commit 4d5e6795e9e5955124079b999fde420c84409d68 Author: ModelHub XC Date: Sun Oct 11 20:29:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Letta-o1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..003f9d5 --- /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 +Letta-o1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Letta-o1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Letta-o1.f16.gguf filter=lfs diff=lfs merge=lfs -text +Letta-o1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Letta-o1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Letta-o1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Letta-o1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Letta-o1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Letta-o1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Letta-o1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Letta-o1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Letta-o1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Letta-o1.IQ4_XS.gguf b/Letta-o1.IQ4_XS.gguf new file mode 100644 index 0000000..460ad32 --- /dev/null +++ b/Letta-o1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:586bc7d020465aaa5f412d112390ed44d092199a9b61b538fc5f195b7fd0d1af +size 4250297216 diff --git a/Letta-o1.Q2_K.gguf b/Letta-o1.Q2_K.gguf new file mode 100644 index 0000000..c42e0bb --- /dev/null +++ b/Letta-o1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e005cce63db2fc7286b2b8934ac7ebc2c1156cf4d23815ff4314db0c8f34bf8d +size 3015938944 diff --git a/Letta-o1.Q3_K_L.gguf b/Letta-o1.Q3_K_L.gguf new file mode 100644 index 0000000..9a07dfc --- /dev/null +++ b/Letta-o1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92e7346bcd6c9192b5a073678fe9d87cdb62904a38c26327e879d7e753a02017 +size 4088458112 diff --git a/Letta-o1.Q3_K_M.gguf b/Letta-o1.Q3_K_M.gguf new file mode 100644 index 0000000..b074a43 --- /dev/null +++ b/Letta-o1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75a0f93b28b18b9673098eb55ad7b738bc3eed0e7d2389a296734d8a6a235701 +size 3808390016 diff --git a/Letta-o1.Q3_K_S.gguf b/Letta-o1.Q3_K_S.gguf new file mode 100644 index 0000000..3c1ae04 --- /dev/null +++ b/Letta-o1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a12b1333ad578e83bb8b7345cec1a67d57d2d93b6cc3bd702024cbf0ea84c816 +size 3492367232 diff --git a/Letta-o1.Q4_K_M.gguf b/Letta-o1.Q4_K_M.gguf new file mode 100644 index 0000000..e8ff30a --- /dev/null +++ b/Letta-o1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12db41f8aa76f2185caffcd71aa620eec9862e89ec473465b7d815a30a6875a1 +size 4683072384 diff --git a/Letta-o1.Q4_K_S.gguf b/Letta-o1.Q4_K_S.gguf new file mode 100644 index 0000000..3d985bc --- /dev/null +++ b/Letta-o1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2b0acd5aa28c7cbc8862d10408d581820f338ba8a9089da49c4790442242f30 +size 4457767808 diff --git a/Letta-o1.Q5_K_M.gguf b/Letta-o1.Q5_K_M.gguf new file mode 100644 index 0000000..0fdb8c9 --- /dev/null +++ b/Letta-o1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11da2a8595cf9855faeb9754f4faf6b3ba95458c27744fc4801702f69f37e90d +size 5444830080 diff --git a/Letta-o1.Q5_K_S.gguf b/Letta-o1.Q5_K_S.gguf new file mode 100644 index 0000000..e16a7a4 --- /dev/null +++ b/Letta-o1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6ef32431d54b3e1c4c56852dc23bc6504d6b4b0881bc28fb50ef5a33840d1db +size 5315175296 diff --git a/Letta-o1.Q6_K.gguf b/Letta-o1.Q6_K.gguf new file mode 100644 index 0000000..f218a18 --- /dev/null +++ b/Letta-o1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef28f005b806e2f23bb97be21f7c41ed94feb92c0b3d9034e05afe590762b2ca +size 6254197632 diff --git a/Letta-o1.Q8_0.gguf b/Letta-o1.Q8_0.gguf new file mode 100644 index 0000000..7699798 --- /dev/null +++ b/Letta-o1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50ea6819042ca87dc4df9ec53445fd45795a9c90496415af5ac38282a04aa26a +size 8098524032 diff --git a/Letta-o1.f16.gguf b/Letta-o1.f16.gguf new file mode 100644 index 0000000..81ef281 --- /dev/null +++ b/Letta-o1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3d8a30f6d86e9b5d226513cf0efe93d582bee93bf4ee28a72f08ce1b4f20e17 +size 15237852032 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b69a2aa --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: minchyeom/Letta-o1 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/minchyeom/Letta-o1 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Letta-o1-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/Letta-o1-GGUF/resolve/main/Letta-o1.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Letta-o1-GGUF/resolve/main/Letta-o1.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Letta-o1-GGUF/resolve/main/Letta-o1.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Letta-o1-GGUF/resolve/main/Letta-o1.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Letta-o1-GGUF/resolve/main/Letta-o1.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Letta-o1-GGUF/resolve/main/Letta-o1.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Letta-o1-GGUF/resolve/main/Letta-o1.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Letta-o1-GGUF/resolve/main/Letta-o1.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Letta-o1-GGUF/resolve/main/Letta-o1.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Letta-o1-GGUF/resolve/main/Letta-o1.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Letta-o1-GGUF/resolve/main/Letta-o1.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Letta-o1-GGUF/resolve/main/Letta-o1.f16.gguf) | f16 | 15.3 | 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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +