commit 4defebc82c3b95e4c4a968b81d2127922a7aa5c7 Author: ModelHub XC Date: Wed Jul 8 04:19:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/EdgeRunner-Command-AgentF-llama31-2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1a4407a --- /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 +EdgeRunner-Command-AgentF-llama31-2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +EdgeRunner-Command-AgentF-llama31-2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +EdgeRunner-Command-AgentF-llama31-2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +EdgeRunner-Command-AgentF-llama31-2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +EdgeRunner-Command-AgentF-llama31-2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +EdgeRunner-Command-AgentF-llama31-2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +EdgeRunner-Command-AgentF-llama31-2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +EdgeRunner-Command-AgentF-llama31-2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +EdgeRunner-Command-AgentF-llama31-2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +EdgeRunner-Command-AgentF-llama31-2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +EdgeRunner-Command-AgentF-llama31-2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +EdgeRunner-Command-AgentF-llama31-2.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/EdgeRunner-Command-AgentF-llama31-2.IQ4_XS.gguf b/EdgeRunner-Command-AgentF-llama31-2.IQ4_XS.gguf new file mode 100644 index 0000000..b600232 --- /dev/null +++ b/EdgeRunner-Command-AgentF-llama31-2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c239535c3114a26a54b825060422340a17e927b11a5ec762f2fd4b003c7ac8a +size 4484367840 diff --git a/EdgeRunner-Command-AgentF-llama31-2.Q2_K.gguf b/EdgeRunner-Command-AgentF-llama31-2.Q2_K.gguf new file mode 100644 index 0000000..b2e8bee --- /dev/null +++ b/EdgeRunner-Command-AgentF-llama31-2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ebca5c758624194fa743f2a536f6fc30e6ba97f874ff65b10eacc82e0dd8e26 +size 3179136480 diff --git a/EdgeRunner-Command-AgentF-llama31-2.Q3_K_L.gguf b/EdgeRunner-Command-AgentF-llama31-2.Q3_K_L.gguf new file mode 100644 index 0000000..a4268f7 --- /dev/null +++ b/EdgeRunner-Command-AgentF-llama31-2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:674d3ea03f51b2902658c8f61bf748a76a0569d14fc56adcf51f4a90c7a429bf +size 4321961440 diff --git a/EdgeRunner-Command-AgentF-llama31-2.Q3_K_M.gguf b/EdgeRunner-Command-AgentF-llama31-2.Q3_K_M.gguf new file mode 100644 index 0000000..92c7e4d --- /dev/null +++ b/EdgeRunner-Command-AgentF-llama31-2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fdd96cce71d35f6554eba6829f0b6b3042fdf9bcb0efcb97c4f38929aafce66 +size 4018922976 diff --git a/EdgeRunner-Command-AgentF-llama31-2.Q3_K_S.gguf b/EdgeRunner-Command-AgentF-llama31-2.Q3_K_S.gguf new file mode 100644 index 0000000..34c54fb --- /dev/null +++ b/EdgeRunner-Command-AgentF-llama31-2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:525aebab45cbd892fd98073b0cfa5420705a5de1ab7601a996d70b43ef1ca3ef +size 3664504288 diff --git a/EdgeRunner-Command-AgentF-llama31-2.Q4_K_M.gguf b/EdgeRunner-Command-AgentF-llama31-2.Q4_K_M.gguf new file mode 100644 index 0000000..f19dc32 --- /dev/null +++ b/EdgeRunner-Command-AgentF-llama31-2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f88f31dc95b7945fea906dc5795fad31b9a61e1c0ddf5dd140d9d24a7ebc701 +size 4920739296 diff --git a/EdgeRunner-Command-AgentF-llama31-2.Q4_K_S.gguf b/EdgeRunner-Command-AgentF-llama31-2.Q4_K_S.gguf new file mode 100644 index 0000000..a363abe --- /dev/null +++ b/EdgeRunner-Command-AgentF-llama31-2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dffd35b49fb24e7d0d8560ea7e8af03c1216d5075e6d61d7e24394140eba584 +size 4692674016 diff --git a/EdgeRunner-Command-AgentF-llama31-2.Q5_K_M.gguf b/EdgeRunner-Command-AgentF-llama31-2.Q5_K_M.gguf new file mode 100644 index 0000000..65589b6 --- /dev/null +++ b/EdgeRunner-Command-AgentF-llama31-2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9eb2fe73012b8177ca79fb83b340bc641f5fc0202df2fefd42cb89388cf50c2a +size 5732992480 diff --git a/EdgeRunner-Command-AgentF-llama31-2.Q5_K_S.gguf b/EdgeRunner-Command-AgentF-llama31-2.Q5_K_S.gguf new file mode 100644 index 0000000..f973942 --- /dev/null +++ b/EdgeRunner-Command-AgentF-llama31-2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b66a3a08611ad62f6d9138646adc3cddc0cbb19bc27cf77587192439ed6289f +size 5599299040 diff --git a/EdgeRunner-Command-AgentF-llama31-2.Q6_K.gguf b/EdgeRunner-Command-AgentF-llama31-2.Q6_K.gguf new file mode 100644 index 0000000..22aa1a2 --- /dev/null +++ b/EdgeRunner-Command-AgentF-llama31-2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75bb7c06137ded04c996e541e12662f53488022db5cfba595340a3faf90bb993 +size 6596011488 diff --git a/EdgeRunner-Command-AgentF-llama31-2.Q8_0.gguf b/EdgeRunner-Command-AgentF-llama31-2.Q8_0.gguf new file mode 100644 index 0000000..6ea63bd --- /dev/null +++ b/EdgeRunner-Command-AgentF-llama31-2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47baec35799a68174ff795b07b937b4da604b9006d663c06647ece789d403e79 +size 8540775904 diff --git a/EdgeRunner-Command-AgentF-llama31-2.f16.gguf b/EdgeRunner-Command-AgentF-llama31-2.f16.gguf new file mode 100644 index 0000000..78183b7 --- /dev/null +++ b/EdgeRunner-Command-AgentF-llama31-2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ec78678348060ba93c297d32619c60c9557b00d60717107c66b12b13322dfab +size 16068896224 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d304120 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: slm-research-vn/EdgeRunner-Command-AgentF-llama31-2 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/slm-research-vn/EdgeRunner-Command-AgentF-llama31-2 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/EdgeRunner-Command-AgentF-llama31-2-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/EdgeRunner-Command-AgentF-llama31-2-GGUF/resolve/main/EdgeRunner-Command-AgentF-llama31-2.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/EdgeRunner-Command-AgentF-llama31-2-GGUF/resolve/main/EdgeRunner-Command-AgentF-llama31-2.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/EdgeRunner-Command-AgentF-llama31-2-GGUF/resolve/main/EdgeRunner-Command-AgentF-llama31-2.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/EdgeRunner-Command-AgentF-llama31-2-GGUF/resolve/main/EdgeRunner-Command-AgentF-llama31-2.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/EdgeRunner-Command-AgentF-llama31-2-GGUF/resolve/main/EdgeRunner-Command-AgentF-llama31-2.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/EdgeRunner-Command-AgentF-llama31-2-GGUF/resolve/main/EdgeRunner-Command-AgentF-llama31-2.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/EdgeRunner-Command-AgentF-llama31-2-GGUF/resolve/main/EdgeRunner-Command-AgentF-llama31-2.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/EdgeRunner-Command-AgentF-llama31-2-GGUF/resolve/main/EdgeRunner-Command-AgentF-llama31-2.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/EdgeRunner-Command-AgentF-llama31-2-GGUF/resolve/main/EdgeRunner-Command-AgentF-llama31-2.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/EdgeRunner-Command-AgentF-llama31-2-GGUF/resolve/main/EdgeRunner-Command-AgentF-llama31-2.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/EdgeRunner-Command-AgentF-llama31-2-GGUF/resolve/main/EdgeRunner-Command-AgentF-llama31-2.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/EdgeRunner-Command-AgentF-llama31-2-GGUF/resolve/main/EdgeRunner-Command-AgentF-llama31-2.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. + +