-8B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4ebc636c25496077010a0033f3cbd8b704396b1732b0c0ae8d6a62797ae8a6b +size 4920739552 diff --git a/Llama-Poro-2-8B-Instruct.Q4_K_S.gguf b/Llama-Poro-2-8B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..fe9f8c3 --- /dev/null +++ b/Llama-Poro-2-8B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a94df006bb23c050eb7c60d50cc254db399bb31cb2df6c886ccb697ba21afdd4 +size 4692674272 diff --git a/Llama-Poro-2-8B-Instruct.Q5_K_M.gguf b/Llama-Poro-2-8B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..54c92e0 --- /dev/null +++ b/Llama-Poro-2-8B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01d852a9fb7d00c9834d86cfa5d4a16afca94eb2c63069a9ed7823a51ade976f +size 5732992736 diff --git a/Llama-Poro-2-8B-Instruct.Q5_K_S.gguf b/Llama-Poro-2-8B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..d556e73 --- /dev/null +++ b/Llama-Poro-2-8B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0259ac65851d19bcba678b4d58005e2e84914f19479c0980da971ec791fd72a1 +size 5599299296 diff --git a/Llama-Poro-2-8B-Instruct.Q6_K.gguf b/Llama-Poro-2-8B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..058f2b3 --- /dev/null +++ b/Llama-Poro-2-8B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53ac28b2e5491f3e698b4dd07a385b7ce0629f580b1611bca1f5d1a9c00bdc90 +size 6596011744 diff --git a/Llama-Poro-2-8B-Instruct.Q8_0.gguf b/Llama-Poro-2-8B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..73f0752 --- /dev/null +++ b/Llama-Poro-2-8B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f98af1c71cba96a1adf47046131522ec8f7c104b77af05e92dfc3eba958eb7a4 +size 8540776160 diff --git a/Llama-Poro-2-8B-Instruct.f16.gguf b/Llama-Poro-2-8B-Instruct.f16.gguf new file mode 100644 index 0000000..fa3c018 --- /dev/null +++ b/Llama-Poro-2-8B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea29f5be8f61ee6ef89d7444cbed765cf04fea433acaa19a3e66502c3e4983f2 +size 16068896480 diff --git a/README.md b/README.md new file mode 100644 index 0000000..cb07b8c --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: LumiOpen/Llama-Poro-2-8B-Instruct +datasets: +- LumiOpen/poro2-instruction-collection +- nvidia/HelpSteer3 +language: +- fi +- en +library_name: transformers +license: llama3.3 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/LumiOpen/Llama-Poro-2-8B-Instruct + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-Poro-2-8B-Instruct-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-Poro-2-8B-Instruct-GGUF/resolve/main/Llama-Poro-2-8B-Instruct.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Poro-2-8B-Instruct-GGUF/resolve/main/Llama-Poro-2-8B-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Poro-2-8B-Instruct-GGUF/resolve/main/Llama-Poro-2-8B-Instruct.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Poro-2-8B-Instruct-GGUF/resolve/main/Llama-Poro-2-8B-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Poro-2-8B-Instruct-GGUF/resolve/main/Llama-Poro-2-8B-Instruct.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Poro-2-8B-Instruct-GGUF/resolve/main/Llama-Poro-2-8B-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-Poro-2-8B-Instruct-GGUF/resolve/main/Llama-Poro-2-8B-Instruct.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-Poro-2-8B-Instruct-GGUF/resolve/main/Llama-Poro-2-8B-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Poro-2-8B-Instruct-GGUF/resolve/main/Llama-Poro-2-8B-Instruct.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Poro-2-8B-Instruct-GGUF/resolve/main/Llama-Poro-2-8B-Instruct.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Poro-2-8B-Instruct-GGUF/resolve/main/Llama-Poro-2-8B-Instruct.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Poro-2-8B-Instruct-GGUF/resolve/main/Llama-Poro-2-8B-Instruct.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. + +