commit cf78e82cf67273513b780b5c8e09316fcf3b62c8 Author: ModelHub XC Date: Tue Sep 8 17:00:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Awanllm-Llama-3-8B-Dolfin-v0.5-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..796672f --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +Awanllm-Llama-3-8B-Dolfin-v0.5.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Awanllm-Llama-3-8B-Dolfin-v0.5.f16.gguf filter=lfs diff=lfs merge=lfs -text +Awanllm-Llama-3-8B-Dolfin-v0.5.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Awanllm-Llama-3-8B-Dolfin-v0.5.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Awanllm-Llama-3-8B-Dolfin-v0.5.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Awanllm-Llama-3-8B-Dolfin-v0.5.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Awanllm-Llama-3-8B-Dolfin-v0.5.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Awanllm-Llama-3-8B-Dolfin-v0.5.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Awanllm-Llama-3-8B-Dolfin-v0.5.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Awanllm-Llama-3-8B-Dolfin-v0.5.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Awanllm-Llama-3-8B-Dolfin-v0.5.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Awanllm-Llama-3-8B-Dolfin-v0.5.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Awanllm-Llama-3-8B-Dolfin-v0.5.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Awanllm-Llama-3-8B-Dolfin-v0.5.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Awanllm-Llama-3-8B-Dolfin-v0.5.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Awanllm-Llama-3-8B-Dolfin-v0.5.IQ3_M.gguf b/Awanllm-Llama-3-8B-Dolfin-v0.5.IQ3_M.gguf new file mode 100644 index 0000000..09ff12a --- /dev/null +++ b/Awanllm-Llama-3-8B-Dolfin-v0.5.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa70719cf365936835920bae3234701159131a3a1c11b5d9ddabdebaae7185d5 +size 3784823552 diff --git a/Awanllm-Llama-3-8B-Dolfin-v0.5.IQ3_S.gguf b/Awanllm-Llama-3-8B-Dolfin-v0.5.IQ3_S.gguf new file mode 100644 index 0000000..e84a283 --- /dev/null +++ b/Awanllm-Llama-3-8B-Dolfin-v0.5.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1df89612670d409deacbff32a8d2e1dd07376af6c7ac959f6305d364f23d1a92 +size 3682325248 diff --git a/Awanllm-Llama-3-8B-Dolfin-v0.5.IQ3_XS.gguf b/Awanllm-Llama-3-8B-Dolfin-v0.5.IQ3_XS.gguf new file mode 100644 index 0000000..3c4b73b --- /dev/null +++ b/Awanllm-Llama-3-8B-Dolfin-v0.5.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b773a77ff845f3a26afc8e96d79ed47b4860b9f4d06f9704f166789ce4fa9aa +size 3518747392 diff --git a/Awanllm-Llama-3-8B-Dolfin-v0.5.IQ4_XS.gguf b/Awanllm-Llama-3-8B-Dolfin-v0.5.IQ4_XS.gguf new file mode 100644 index 0000000..e3dc5a8 --- /dev/null +++ b/Awanllm-Llama-3-8B-Dolfin-v0.5.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d02739a6e5bd47105f8266719c76f7eeaba2530dde14e6ff3e2257e8046fc92 +size 4484363008 diff --git a/Awanllm-Llama-3-8B-Dolfin-v0.5.Q2_K.gguf b/Awanllm-Llama-3-8B-Dolfin-v0.5.Q2_K.gguf new file mode 100644 index 0000000..b0ff60d --- /dev/null +++ b/Awanllm-Llama-3-8B-Dolfin-v0.5.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bd893da956525c44a6ba0653699d2223c9e15983a14d10ac0c51572cec43d8f +size 3179131648 diff --git a/Awanllm-Llama-3-8B-Dolfin-v0.5.Q3_K_L.gguf b/Awanllm-Llama-3-8B-Dolfin-v0.5.Q3_K_L.gguf new file mode 100644 index 0000000..8964bad --- /dev/null +++ b/Awanllm-Llama-3-8B-Dolfin-v0.5.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1aeb22ca2c7a739be7b9fbb2acf25e1b3445750e3136128530fa6dcf949ee582 +size 4321956608 diff --git a/Awanllm-Llama-3-8B-Dolfin-v0.5.Q3_K_M.gguf b/Awanllm-Llama-3-8B-Dolfin-v0.5.Q3_K_M.gguf new file mode 100644 index 0000000..fd89e03 --- /dev/null +++ b/Awanllm-Llama-3-8B-Dolfin-v0.5.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3441fd65d62e30a98c0d186bd889dbcd3eeaa80f428466f8bac2c39a622618d9 +size 4018918144 diff --git a/Awanllm-Llama-3-8B-Dolfin-v0.5.Q3_K_S.gguf b/Awanllm-Llama-3-8B-Dolfin-v0.5.Q3_K_S.gguf new file mode 100644 index 0000000..33dd436 --- /dev/null +++ b/Awanllm-Llama-3-8B-Dolfin-v0.5.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:998f1b3173144d568b0d8cfc2a1eb72fbd225832b3ccacc4656255d4e5424649 +size 3664499456 diff --git a/Awanllm-Llama-3-8B-Dolfin-v0.5.Q4_K_M.gguf b/Awanllm-Llama-3-8B-Dolfin-v0.5.Q4_K_M.gguf new file mode 100644 index 0000000..d526829 --- /dev/null +++ b/Awanllm-Llama-3-8B-Dolfin-v0.5.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11c646192e7bab605a3c6f56afee78bc466a697cb6b47ec1dee6da26a26089b5 +size 4920734464 diff --git a/Awanllm-Llama-3-8B-Dolfin-v0.5.Q4_K_S.gguf b/Awanllm-Llama-3-8B-Dolfin-v0.5.Q4_K_S.gguf new file mode 100644 index 0000000..e6cd649 --- /dev/null +++ b/Awanllm-Llama-3-8B-Dolfin-v0.5.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3244cc3d37e96728ffabcd0e90dce0e7eea96a7b0b635bf49b12b1ec27173a6 +size 4692669184 diff --git a/Awanllm-Llama-3-8B-Dolfin-v0.5.Q5_K_M.gguf b/Awanllm-Llama-3-8B-Dolfin-v0.5.Q5_K_M.gguf new file mode 100644 index 0000000..c55b9f5 --- /dev/null +++ b/Awanllm-Llama-3-8B-Dolfin-v0.5.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23f817ff46de21e95c9997f16a7896565f80f1b227d18696da415577d6e28e9d +size 5732987648 diff --git a/Awanllm-Llama-3-8B-Dolfin-v0.5.Q5_K_S.gguf b/Awanllm-Llama-3-8B-Dolfin-v0.5.Q5_K_S.gguf new file mode 100644 index 0000000..c063a1c --- /dev/null +++ b/Awanllm-Llama-3-8B-Dolfin-v0.5.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:660c8eb393b6b189f19e94bb0eb1501597d9c9de7230c21cd22a3fbe8147f448 +size 5599294208 diff --git a/Awanllm-Llama-3-8B-Dolfin-v0.5.Q6_K.gguf b/Awanllm-Llama-3-8B-Dolfin-v0.5.Q6_K.gguf new file mode 100644 index 0000000..55d33de --- /dev/null +++ b/Awanllm-Llama-3-8B-Dolfin-v0.5.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f41c525b60554f80b9096521d3002e122ec505505282419ab8c566f21af3514 +size 6596006656 diff --git a/Awanllm-Llama-3-8B-Dolfin-v0.5.Q8_0.gguf b/Awanllm-Llama-3-8B-Dolfin-v0.5.Q8_0.gguf new file mode 100644 index 0000000..e6e73e4 --- /dev/null +++ b/Awanllm-Llama-3-8B-Dolfin-v0.5.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a27cfff78532d810cecf401f802c2f5a669186f9299824f3d2b6bd2882dd13f +size 8540771072 diff --git a/Awanllm-Llama-3-8B-Dolfin-v0.5.f16.gguf b/Awanllm-Llama-3-8B-Dolfin-v0.5.f16.gguf new file mode 100644 index 0000000..5f8a2ad --- /dev/null +++ b/Awanllm-Llama-3-8B-Dolfin-v0.5.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a2e04010088294eb48d24ff140f94abf943ddf9c3c14e480cb2cbd95ae4254c +size 16068891392 diff --git a/README.md b/README.md new file mode 100644 index 0000000..04f058f --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: OwenArli/ArliAI-Llama-3-8B-Dolfin-v0.5 +language: +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +--- +## About + + + + + +static quants of https://huggingface.co/OwenArli/ArliAI-Llama-3-8B-Dolfin-v0.5 + + +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/Awanllm-Llama-3-8B-Dolfin-v0.5-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v0.5.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v0.5-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v0.5.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v0.5-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v0.5.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v0.5-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v0.5.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v0.5-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v0.5.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v0.5-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v0.5.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v0.5-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v0.5.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v0.5-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v0.5.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v0.5-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v0.5.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v0.5-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v0.5.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v0.5-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v0.5.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v0.5-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v0.5.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v0.5-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v0.5.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v0.5-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v0.5.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v0.5-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v0.5.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. + +