commit 7f951ae448499571032b2f79e1d2e1871d7ca251 Author: ModelHub XC Date: Sun Jun 14 09:20:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama_3.2_1b_Odyssea_V1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7cb1615 --- /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_3.2_1b_Odyssea_V1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_1b_Odyssea_V1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_1b_Odyssea_V1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_1b_Odyssea_V1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_1b_Odyssea_V1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_1b_Odyssea_V1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_1b_Odyssea_V1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_1b_Odyssea_V1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_1b_Odyssea_V1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_1b_Odyssea_V1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_1b_Odyssea_V1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.2_1b_Odyssea_V1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama_3.2_1b_Odyssea_V1.IQ4_XS.gguf b/Llama_3.2_1b_Odyssea_V1.IQ4_XS.gguf new file mode 100644 index 0000000..c9f6a0f --- /dev/null +++ b/Llama_3.2_1b_Odyssea_V1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cde933b523ef8890763fd7a02b359ea26a52b52fa47ab96e19955023b269b8d +size 887927808 diff --git a/Llama_3.2_1b_Odyssea_V1.Q2_K.gguf b/Llama_3.2_1b_Odyssea_V1.Q2_K.gguf new file mode 100644 index 0000000..a195d92 --- /dev/null +++ b/Llama_3.2_1b_Odyssea_V1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9dadf8c9d25a48af712e4695cb9241e667c12cad4bbee74a690f1566cb58343 +size 667063296 diff --git a/Llama_3.2_1b_Odyssea_V1.Q3_K_L.gguf b/Llama_3.2_1b_Odyssea_V1.Q3_K_L.gguf new file mode 100644 index 0000000..d256acc --- /dev/null +++ b/Llama_3.2_1b_Odyssea_V1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b9a7ec6b4674117b3ee38e7ddfd6dd41ad22352ebebb56287e891d798198bde +size 845390848 diff --git a/Llama_3.2_1b_Odyssea_V1.Q3_K_M.gguf b/Llama_3.2_1b_Odyssea_V1.Q3_K_M.gguf new file mode 100644 index 0000000..49a4eb9 --- /dev/null +++ b/Llama_3.2_1b_Odyssea_V1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0167fe6fe4cd019bbceb91e177a9165440318dd1cf79828bbbc1b96cd8596e5 +size 803709952 diff --git a/Llama_3.2_1b_Odyssea_V1.Q3_K_S.gguf b/Llama_3.2_1b_Odyssea_V1.Q3_K_S.gguf new file mode 100644 index 0000000..8c4c7b7 --- /dev/null +++ b/Llama_3.2_1b_Odyssea_V1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4820e46b49dafabbb7584ffbbd692b840d300e40799abcd7606ffef73e74da1c +size 754557952 diff --git a/Llama_3.2_1b_Odyssea_V1.Q4_K_M.gguf b/Llama_3.2_1b_Odyssea_V1.Q4_K_M.gguf new file mode 100644 index 0000000..b4ed3fe --- /dev/null +++ b/Llama_3.2_1b_Odyssea_V1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63ff780b0edfd565e449780af9e24e9665e49c163b73c64e39a295f917b314b5 +size 955446272 diff --git a/Llama_3.2_1b_Odyssea_V1.Q4_K_S.gguf b/Llama_3.2_1b_Odyssea_V1.Q4_K_S.gguf new file mode 100644 index 0000000..331f889 --- /dev/null +++ b/Llama_3.2_1b_Odyssea_V1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1f7e3a6af776ba57504835cf710e314d8d800406b7baf2529b71574edc95a98 +size 923399168 diff --git a/Llama_3.2_1b_Odyssea_V1.Q5_K_M.gguf b/Llama_3.2_1b_Odyssea_V1.Q5_K_M.gguf new file mode 100644 index 0000000..aa9fb3d --- /dev/null +++ b/Llama_3.2_1b_Odyssea_V1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1105f484bd49fa81f2d03e6dcdf256c030da7cd4c9ecd2da2211ffd9f51731f1 +size 1092088832 diff --git a/Llama_3.2_1b_Odyssea_V1.Q5_K_S.gguf b/Llama_3.2_1b_Odyssea_V1.Q5_K_S.gguf new file mode 100644 index 0000000..dcc3daf --- /dev/null +++ b/Llama_3.2_1b_Odyssea_V1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:357216311957e3f4735363431c10bb323383e2f93543a52e16375c1677a80939 +size 1073148928 diff --git a/Llama_3.2_1b_Odyssea_V1.Q6_K.gguf b/Llama_3.2_1b_Odyssea_V1.Q6_K.gguf new file mode 100644 index 0000000..54c1ee7 --- /dev/null +++ b/Llama_3.2_1b_Odyssea_V1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d650815fb68ddd5503f19169ced68bc0988133f9656916fefca1fee5fc5be85c +size 1237271552 diff --git a/Llama_3.2_1b_Odyssea_V1.Q8_0.gguf b/Llama_3.2_1b_Odyssea_V1.Q8_0.gguf new file mode 100644 index 0000000..9698a8a --- /dev/null +++ b/Llama_3.2_1b_Odyssea_V1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d945fa2d39bfe036b633578f3dc0787e12b950ec96377308651eca0b7869d4d +size 1600168960 diff --git a/Llama_3.2_1b_Odyssea_V1.f16.gguf b/Llama_3.2_1b_Odyssea_V1.f16.gguf new file mode 100644 index 0000000..c11cc72 --- /dev/null +++ b/Llama_3.2_1b_Odyssea_V1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d78c36d4c121455aae67434338368e96c5e17aa6cb7f8835461105f58dc797e +size 3004933120 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6547f8f --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: Nexesenex/Llama_3.2_1b_Odyssea_V1 +language: +- en +library_name: transformers +license: llama3.2 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/Nexesenex/Llama_3.2_1b_Odyssea_V1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama_3.2_1b_Odyssea_V1-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama_3.2_1b_Odyssea_V1-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_3.2_1b_Odyssea_V1-GGUF/resolve/main/Llama_3.2_1b_Odyssea_V1.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_1b_Odyssea_V1-GGUF/resolve/main/Llama_3.2_1b_Odyssea_V1.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_1b_Odyssea_V1-GGUF/resolve/main/Llama_3.2_1b_Odyssea_V1.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_1b_Odyssea_V1-GGUF/resolve/main/Llama_3.2_1b_Odyssea_V1.Q3_K_L.gguf) | Q3_K_L | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_1b_Odyssea_V1-GGUF/resolve/main/Llama_3.2_1b_Odyssea_V1.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_1b_Odyssea_V1-GGUF/resolve/main/Llama_3.2_1b_Odyssea_V1.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_1b_Odyssea_V1-GGUF/resolve/main/Llama_3.2_1b_Odyssea_V1.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_1b_Odyssea_V1-GGUF/resolve/main/Llama_3.2_1b_Odyssea_V1.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_1b_Odyssea_V1-GGUF/resolve/main/Llama_3.2_1b_Odyssea_V1.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_1b_Odyssea_V1-GGUF/resolve/main/Llama_3.2_1b_Odyssea_V1.Q6_K.gguf) | Q6_K | 1.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_1b_Odyssea_V1-GGUF/resolve/main/Llama_3.2_1b_Odyssea_V1.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_1b_Odyssea_V1-GGUF/resolve/main/Llama_3.2_1b_Odyssea_V1.f16.gguf) | f16 | 3.1 | 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. + +