commit da607e1d276d01fcc91620c551993ecf6cb84ff0 Author: ModelHub XC Date: Mon Oct 12 11:57:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/typhoon-7b-instruct-01-30-2024-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..070d11d --- /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 +typhoon-7b-instruct-01-30-2024.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +typhoon-7b-instruct-01-30-2024.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +typhoon-7b-instruct-01-30-2024.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +typhoon-7b-instruct-01-30-2024.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +typhoon-7b-instruct-01-30-2024.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +typhoon-7b-instruct-01-30-2024.f16.gguf filter=lfs diff=lfs merge=lfs -text +typhoon-7b-instruct-01-30-2024.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +typhoon-7b-instruct-01-30-2024.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +typhoon-7b-instruct-01-30-2024.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +typhoon-7b-instruct-01-30-2024.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +typhoon-7b-instruct-01-30-2024.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +typhoon-7b-instruct-01-30-2024.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..56e5fb0 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: typhoon-ai/typhoon-7b-instruct-01-30-2024 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/typhoon-ai/typhoon-7b-instruct-01-30-2024 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#typhoon-7b-instruct-01-30-2024-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/typhoon-7b-instruct-01-30-2024-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/typhoon-7b-instruct-01-30-2024-GGUF/resolve/main/typhoon-7b-instruct-01-30-2024.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/typhoon-7b-instruct-01-30-2024-GGUF/resolve/main/typhoon-7b-instruct-01-30-2024.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/typhoon-7b-instruct-01-30-2024-GGUF/resolve/main/typhoon-7b-instruct-01-30-2024.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/typhoon-7b-instruct-01-30-2024-GGUF/resolve/main/typhoon-7b-instruct-01-30-2024.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/typhoon-7b-instruct-01-30-2024-GGUF/resolve/main/typhoon-7b-instruct-01-30-2024.IQ4_XS.gguf) | IQ4_XS | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/typhoon-7b-instruct-01-30-2024-GGUF/resolve/main/typhoon-7b-instruct-01-30-2024.Q4_K_S.gguf) | Q4_K_S | 4.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/typhoon-7b-instruct-01-30-2024-GGUF/resolve/main/typhoon-7b-instruct-01-30-2024.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/typhoon-7b-instruct-01-30-2024-GGUF/resolve/main/typhoon-7b-instruct-01-30-2024.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/typhoon-7b-instruct-01-30-2024-GGUF/resolve/main/typhoon-7b-instruct-01-30-2024.Q5_K_M.gguf) | Q5_K_M | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/typhoon-7b-instruct-01-30-2024-GGUF/resolve/main/typhoon-7b-instruct-01-30-2024.Q6_K.gguf) | Q6_K | 6.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/typhoon-7b-instruct-01-30-2024-GGUF/resolve/main/typhoon-7b-instruct-01-30-2024.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/typhoon-7b-instruct-01-30-2024-GGUF/resolve/main/typhoon-7b-instruct-01-30-2024.f16.gguf) | f16 | 14.6 | 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. + + diff --git a/typhoon-7b-instruct-01-30-2024.IQ4_XS.gguf b/typhoon-7b-instruct-01-30-2024.IQ4_XS.gguf new file mode 100644 index 0000000..c28761e --- /dev/null +++ b/typhoon-7b-instruct-01-30-2024.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8bddea4a08cb05ac97fb4a7c8073e33e105dce8b5ec55ee5fd150bff5964cd2 +size 3962313088 diff --git a/typhoon-7b-instruct-01-30-2024.Q2_K.gguf b/typhoon-7b-instruct-01-30-2024.Q2_K.gguf new file mode 100644 index 0000000..388c33b --- /dev/null +++ b/typhoon-7b-instruct-01-30-2024.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89e2cb8b8b0926967c99daefb05fddb912167ce5a23854b53e28c12cd6d02fda +size 2734486848 diff --git a/typhoon-7b-instruct-01-30-2024.Q3_K_L.gguf b/typhoon-7b-instruct-01-30-2024.Q3_K_L.gguf new file mode 100644 index 0000000..af8202c --- /dev/null +++ b/typhoon-7b-instruct-01-30-2024.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bd6958aed24438c5d45ddd8609b7627348600e1a876de621d8be838dd1951ed +size 3838609248 diff --git a/typhoon-7b-instruct-01-30-2024.Q3_K_M.gguf b/typhoon-7b-instruct-01-30-2024.Q3_K_M.gguf new file mode 100644 index 0000000..02ce4d1 --- /dev/null +++ b/typhoon-7b-instruct-01-30-2024.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95d8665b3b00d016736fe5300cf82ca2fd3d6535a5f513be4abd15f56833c437 +size 3535570784 diff --git a/typhoon-7b-instruct-01-30-2024.Q3_K_S.gguf b/typhoon-7b-instruct-01-30-2024.Q3_K_S.gguf new file mode 100644 index 0000000..e53223a --- /dev/null +++ b/typhoon-7b-instruct-01-30-2024.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ce4dcabccf46344d6dd6f167ceca09257be491d0b59c26602175ab0968326d5 +size 3181152096 diff --git a/typhoon-7b-instruct-01-30-2024.Q4_K_M.gguf b/typhoon-7b-instruct-01-30-2024.Q4_K_M.gguf new file mode 100644 index 0000000..c2b87e7 --- /dev/null +++ b/typhoon-7b-instruct-01-30-2024.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e5e24bc168e0ec2c793b3dd36a3eadbc0d26a78ae3ac9b990cc194732cdb1f9 +size 4386776064 diff --git a/typhoon-7b-instruct-01-30-2024.Q4_K_S.gguf b/typhoon-7b-instruct-01-30-2024.Q4_K_S.gguf new file mode 100644 index 0000000..dba9696 --- /dev/null +++ b/typhoon-7b-instruct-01-30-2024.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8395eedff539f54a96f70d0ed0147844df9c463e8ddcd4f39c31facb0e8dddd1 +size 4158710784 diff --git a/typhoon-7b-instruct-01-30-2024.Q5_K_M.gguf b/typhoon-7b-instruct-01-30-2024.Q5_K_M.gguf new file mode 100644 index 0000000..a00505a --- /dev/null +++ b/typhoon-7b-instruct-01-30-2024.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0409ddf6be59b01fa3bd34d540703a4d383a7d6a463c942352a0b543ec15a5f3 +size 5151395328 diff --git a/typhoon-7b-instruct-01-30-2024.Q5_K_S.gguf b/typhoon-7b-instruct-01-30-2024.Q5_K_S.gguf new file mode 100644 index 0000000..df4ecf5 --- /dev/null +++ b/typhoon-7b-instruct-01-30-2024.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54d2b1e4aa656a76cedc81d57030b4a4f0b0022f4c686ed5dda882316081a6f4 +size 5017701888 diff --git a/typhoon-7b-instruct-01-30-2024.Q6_K.gguf b/typhoon-7b-instruct-01-30-2024.Q6_K.gguf new file mode 100644 index 0000000..bb3be9e --- /dev/null +++ b/typhoon-7b-instruct-01-30-2024.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82d390a1e4b17f3979d1c010f3da858ac1997ea6846bcbbe9ecf9b1466ad2cf2 +size 5963803296 diff --git a/typhoon-7b-instruct-01-30-2024.Q8_0.gguf b/typhoon-7b-instruct-01-30-2024.Q8_0.gguf new file mode 100644 index 0000000..08a5380 --- /dev/null +++ b/typhoon-7b-instruct-01-30-2024.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:817132e0cb3f3912d330e18cccbcc5f763dd990f07199cfafff4630971770150 +size 7723986272 diff --git a/typhoon-7b-instruct-01-30-2024.f16.gguf b/typhoon-7b-instruct-01-30-2024.f16.gguf new file mode 100644 index 0000000..0d50a5c --- /dev/null +++ b/typhoon-7b-instruct-01-30-2024.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:215e61c0f57570eac9c60ef747510eb63297d99ab0c4951084db96285b3a5241 +size 14537597792