commit a30137e8bb8eb831db733cebe690dd2d4f9a521d Author: ModelHub XC Date: Sat Oct 24 01:04:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-2-7b-chat-norwegian-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..26b9a9f --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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-chat-norwegian.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-norwegian.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-norwegian.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-norwegian.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-norwegian.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-norwegian.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-norwegian.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-norwegian.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-norwegian.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-norwegian.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-norwegian.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-norwegian.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-norwegian.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-2-7b-chat-norwegian.IQ4_XS.gguf b/Llama-2-7b-chat-norwegian.IQ4_XS.gguf new file mode 100644 index 0000000..28d31ee --- /dev/null +++ b/Llama-2-7b-chat-norwegian.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35b062c4cf812e86439e81381dc3eaf50e65df5abef4b0beff634185fcc88ee1 +size 3647517856 diff --git a/Llama-2-7b-chat-norwegian.Q2_K.gguf b/Llama-2-7b-chat-norwegian.Q2_K.gguf new file mode 100644 index 0000000..c88e51a --- /dev/null +++ b/Llama-2-7b-chat-norwegian.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73e4cc0611d4bca1b46b6da6f038450244d10847d6c0993b2ee4be2ac9d1bd48 +size 2532865184 diff --git a/Llama-2-7b-chat-norwegian.Q3_K_L.gguf b/Llama-2-7b-chat-norwegian.Q3_K_L.gguf new file mode 100644 index 0000000..8f10607 --- /dev/null +++ b/Llama-2-7b-chat-norwegian.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f3cc326eeea68fbcbf688ec915a37370d7b0a09f8ffc74edf0341da48f1f8e0 +size 3597112480 diff --git a/Llama-2-7b-chat-norwegian.Q3_K_M.gguf b/Llama-2-7b-chat-norwegian.Q3_K_M.gguf new file mode 100644 index 0000000..17c9260 --- /dev/null +++ b/Llama-2-7b-chat-norwegian.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db191d21ccce0ff46f598e3c6a87b9ad282694e05907ed725235bf8093e747fa +size 3298006176 diff --git a/Llama-2-7b-chat-norwegian.Q3_K_S.gguf b/Llama-2-7b-chat-norwegian.Q3_K_S.gguf new file mode 100644 index 0000000..aee8e29 --- /dev/null +++ b/Llama-2-7b-chat-norwegian.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31c213cea2d97015115d4afe2d8a61719d4d8380f9e9e22adbd078c7b0864238 +size 2948306080 diff --git a/Llama-2-7b-chat-norwegian.Q4_0_4_4.gguf b/Llama-2-7b-chat-norwegian.Q4_0_4_4.gguf new file mode 100644 index 0000000..f0b5716 --- /dev/null +++ b/Llama-2-7b-chat-norwegian.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cde47c13cc086893abb989773e14a2d9c728c9da43cdf66cd124d1d33280db9d +size 3825808544 diff --git a/Llama-2-7b-chat-norwegian.Q4_K_M.gguf b/Llama-2-7b-chat-norwegian.Q4_K_M.gguf new file mode 100644 index 0000000..2a247c7 --- /dev/null +++ b/Llama-2-7b-chat-norwegian.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62c8b1ffb15326691cc53bb2ae1388e046ed8c077ae66eaad47f2784701b3570 +size 4081005728 diff --git a/Llama-2-7b-chat-norwegian.Q4_K_S.gguf b/Llama-2-7b-chat-norwegian.Q4_K_S.gguf new file mode 100644 index 0000000..717585c --- /dev/null +++ b/Llama-2-7b-chat-norwegian.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1421a4f880d2306e1f24918dd5ad17243451b60eac1e0cf43d71e810537ac395 +size 3856741536 diff --git a/Llama-2-7b-chat-norwegian.Q5_K_M.gguf b/Llama-2-7b-chat-norwegian.Q5_K_M.gguf new file mode 100644 index 0000000..8266efe --- /dev/null +++ b/Llama-2-7b-chat-norwegian.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e18f4661e722fd5fa775476485f97ff97b73caea9963cbe777d6edf98504da7 +size 4783158432 diff --git a/Llama-2-7b-chat-norwegian.Q5_K_S.gguf b/Llama-2-7b-chat-norwegian.Q5_K_S.gguf new file mode 100644 index 0000000..94d744e --- /dev/null +++ b/Llama-2-7b-chat-norwegian.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:322286373dc7d4bf7097bdb977f2c65b54453ea455d8da60b56930bffbd35256 +size 4651693216 diff --git a/Llama-2-7b-chat-norwegian.Q6_K.gguf b/Llama-2-7b-chat-norwegian.Q6_K.gguf new file mode 100644 index 0000000..78eb718 --- /dev/null +++ b/Llama-2-7b-chat-norwegian.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ea8d04458278eceb15f1f705f229ea43af54a2ecd447ea486b7bdc8cda6f42f +size 5529195680 diff --git a/Llama-2-7b-chat-norwegian.Q8_0.gguf b/Llama-2-7b-chat-norwegian.Q8_0.gguf new file mode 100644 index 0000000..1a36b8c --- /dev/null +++ b/Llama-2-7b-chat-norwegian.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33788117916e28ddc6be8dac6769f31aeedcd08ce19841e07a1be76cf0c90e90 +size 7161091232 diff --git a/Llama-2-7b-chat-norwegian.f16.gguf b/Llama-2-7b-chat-norwegian.f16.gguf new file mode 100644 index 0000000..85c5bc4 --- /dev/null +++ b/Llama-2-7b-chat-norwegian.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e051c2ce2ed6f6b0f9cbbb2381b5ddf1c419ea8753f5b1bc4881f09a06d4f9b7 +size 13478106272 diff --git a/README.md b/README.md new file mode 100644 index 0000000..23b18d2 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: RuterNorway/Llama-2-7b-chat-norwegian +datasets: +- NbAiLab/norwegian-alpaca +- RuterNorway/OpenOrcaNo-15k +language: +- en +- no +library_name: transformers +license: llama2 +quantized_by: mradermacher +tags: +- pytorch +- llama +- llama-2 +- norwegian +- norsk +--- +## About + + + + + + +static quants of https://huggingface.co/RuterNorway/Llama-2-7b-chat-norwegian + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-2-7b-chat-norwegian-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-2-7b-chat-norwegian-GGUF/resolve/main/Llama-2-7b-chat-norwegian.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-norwegian-GGUF/resolve/main/Llama-2-7b-chat-norwegian.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-norwegian-GGUF/resolve/main/Llama-2-7b-chat-norwegian.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-norwegian-GGUF/resolve/main/Llama-2-7b-chat-norwegian.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-norwegian-GGUF/resolve/main/Llama-2-7b-chat-norwegian.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-norwegian-GGUF/resolve/main/Llama-2-7b-chat-norwegian.Q4_0_4_4.gguf) | Q4_0_4_4 | 3.9 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-norwegian-GGUF/resolve/main/Llama-2-7b-chat-norwegian.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-norwegian-GGUF/resolve/main/Llama-2-7b-chat-norwegian.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-norwegian-GGUF/resolve/main/Llama-2-7b-chat-norwegian.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-norwegian-GGUF/resolve/main/Llama-2-7b-chat-norwegian.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-norwegian-GGUF/resolve/main/Llama-2-7b-chat-norwegian.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-norwegian-GGUF/resolve/main/Llama-2-7b-chat-norwegian.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-norwegian-GGUF/resolve/main/Llama-2-7b-chat-norwegian.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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +