commit 4b62d95ff5bd00e510ae5c8bc8479fd445ff3a89 Author: ModelHub XC Date: Sun Jun 14 07:08:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/AI21-Jamba2-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3cfa542 --- /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 +AI21-Jamba2-3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba2-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba2-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba2-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba2-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba2-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba2-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba2-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba2-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba2-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba2-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba2-3B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/AI21-Jamba2-3B.IQ4_XS.gguf b/AI21-Jamba2-3B.IQ4_XS.gguf new file mode 100644 index 0000000..ee00176 --- /dev/null +++ b/AI21-Jamba2-3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f835e4bca0122850b61c040bf7bc2443c8569ccfabb7437b65d9e77c3dc88a43 +size 1770185248 diff --git a/AI21-Jamba2-3B.Q2_K.gguf b/AI21-Jamba2-3B.Q2_K.gguf new file mode 100644 index 0000000..cdc5492 --- /dev/null +++ b/AI21-Jamba2-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cbd2ce94d01e6046f97cd8491b5b820d5a84b8bb8e252b0fe0173c22682dfdb +size 1211035168 diff --git a/AI21-Jamba2-3B.Q3_K_L.gguf b/AI21-Jamba2-3B.Q3_K_L.gguf new file mode 100644 index 0000000..8d39b60 --- /dev/null +++ b/AI21-Jamba2-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80fe448156e57625b20179701914ed7214804db35d31b301237e7ae49bd04eb3 +size 1610113568 diff --git a/AI21-Jamba2-3B.Q3_K_M.gguf b/AI21-Jamba2-3B.Q3_K_M.gguf new file mode 100644 index 0000000..7c3e7bd --- /dev/null +++ b/AI21-Jamba2-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50308829c2cf381bb5f30c93b3c35c989dfd23bd8f15811bc8c38f24ba15c79f +size 1537696288 diff --git a/AI21-Jamba2-3B.Q3_K_S.gguf b/AI21-Jamba2-3B.Q3_K_S.gguf new file mode 100644 index 0000000..0bcecc3 --- /dev/null +++ b/AI21-Jamba2-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05f42c20dad877932a72801c83e5ecbda2c6d1e9c7350c40811939e40102a82b +size 1455177248 diff --git a/AI21-Jamba2-3B.Q4_K_M.gguf b/AI21-Jamba2-3B.Q4_K_M.gguf new file mode 100644 index 0000000..9c8870e --- /dev/null +++ b/AI21-Jamba2-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:061bc1ec3264488fa3405727074d7acbffecc58f2b7d2e188f8d64d22c0e95c9 +size 1932696608 diff --git a/AI21-Jamba2-3B.Q4_K_S.gguf b/AI21-Jamba2-3B.Q4_K_S.gguf new file mode 100644 index 0000000..1a6acf7 --- /dev/null +++ b/AI21-Jamba2-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83e57b62b50b5134befe7e1b7977409743c139e5e4c6bb6db467d4c3ca3df38c +size 1864864288 diff --git a/AI21-Jamba2-3B.Q5_K_M.gguf b/AI21-Jamba2-3B.Q5_K_M.gguf new file mode 100644 index 0000000..c18e262 --- /dev/null +++ b/AI21-Jamba2-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73373563345070bf47e2beed0693bfff53d11841c3afc477f835101df2aa3309 +size 2272889888 diff --git a/AI21-Jamba2-3B.Q5_K_S.gguf b/AI21-Jamba2-3B.Q5_K_S.gguf new file mode 100644 index 0000000..47e2ce7 --- /dev/null +++ b/AI21-Jamba2-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8208ad50333291533b77a4ddb05c3ae64fe3addd114d3806de7309d25eb6e92a +size 2233852448 diff --git a/AI21-Jamba2-3B.Q6_K.gguf b/AI21-Jamba2-3B.Q6_K.gguf new file mode 100644 index 0000000..a657fa3 --- /dev/null +++ b/AI21-Jamba2-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:832161e311f9daf880eb6b33241574b81a1d19a9890d223f8e86e561ee8e816f +size 2639586848 diff --git a/AI21-Jamba2-3B.Q8_0.gguf b/AI21-Jamba2-3B.Q8_0.gguf new file mode 100644 index 0000000..1b75102 --- /dev/null +++ b/AI21-Jamba2-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f1b6ceebf25bf6b94e29fd77ac18354aca46a244d8679355995daa86898bd22 +size 3407950368 diff --git a/AI21-Jamba2-3B.f16.gguf b/AI21-Jamba2-3B.f16.gguf new file mode 100644 index 0000000..4cb8757 --- /dev/null +++ b/AI21-Jamba2-3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1173b5da90948a46ea144d341bdfc2a7cdc6ce4b38e5914b7a7d4acaa338e57 +size 6402228768 diff --git a/README.md b/README.md new file mode 100644 index 0000000..219832c --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: ai21labs/AI21-Jamba2-3B +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/ai21labs/AI21-Jamba2-3B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#AI21-Jamba2-3B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/AI21-Jamba2-3B-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/AI21-Jamba2-3B-GGUF/resolve/main/AI21-Jamba2-3B.Q2_K.gguf) | Q2_K | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba2-3B-GGUF/resolve/main/AI21-Jamba2-3B.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba2-3B-GGUF/resolve/main/AI21-Jamba2-3B.Q3_K_M.gguf) | Q3_K_M | 1.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba2-3B-GGUF/resolve/main/AI21-Jamba2-3B.Q3_K_L.gguf) | Q3_K_L | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba2-3B-GGUF/resolve/main/AI21-Jamba2-3B.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba2-3B-GGUF/resolve/main/AI21-Jamba2-3B.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba2-3B-GGUF/resolve/main/AI21-Jamba2-3B.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba2-3B-GGUF/resolve/main/AI21-Jamba2-3B.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba2-3B-GGUF/resolve/main/AI21-Jamba2-3B.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba2-3B-GGUF/resolve/main/AI21-Jamba2-3B.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba2-3B-GGUF/resolve/main/AI21-Jamba2-3B.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba2-3B-GGUF/resolve/main/AI21-Jamba2-3B.f16.gguf) | f16 | 6.5 | 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. + +