commit dd53dd773b238664b32e74155e2394c3f5b3945b Author: ModelHub XC Date: Thu Sep 17 04:44:24 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-Diffbot-Small-2412-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..bb0a31a --- /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-3.1-Diffbot-Small-2412.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Diffbot-Small-2412.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Diffbot-Small-2412.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Diffbot-Small-2412.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Diffbot-Small-2412.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Diffbot-Small-2412.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Diffbot-Small-2412.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Diffbot-Small-2412.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Diffbot-Small-2412.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Diffbot-Small-2412.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Diffbot-Small-2412.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Diffbot-Small-2412.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-Diffbot-Small-2412.IQ4_XS.gguf b/Llama-3.1-Diffbot-Small-2412.IQ4_XS.gguf new file mode 100644 index 0000000..7634005 --- /dev/null +++ b/Llama-3.1-Diffbot-Small-2412.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2141552f6892cd2eee1629b3184d8a40c4e91391e34ff591bef5bd49453f00a +size 4484363968 diff --git a/Llama-3.1-Diffbot-Small-2412.Q2_K.gguf b/Llama-3.1-Diffbot-Small-2412.Q2_K.gguf new file mode 100644 index 0000000..eafae7a --- /dev/null +++ b/Llama-3.1-Diffbot-Small-2412.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac9ae18ea95a869c29e48cf731e03c0985e27bb0451131a9fcef37a0e443aa4a +size 3179132608 diff --git a/Llama-3.1-Diffbot-Small-2412.Q3_K_L.gguf b/Llama-3.1-Diffbot-Small-2412.Q3_K_L.gguf new file mode 100644 index 0000000..a0032a9 --- /dev/null +++ b/Llama-3.1-Diffbot-Small-2412.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e70d18da1a7931953505b688396a49866b558d5872f80836135a2756d9d598b7 +size 4321957568 diff --git a/Llama-3.1-Diffbot-Small-2412.Q3_K_M.gguf b/Llama-3.1-Diffbot-Small-2412.Q3_K_M.gguf new file mode 100644 index 0000000..e20c141 --- /dev/null +++ b/Llama-3.1-Diffbot-Small-2412.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a96cd237107d1f6fb4854b2102878880a603f80ba1a3409acbad7ee85db95a22 +size 4018919104 diff --git a/Llama-3.1-Diffbot-Small-2412.Q3_K_S.gguf b/Llama-3.1-Diffbot-Small-2412.Q3_K_S.gguf new file mode 100644 index 0000000..884a774 --- /dev/null +++ b/Llama-3.1-Diffbot-Small-2412.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:500d8b6eb2d75a2a894ce3156fc6322b81714d06942bad7369f62960b48f964c +size 3664500416 diff --git a/Llama-3.1-Diffbot-Small-2412.Q4_K_M.gguf b/Llama-3.1-Diffbot-Small-2412.Q4_K_M.gguf new file mode 100644 index 0000000..7c4462d --- /dev/null +++ b/Llama-3.1-Diffbot-Small-2412.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:891c95dec10238c513e355d8c96c363b6013719546ca61682c2734cff59bfb5c +size 4920735424 diff --git a/Llama-3.1-Diffbot-Small-2412.Q4_K_S.gguf b/Llama-3.1-Diffbot-Small-2412.Q4_K_S.gguf new file mode 100644 index 0000000..657a21b --- /dev/null +++ b/Llama-3.1-Diffbot-Small-2412.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01db3c40234965ff22dab78b1feac7457d37ebafa9ce88e7e54d248020f190b1 +size 4692670144 diff --git a/Llama-3.1-Diffbot-Small-2412.Q5_K_M.gguf b/Llama-3.1-Diffbot-Small-2412.Q5_K_M.gguf new file mode 100644 index 0000000..2e590a6 --- /dev/null +++ b/Llama-3.1-Diffbot-Small-2412.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1a9a0f7c694530b6a32affb9cb7d163a0f84fbed2ce263b399489561752358b +size 5732988608 diff --git a/Llama-3.1-Diffbot-Small-2412.Q5_K_S.gguf b/Llama-3.1-Diffbot-Small-2412.Q5_K_S.gguf new file mode 100644 index 0000000..830ff34 --- /dev/null +++ b/Llama-3.1-Diffbot-Small-2412.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51c0547b2abcfb987e771915163367dfba68d1e249212306469a5f0eab00324b +size 5599295168 diff --git a/Llama-3.1-Diffbot-Small-2412.Q6_K.gguf b/Llama-3.1-Diffbot-Small-2412.Q6_K.gguf new file mode 100644 index 0000000..7edf65a --- /dev/null +++ b/Llama-3.1-Diffbot-Small-2412.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e7890032ff63834641717d712906af4e3f64a58da09d8bcf39e049700ff81dc +size 6596007616 diff --git a/Llama-3.1-Diffbot-Small-2412.Q8_0.gguf b/Llama-3.1-Diffbot-Small-2412.Q8_0.gguf new file mode 100644 index 0000000..bae4fdb --- /dev/null +++ b/Llama-3.1-Diffbot-Small-2412.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:578630f7a21be4efe60c545bf55a5561b4bef89a06b85f4138097013aac42c02 +size 8540772032 diff --git a/Llama-3.1-Diffbot-Small-2412.f16.gguf b/Llama-3.1-Diffbot-Small-2412.f16.gguf new file mode 100644 index 0000000..1c2c55e --- /dev/null +++ b/Llama-3.1-Diffbot-Small-2412.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08d906940f7a59bb1087ef943e17cef0039140e3e5e09e869894b20e58899a32 +size 16068892352 diff --git a/README.md b/README.md new file mode 100644 index 0000000..aac9e23 --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: diffbot/Llama-3.1-Diffbot-Small-2412 +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/diffbot/Llama-3.1-Diffbot-Small-2412 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.1-Diffbot-Small-2412-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-3.1-Diffbot-Small-2412-GGUF/resolve/main/Llama-3.1-Diffbot-Small-2412.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Diffbot-Small-2412-GGUF/resolve/main/Llama-3.1-Diffbot-Small-2412.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Diffbot-Small-2412-GGUF/resolve/main/Llama-3.1-Diffbot-Small-2412.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Diffbot-Small-2412-GGUF/resolve/main/Llama-3.1-Diffbot-Small-2412.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Diffbot-Small-2412-GGUF/resolve/main/Llama-3.1-Diffbot-Small-2412.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Diffbot-Small-2412-GGUF/resolve/main/Llama-3.1-Diffbot-Small-2412.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Diffbot-Small-2412-GGUF/resolve/main/Llama-3.1-Diffbot-Small-2412.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Diffbot-Small-2412-GGUF/resolve/main/Llama-3.1-Diffbot-Small-2412.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Diffbot-Small-2412-GGUF/resolve/main/Llama-3.1-Diffbot-Small-2412.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Diffbot-Small-2412-GGUF/resolve/main/Llama-3.1-Diffbot-Small-2412.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Diffbot-Small-2412-GGUF/resolve/main/Llama-3.1-Diffbot-Small-2412.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Diffbot-Small-2412-GGUF/resolve/main/Llama-3.1-Diffbot-Small-2412.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. + +