commit 8912b09c4ac7863f74ce4fc2f30f28222e8eeb99 Author: ModelHub XC Date: Mon Aug 31 16:48:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/tencent_Hunyuan-0.5B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..53d7257 --- /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 +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..99124e5 --- /dev/null +++ b/README.md @@ -0,0 +1,166 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +base_model_relation: quantized +base_model: tencent/Hunyuan-0.5B-Instruct +--- + +## Llamacpp imatrix Quantizations of Hunyuan-0.5B-Instruct by tencent + +Using llama.cpp release b6076 for quantization. + +Original model: https://huggingface.co/tencent/Hunyuan-0.5B-Instruct + +All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) + +Run them in [LM Studio](https://lmstudio.ai/) + +Run them directly with [llama.cpp](https://github.com/ggerganov/llama.cpp), or any other llama.cpp based project + +## Prompt format + +``` +<｜hy_begin▁of▁sentence｜>{system_prompt}<｜hy_place▁holder▁no▁3｜><｜hy_User｜>{prompt}<｜hy_Assistant｜><｜hy_place▁holder▁no▁2｜><｜hy_Assistant｜> +``` + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [Hunyuan-0.5B-Instruct-bf16.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-0.5B-Instruct-GGUF/blob/main/tencent_Hunyuan-0.5B-Instruct-bf16.gguf) | bf16 | 1.08GB | false | Full BF16 weights. | +| [Hunyuan-0.5B-Instruct-Q8_0.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-0.5B-Instruct-GGUF/blob/main/tencent_Hunyuan-0.5B-Instruct-Q8_0.gguf) | Q8_0 | 0.58GB | false | Extremely high quality, generally unneeded but max available quant. | +| [Hunyuan-0.5B-Instruct-Q6_K_L.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-0.5B-Instruct-GGUF/blob/main/tencent_Hunyuan-0.5B-Instruct-Q6_K_L.gguf) | Q6_K_L | 0.48GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [Hunyuan-0.5B-Instruct-Q6_K.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-0.5B-Instruct-GGUF/blob/main/tencent_Hunyuan-0.5B-Instruct-Q6_K.gguf) | Q6_K | 0.45GB | false | Very high quality, near perfect, *recommended*. | +| [Hunyuan-0.5B-Instruct-Q5_K_L.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-0.5B-Instruct-GGUF/blob/main/tencent_Hunyuan-0.5B-Instruct-Q5_K_L.gguf) | Q5_K_L | 0.43GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [Hunyuan-0.5B-Instruct-Q5_K_M.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-0.5B-Instruct-GGUF/blob/main/tencent_Hunyuan-0.5B-Instruct-Q5_K_M.gguf) | Q5_K_M | 0.40GB | false | High quality, *recommended*. | +| [Hunyuan-0.5B-Instruct-Q5_K_S.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-0.5B-Instruct-GGUF/blob/main/tencent_Hunyuan-0.5B-Instruct-Q5_K_S.gguf) | Q5_K_S | 0.39GB | false | High quality, *recommended*. | +| [Hunyuan-0.5B-Instruct-Q4_K_L.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-0.5B-Instruct-GGUF/blob/main/tencent_Hunyuan-0.5B-Instruct-Q4_K_L.gguf) | Q4_K_L | 0.38GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [Hunyuan-0.5B-Instruct-Q4_1.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-0.5B-Instruct-GGUF/blob/main/tencent_Hunyuan-0.5B-Instruct-Q4_1.gguf) | Q4_1 | 0.37GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [Hunyuan-0.5B-Instruct-Q3_K_XL.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-0.5B-Instruct-GGUF/blob/main/tencent_Hunyuan-0.5B-Instruct-Q3_K_XL.gguf) | Q3_K_XL | 0.36GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [Hunyuan-0.5B-Instruct-Q4_K_M.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-0.5B-Instruct-GGUF/blob/main/tencent_Hunyuan-0.5B-Instruct-Q4_K_M.gguf) | Q4_K_M | 0.35GB | false | Good quality, default size for most use cases, *recommended*. | +| [Hunyuan-0.5B-Instruct-Q4_K_S.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-0.5B-Instruct-GGUF/blob/main/tencent_Hunyuan-0.5B-Instruct-Q4_K_S.gguf) | Q4_K_S | 0.34GB | false | Slightly lower quality with more space savings, *recommended*. | +| [Hunyuan-0.5B-Instruct-Q4_0.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-0.5B-Instruct-GGUF/blob/main/tencent_Hunyuan-0.5B-Instruct-Q4_0.gguf) | Q4_0 | 0.34GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [Hunyuan-0.5B-Instruct-IQ4_NL.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-0.5B-Instruct-GGUF/blob/main/tencent_Hunyuan-0.5B-Instruct-IQ4_NL.gguf) | IQ4_NL | 0.34GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [Hunyuan-0.5B-Instruct-IQ4_XS.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-0.5B-Instruct-GGUF/blob/main/tencent_Hunyuan-0.5B-Instruct-IQ4_XS.gguf) | IQ4_XS | 0.33GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Hunyuan-0.5B-Instruct-Q3_K_L.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-0.5B-Instruct-GGUF/blob/main/tencent_Hunyuan-0.5B-Instruct-Q3_K_L.gguf) | Q3_K_L | 0.33GB | false | Lower quality but usable, good for low RAM availability. | +| [Hunyuan-0.5B-Instruct-Q3_K_M.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-0.5B-Instruct-GGUF/blob/main/tencent_Hunyuan-0.5B-Instruct-Q3_K_M.gguf) | Q3_K_M | 0.31GB | false | Low quality. | +| [Hunyuan-0.5B-Instruct-IQ3_M.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-0.5B-Instruct-GGUF/blob/main/tencent_Hunyuan-0.5B-Instruct-IQ3_M.gguf) | IQ3_M | 0.30GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [Hunyuan-0.5B-Instruct-Q3_K_S.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-0.5B-Instruct-GGUF/blob/main/tencent_Hunyuan-0.5B-Instruct-Q3_K_S.gguf) | Q3_K_S | 0.29GB | false | Low quality, not recommended. | +| [Hunyuan-0.5B-Instruct-Q2_K_L.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-0.5B-Instruct-GGUF/blob/main/tencent_Hunyuan-0.5B-Instruct-Q2_K_L.gguf) | Q2_K_L | 0.29GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [Hunyuan-0.5B-Instruct-IQ3_XS.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-0.5B-Instruct-GGUF/blob/main/tencent_Hunyuan-0.5B-Instruct-IQ3_XS.gguf) | IQ3_XS | 0.28GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [Hunyuan-0.5B-Instruct-Q2_K.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-0.5B-Instruct-GGUF/blob/main/tencent_Hunyuan-0.5B-Instruct-Q2_K.gguf) | Q2_K | 0.26GB | false | Very low quality but surprisingly usable. | +| [Hunyuan-0.5B-Instruct-IQ3_XXS.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-0.5B-Instruct-GGUF/blob/main/tencent_Hunyuan-0.5B-Instruct-IQ3_XXS.gguf) | IQ3_XXS | 0.25GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [Hunyuan-0.5B-Instruct-IQ2_M.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-0.5B-Instruct-GGUF/blob/main/tencent_Hunyuan-0.5B-Instruct-IQ2_M.gguf) | IQ2_M | 0.23GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. | + +## Embed/output weights + +Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to. + +## Downloading using huggingface-cli + +
+ Click to view download instructions + +First, make sure you have hugginface-cli installed: + +``` +pip install -U "huggingface_hub[cli]" +``` + +Then, you can target the specific file you want: + +``` +huggingface-cli download bartowski/tencent_Hunyuan-0.5B-Instruct-GGUF --include "tencent_Hunyuan-0.5B-Instruct-Q4_K_M.gguf" --local-dir ./ +``` + +If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run: + +``` +huggingface-cli download bartowski/tencent_Hunyuan-0.5B-Instruct-GGUF --include "tencent_Hunyuan-0.5B-Instruct-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (tencent_Hunyuan-0.5B-Instruct-Q8_0) or download them all in place (./) + +
+ +## ARM/AVX information + +Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass. + +Now, however, there is something called "online repacking" for weights. details in [this PR](https://github.com/ggerganov/llama.cpp/pull/9921). If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly. + +As of llama.cpp build [b4282](https://github.com/ggerganov/llama.cpp/releases/tag/b4282) you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0. + +Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to [this PR](https://github.com/ggerganov/llama.cpp/pull/10541) which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase. + +
+ Click to view Q4_0_X_X information (deprecated + +I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking. + +
+ Click to view benchmarks on an AVX2 system (EPYC7702) + +| model | size | params | backend | threads | test | t/s | % (vs Q4_0) | +| ------------------------------ | ---------: | ---------: | ---------- | ------: | ------------: | -------------------: |-------------: | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp512 | 204.03 ± 1.03 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp1024 | 282.92 ± 0.19 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp2048 | 259.49 ± 0.44 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg128 | 39.12 ± 0.27 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg256 | 39.31 ± 0.69 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg512 | 40.52 ± 0.03 | 100% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp512 | 301.02 ± 1.74 | 147% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp1024 | 287.23 ± 0.20 | 101% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp2048 | 262.77 ± 1.81 | 101% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg128 | 18.80 ± 0.99 | 48% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg256 | 24.46 ± 3.04 | 83% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg512 | 36.32 ± 3.59 | 90% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp512 | 271.71 ± 3.53 | 133% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp1024 | 279.86 ± 45.63 | 100% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp2048 | 320.77 ± 5.00 | 124% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg128 | 43.51 ± 0.05 | 111% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg256 | 43.35 ± 0.09 | 110% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg512 | 42.60 ± 0.31 | 105% | + +Q4_0_8_8 offers a nice bump to prompt processing and a small bump to text generation + +
+ +
+ +## Which file should I choose? + +
+ Click here for details + +A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9) + +The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have. + +If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM. + +If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total. + +Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'. + +If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M. + +If you want to get more into the weeds, you can check out this extremely useful feature chart: + +[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix) + +But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size. + +These I-quants can also be used on CPU, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide. + +
+ +## Credits + +Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset. + +Thank you ZeroWw for the inspiration to experiment with embed/output. + +Thank you to LM Studio for sponsoring my work. + +Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/tencent_Hunyuan-0.5B-Instruct-IQ2_M.gguf b/tencent_Hunyuan-0.5B-Instruct-IQ2_M.gguf new file mode 100644 index 0000000..e22eb7e --- /dev/null +++ b/tencent_Hunyuan-0.5B-Instruct-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7540747de780d69916e5e4ff2aa9f932ed0de6cd9978d09277ca81f98f8f782d +size 232837824 diff --git a/tencent_Hunyuan-0.5B-Instruct-IQ3_M.gguf b/tencent_Hunyuan-0.5B-Instruct-IQ3_M.gguf new file mode 100644 index 0000000..d7c498e --- /dev/null +++ b/tencent_Hunyuan-0.5B-Instruct-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f61147bdf679e5d110f6e71dd97fb9275106adf1b77358a895b20798a3a66b08 +size 296713056 diff --git a/tencent_Hunyuan-0.5B-Instruct-IQ3_XS.gguf b/tencent_Hunyuan-0.5B-Instruct-IQ3_XS.gguf new file mode 100644 index 0000000..9d5d067 --- /dev/null +++ b/tencent_Hunyuan-0.5B-Instruct-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d726f1e7a757b749b6b70436974a7afd0acce53e85d3c8486f1d1b1f9903b45c +size 275491680 diff --git a/tencent_Hunyuan-0.5B-Instruct-IQ3_XXS.gguf b/tencent_Hunyuan-0.5B-Instruct-IQ3_XXS.gguf new file mode 100644 index 0000000..1e782c8 --- /dev/null +++ b/tencent_Hunyuan-0.5B-Instruct-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b2713a7c12a0c91e9b664ddf56de842b84b0055f7c02151aa792f76c43d3600 +size 246969024 diff --git a/tencent_Hunyuan-0.5B-Instruct-IQ4_NL.gguf b/tencent_Hunyuan-0.5B-Instruct-IQ4_NL.gguf new file mode 100644 index 0000000..af1cf5a --- /dev/null +++ b/tencent_Hunyuan-0.5B-Instruct-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a313e61ce8852d30d3cb363c3fa2a2c22e7573d43076b50c1c218066cd5c9401 +size 340372320 diff --git a/tencent_Hunyuan-0.5B-Instruct-IQ4_XS.gguf b/tencent_Hunyuan-0.5B-Instruct-IQ4_XS.gguf new file mode 100644 index 0000000..6669d4a --- /dev/null +++ b/tencent_Hunyuan-0.5B-Instruct-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8f25b2a8e32ee2da1ee791361f5d7a35f67656dc5ad0eb39144cf24a521c836 +size 327396192 diff --git a/tencent_Hunyuan-0.5B-Instruct-Q2_K.gguf b/tencent_Hunyuan-0.5B-Instruct-Q2_K.gguf new file mode 100644 index 0000000..fa1c263 --- /dev/null +++ b/tencent_Hunyuan-0.5B-Instruct-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:046f5a7378a9683e5f14b425a999b7bda293a2e9e13bb5a051605822982e3e21 +size 259664736 diff --git a/tencent_Hunyuan-0.5B-Instruct-Q2_K_L.gguf b/tencent_Hunyuan-0.5B-Instruct-Q2_K_L.gguf new file mode 100644 index 0000000..85968eb --- /dev/null +++ b/tencent_Hunyuan-0.5B-Instruct-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca6cda4237f02d0d89b95770f08f7b4760f3a5d0dab8c43043ca2f3596102384 +size 289627584 diff --git a/tencent_Hunyuan-0.5B-Instruct-Q3_K_L.gguf b/tencent_Hunyuan-0.5B-Instruct-Q3_K_L.gguf new file mode 100644 index 0000000..f0c2a56 --- /dev/null +++ b/tencent_Hunyuan-0.5B-Instruct-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ccf91cb1cf68aafc6b97e797001cde48f04c7f94403bda8f33160c3dc7e76e7 +size 327396192 diff --git a/tencent_Hunyuan-0.5B-Instruct-Q3_K_M.gguf b/tencent_Hunyuan-0.5B-Instruct-Q3_K_M.gguf new file mode 100644 index 0000000..5741116 --- /dev/null +++ b/tencent_Hunyuan-0.5B-Instruct-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:883b6f8479ecc805384e72071311e612b6269dd5403bf1c3b7d9a079625824a7 +size 307669856 diff --git a/tencent_Hunyuan-0.5B-Instruct-Q3_K_S.gguf b/tencent_Hunyuan-0.5B-Instruct-Q3_K_S.gguf new file mode 100644 index 0000000..7b04b7c --- /dev/null +++ b/tencent_Hunyuan-0.5B-Instruct-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55c8e65f77ca1bedda5c7f50496b6eee96022522a172aa4e11fcb3b2f5f09048 +size 285223776 diff --git a/tencent_Hunyuan-0.5B-Instruct-Q3_K_XL.gguf b/tencent_Hunyuan-0.5B-Instruct-Q3_K_XL.gguf new file mode 100644 index 0000000..d1566e2 --- /dev/null +++ b/tencent_Hunyuan-0.5B-Instruct-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b95c029ca9bf075dbd86c2e1e126cc93e8f591c13047b521327b0b79a3bff73 +size 357359040 diff --git a/tencent_Hunyuan-0.5B-Instruct-Q4_0.gguf b/tencent_Hunyuan-0.5B-Instruct-Q4_0.gguf new file mode 100644 index 0000000..89d1756 --- /dev/null +++ b/tencent_Hunyuan-0.5B-Instruct-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c60e1323d67f82c6d65e79454dc4ecd0f5891da38d7becd3146648ac01550234 +size 341060448 diff --git a/tencent_Hunyuan-0.5B-Instruct-Q4_1.gguf b/tencent_Hunyuan-0.5B-Instruct-Q4_1.gguf new file mode 100644 index 0000000..f8e5ac2 --- /dev/null +++ b/tencent_Hunyuan-0.5B-Instruct-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f51416e144acc04b0f517c0e8843ff824a3b93197863eb062f2134647ce83fe8 +size 366324576 diff --git a/tencent_Hunyuan-0.5B-Instruct-Q4_K_L.gguf b/tencent_Hunyuan-0.5B-Instruct-Q4_K_L.gguf new file mode 100644 index 0000000..980e473 --- /dev/null +++ b/tencent_Hunyuan-0.5B-Instruct-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ffcae5840a66376a30d8bf839d5fc066e6349904a1e283e0fc1dcead98c1e64 +size 384933312 diff --git a/tencent_Hunyuan-0.5B-Instruct-Q4_K_M.gguf b/tencent_Hunyuan-0.5B-Instruct-Q4_K_M.gguf new file mode 100644 index 0000000..d8cf672 --- /dev/null +++ b/tencent_Hunyuan-0.5B-Instruct-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0820d20c5fb0e4d5e1b9ec660aae6996676280486c9dae17475708efe60b3f2d +size 354970464 diff --git a/tencent_Hunyuan-0.5B-Instruct-Q4_K_S.gguf b/tencent_Hunyuan-0.5B-Instruct-Q4_K_S.gguf new file mode 100644 index 0000000..a5beab1 --- /dev/null +++ b/tencent_Hunyuan-0.5B-Instruct-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7d83c793ae4a4743e1847304bb77f3a89d279cc64f43c86b66a394e94aab5d8 +size 342272864 diff --git a/tencent_Hunyuan-0.5B-Instruct-Q5_K_L.gguf b/tencent_Hunyuan-0.5B-Instruct-Q5_K_L.gguf new file mode 100644 index 0000000..70f6039 --- /dev/null +++ b/tencent_Hunyuan-0.5B-Instruct-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:546290115c1f40dfb0c568e651b89c7c2dfb27e713149676725b86b3a16c40eb +size 429759936 diff --git a/tencent_Hunyuan-0.5B-Instruct-Q5_K_M.gguf b/tencent_Hunyuan-0.5B-Instruct-Q5_K_M.gguf new file mode 100644 index 0000000..1bfef58 --- /dev/null +++ b/tencent_Hunyuan-0.5B-Instruct-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:932a6a4c572d646bf2cc9189d8733237a1412270580002a87bb9b8a602f89efb +size 399797088 diff --git a/tencent_Hunyuan-0.5B-Instruct-Q5_K_S.gguf b/tencent_Hunyuan-0.5B-Instruct-Q5_K_S.gguf new file mode 100644 index 0000000..396fe2c --- /dev/null +++ b/tencent_Hunyuan-0.5B-Instruct-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25c460e74192b6cedba166a1319b272545972ca9c8aec3f2447d160563561e69 +size 392276832 diff --git a/tencent_Hunyuan-0.5B-Instruct-Q6_K.gguf b/tencent_Hunyuan-0.5B-Instruct-Q6_K.gguf new file mode 100644 index 0000000..5c95be0 --- /dev/null +++ b/tencent_Hunyuan-0.5B-Instruct-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1941645c76ceb6974a2e37c2c6a8f85bcdd8a8ab9187679137d3daa37a70b8e +size 447425376 diff --git a/tencent_Hunyuan-0.5B-Instruct-Q6_K_L.gguf b/tencent_Hunyuan-0.5B-Instruct-Q6_K_L.gguf new file mode 100644 index 0000000..1126658 --- /dev/null +++ b/tencent_Hunyuan-0.5B-Instruct-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5500225832f0b2b22762ab2431cec934482b3670a6617d72c364ce471f0f95e9 +size 477388224 diff --git a/tencent_Hunyuan-0.5B-Instruct-Q8_0.gguf b/tencent_Hunyuan-0.5B-Instruct-Q8_0.gguf new file mode 100644 index 0000000..ebc614e --- /dev/null +++ b/tencent_Hunyuan-0.5B-Instruct-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:802e93eb14c3d01b926ff3944a775a1968ff7c039c2ab734dad9ba1b40d0cb9a +size 577953216 diff --git a/tencent_Hunyuan-0.5B-Instruct-bf16.gguf b/tencent_Hunyuan-0.5B-Instruct-bf16.gguf new file mode 100644 index 0000000..35a3052 --- /dev/null +++ b/tencent_Hunyuan-0.5B-Instruct-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04a2bc70f10a83b6d264e4d43e957138396e42d8e7659494e0afbb1d632f7b23 +size 1083222048 diff --git a/tencent_Hunyuan-0.5B-Instruct-imatrix.gguf b/tencent_Hunyuan-0.5B-Instruct-imatrix.gguf new file mode 100644 index 0000000..a8b25b3 --- /dev/null +++ b/tencent_Hunyuan-0.5B-Instruct-imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a46d1f1db2c8c75664e87bfcc26569c48f7bc7fade11a91dad3e0449626c5036 +size 1058080