commit 148adef32b2074ec31b6c30975b94370fb05ef27 Author: ModelHub XC Date: Tue Jul 21 19:52:06 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/tencent_Hunyuan-7B-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..332aba5 --- /dev/null +++ b/README.md @@ -0,0 +1,166 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +base_model_relation: quantized +base_model: tencent/Hunyuan-7B-Instruct +--- + +## Llamacpp imatrix Quantizations of Hunyuan-7B-Instruct by tencent + +Using llama.cpp release b6076 for quantization. + +Original model: https://huggingface.co/tencent/Hunyuan-7B-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 + +``` +<|startoftext|>{system_prompt}<|extra_4|>{prompt}<|extra_0|><|eos|><|extra_0|> +``` + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [Hunyuan-7B-Instruct-bf16.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-7B-Instruct-GGUF/blob/main/tencent_Hunyuan-7B-Instruct-bf16.gguf) | bf16 | 15.01GB | false | Full BF16 weights. | +| [Hunyuan-7B-Instruct-Q8_0.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-7B-Instruct-GGUF/blob/main/tencent_Hunyuan-7B-Instruct-Q8_0.gguf) | Q8_0 | 7.98GB | false | Extremely high quality, generally unneeded but max available quant. | +| [Hunyuan-7B-Instruct-Q6_K_L.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-7B-Instruct-GGUF/blob/main/tencent_Hunyuan-7B-Instruct-Q6_K_L.gguf) | Q6_K_L | 6.29GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [Hunyuan-7B-Instruct-Q6_K.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-7B-Instruct-GGUF/blob/main/tencent_Hunyuan-7B-Instruct-Q6_K.gguf) | Q6_K | 6.16GB | false | Very high quality, near perfect, *recommended*. | +| [Hunyuan-7B-Instruct-Q5_K_L.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-7B-Instruct-GGUF/blob/main/tencent_Hunyuan-7B-Instruct-Q5_K_L.gguf) | Q5_K_L | 5.50GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [Hunyuan-7B-Instruct-Q5_K_M.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-7B-Instruct-GGUF/blob/main/tencent_Hunyuan-7B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5.37GB | false | High quality, *recommended*. | +| [Hunyuan-7B-Instruct-Q5_K_S.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-7B-Instruct-GGUF/blob/main/tencent_Hunyuan-7B-Instruct-Q5_K_S.gguf) | Q5_K_S | 5.23GB | false | High quality, *recommended*. | +| [Hunyuan-7B-Instruct-Q4_1.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-7B-Instruct-GGUF/blob/main/tencent_Hunyuan-7B-Instruct-Q4_1.gguf) | Q4_1 | 4.80GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [Hunyuan-7B-Instruct-Q4_K_L.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-7B-Instruct-GGUF/blob/main/tencent_Hunyuan-7B-Instruct-Q4_K_L.gguf) | Q4_K_L | 4.75GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [Hunyuan-7B-Instruct-Q4_K_M.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-7B-Instruct-GGUF/blob/main/tencent_Hunyuan-7B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4.62GB | false | Good quality, default size for most use cases, *recommended*. | +| [Hunyuan-7B-Instruct-Q4_K_S.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-7B-Instruct-GGUF/blob/main/tencent_Hunyuan-7B-Instruct-Q4_K_S.gguf) | Q4_K_S | 4.39GB | false | Slightly lower quality with more space savings, *recommended*. | +| [Hunyuan-7B-Instruct-Q4_0.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-7B-Instruct-GGUF/blob/main/tencent_Hunyuan-7B-Instruct-Q4_0.gguf) | Q4_0 | 4.38GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [Hunyuan-7B-Instruct-IQ4_NL.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-7B-Instruct-GGUF/blob/main/tencent_Hunyuan-7B-Instruct-IQ4_NL.gguf) | IQ4_NL | 4.38GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [Hunyuan-7B-Instruct-Q3_K_XL.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-7B-Instruct-GGUF/blob/main/tencent_Hunyuan-7B-Instruct-Q3_K_XL.gguf) | Q3_K_XL | 4.22GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [Hunyuan-7B-Instruct-IQ4_XS.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-7B-Instruct-GGUF/blob/main/tencent_Hunyuan-7B-Instruct-IQ4_XS.gguf) | IQ4_XS | 4.17GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Hunyuan-7B-Instruct-Q3_K_L.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-7B-Instruct-GGUF/blob/main/tencent_Hunyuan-7B-Instruct-Q3_K_L.gguf) | Q3_K_L | 4.09GB | false | Lower quality but usable, good for low RAM availability. | +| [Hunyuan-7B-Instruct-Q3_K_M.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-7B-Instruct-GGUF/blob/main/tencent_Hunyuan-7B-Instruct-Q3_K_M.gguf) | Q3_K_M | 3.79GB | false | Low quality. | +| [Hunyuan-7B-Instruct-IQ3_M.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-7B-Instruct-GGUF/blob/main/tencent_Hunyuan-7B-Instruct-IQ3_M.gguf) | IQ3_M | 3.56GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [Hunyuan-7B-Instruct-Q3_K_S.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-7B-Instruct-GGUF/blob/main/tencent_Hunyuan-7B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3.44GB | false | Low quality, not recommended. | +| [Hunyuan-7B-Instruct-IQ3_XS.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-7B-Instruct-GGUF/blob/main/tencent_Hunyuan-7B-Instruct-IQ3_XS.gguf) | IQ3_XS | 3.29GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [Hunyuan-7B-Instruct-Q2_K_L.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-7B-Instruct-GGUF/blob/main/tencent_Hunyuan-7B-Instruct-Q2_K_L.gguf) | Q2_K_L | 3.13GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [Hunyuan-7B-Instruct-IQ3_XXS.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-7B-Instruct-GGUF/blob/main/tencent_Hunyuan-7B-Instruct-IQ3_XXS.gguf) | IQ3_XXS | 3.05GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [Hunyuan-7B-Instruct-Q2_K.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-7B-Instruct-GGUF/blob/main/tencent_Hunyuan-7B-Instruct-Q2_K.gguf) | Q2_K | 3.00GB | false | Very low quality but surprisingly usable. | +| [Hunyuan-7B-Instruct-IQ2_M.gguf](https://huggingface.co/bartowski/tencent_Hunyuan-7B-Instruct-GGUF/blob/main/tencent_Hunyuan-7B-Instruct-IQ2_M.gguf) | IQ2_M | 2.72GB | 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-7B-Instruct-GGUF --include "tencent_Hunyuan-7B-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-7B-Instruct-GGUF --include "tencent_Hunyuan-7B-Instruct-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (tencent_Hunyuan-7B-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-7B-Instruct-IQ2_M.gguf b/tencent_Hunyuan-7B-Instruct-IQ2_M.gguf new file mode 100644 index 0000000..708f364 --- /dev/null +++ b/tencent_Hunyuan-7B-Instruct-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30e48d3f9ba2343e239bac4179fceb21420cad4740d68420f390afd59bca56ce +size 2719359264 diff --git a/tencent_Hunyuan-7B-Instruct-IQ3_M.gguf b/tencent_Hunyuan-7B-Instruct-IQ3_M.gguf new file mode 100644 index 0000000..9ab160c --- /dev/null +++ b/tencent_Hunyuan-7B-Instruct-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b83c7ab828df908de624567af631c8a4db0b5acb84d7cab56e9871579efb8013 +size 3555853312 diff --git a/tencent_Hunyuan-7B-Instruct-IQ3_XS.gguf b/tencent_Hunyuan-7B-Instruct-IQ3_XS.gguf new file mode 100644 index 0000000..7dacf0b --- /dev/null +++ b/tencent_Hunyuan-7B-Instruct-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2be35d983723441e2f5692f06794b915029684a4a6a11ed008cb369d9a771cdd +size 3289777152 diff --git a/tencent_Hunyuan-7B-Instruct-IQ3_XXS.gguf b/tencent_Hunyuan-7B-Instruct-IQ3_XXS.gguf new file mode 100644 index 0000000..008fa10 --- /dev/null +++ b/tencent_Hunyuan-7B-Instruct-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42cd5528d789bf252fa93b9f7866c9708df816ffc93612b2a6f1d6e11efe1322 +size 3045990688 diff --git a/tencent_Hunyuan-7B-Instruct-IQ4_NL.gguf b/tencent_Hunyuan-7B-Instruct-IQ4_NL.gguf new file mode 100644 index 0000000..c71c9f2 --- /dev/null +++ b/tencent_Hunyuan-7B-Instruct-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90d4ef6404356f3a7e0c0fcdf523c0b8105bb7e5646a1118b3f598ee107de4ef +size 4379247616 diff --git a/tencent_Hunyuan-7B-Instruct-IQ4_XS.gguf b/tencent_Hunyuan-7B-Instruct-IQ4_XS.gguf new file mode 100644 index 0000000..d50899c --- /dev/null +++ b/tencent_Hunyuan-7B-Instruct-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ebad9f23d8bbf7ac3af4e18b0b3022b17284d967a725c3b9b3ebc133f686e08 +size 4165338112 diff --git a/tencent_Hunyuan-7B-Instruct-Q2_K.gguf b/tencent_Hunyuan-7B-Instruct-Q2_K.gguf new file mode 100644 index 0000000..fa53637 --- /dev/null +++ b/tencent_Hunyuan-7B-Instruct-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea9921f4107e708ec7ae60182ca31214a4d468d9445743512983ff14990a550f +size 3003515904 diff --git a/tencent_Hunyuan-7B-Instruct-Q2_K_L.gguf b/tencent_Hunyuan-7B-Instruct-Q2_K_L.gguf new file mode 100644 index 0000000..4431670 --- /dev/null +++ b/tencent_Hunyuan-7B-Instruct-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0057ad02fb7140899b58af7162b71e5b2d8afb6dbe2e209ad92b620606e73af9 +size 3130657568 diff --git a/tencent_Hunyuan-7B-Instruct-Q3_K_L.gguf b/tencent_Hunyuan-7B-Instruct-Q3_K_L.gguf new file mode 100644 index 0000000..3f3adfc --- /dev/null +++ b/tencent_Hunyuan-7B-Instruct-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09b13843a066ce7839aa524218063b718cb9e2cbeb9b98cc0a6edb6d6bf23bad +size 4092986368 diff --git a/tencent_Hunyuan-7B-Instruct-Q3_K_M.gguf b/tencent_Hunyuan-7B-Instruct-Q3_K_M.gguf new file mode 100644 index 0000000..939768c --- /dev/null +++ b/tencent_Hunyuan-7B-Instruct-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50984a7f343f492776bc4900380021785d33b8c7baeb5bf98beb46ef27f4ee87 +size 3789947904 diff --git a/tencent_Hunyuan-7B-Instruct-Q3_K_S.gguf b/tencent_Hunyuan-7B-Instruct-Q3_K_S.gguf new file mode 100644 index 0000000..6fd6e13 --- /dev/null +++ b/tencent_Hunyuan-7B-Instruct-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:112d1813d17f29f7786e8bd181f7fb77756cf0494388586bec6d91e967cc72d4 +size 3435529216 diff --git a/tencent_Hunyuan-7B-Instruct-Q3_K_XL.gguf b/tencent_Hunyuan-7B-Instruct-Q3_K_XL.gguf new file mode 100644 index 0000000..4dd9b86 --- /dev/null +++ b/tencent_Hunyuan-7B-Instruct-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a160e4d540eba08d7d34980619df79e26fbbc493184e79beec4294c2bfae35a3 +size 4220128032 diff --git a/tencent_Hunyuan-7B-Instruct-Q4_0.gguf b/tencent_Hunyuan-7B-Instruct-Q4_0.gguf new file mode 100644 index 0000000..759d2d0 --- /dev/null +++ b/tencent_Hunyuan-7B-Instruct-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:289187a6ae4ff7482c61bc1d2c165d97cf74ca85d1bb63ce2d9aa46354ef93ac +size 4377150464 diff --git a/tencent_Hunyuan-7B-Instruct-Q4_1.gguf b/tencent_Hunyuan-7B-Instruct-Q4_1.gguf new file mode 100644 index 0000000..c5f1e0e --- /dev/null +++ b/tencent_Hunyuan-7B-Instruct-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:123dcf760de41854e90d52ad823b2208da20b3b67344b329a93b72db878276f8 +size 4798678016 diff --git a/tencent_Hunyuan-7B-Instruct-Q4_K_L.gguf b/tencent_Hunyuan-7B-Instruct-Q4_K_L.gguf new file mode 100644 index 0000000..8a06032 --- /dev/null +++ b/tencent_Hunyuan-7B-Instruct-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3416d123c6464e59a9bd5d92a71b89f6265bf9dc4922b3f2a918d078158a0889 +size 4749134624 diff --git a/tencent_Hunyuan-7B-Instruct-Q4_K_M.gguf b/tencent_Hunyuan-7B-Instruct-Q4_K_M.gguf new file mode 100644 index 0000000..b16195b --- /dev/null +++ b/tencent_Hunyuan-7B-Instruct-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37361ed44b126de00a551260fd7c3de3c3a7a58d6060bce99b6b8fe0c0665d63 +size 4621992960 diff --git a/tencent_Hunyuan-7B-Instruct-Q4_K_S.gguf b/tencent_Hunyuan-7B-Instruct-Q4_K_S.gguf new file mode 100644 index 0000000..d0e9f56 --- /dev/null +++ b/tencent_Hunyuan-7B-Instruct-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cea88d81a3d0b690e39eda7326c5d992398c496814a6291c471d9b473a5c2312 +size 4393927680 diff --git a/tencent_Hunyuan-7B-Instruct-Q5_K_L.gguf b/tencent_Hunyuan-7B-Instruct-Q5_K_L.gguf new file mode 100644 index 0000000..b2cdd83 --- /dev/null +++ b/tencent_Hunyuan-7B-Instruct-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6a43b537b0d857ce266387020c5ac47868912105c6e016d519de997a21ad797 +size 5495720736 diff --git a/tencent_Hunyuan-7B-Instruct-Q5_K_M.gguf b/tencent_Hunyuan-7B-Instruct-Q5_K_M.gguf new file mode 100644 index 0000000..66efd18 --- /dev/null +++ b/tencent_Hunyuan-7B-Instruct-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb253866770662c79b52238cd76b6682c80c1abedb06c6d22a84ee31949c7e1b +size 5368579072 diff --git a/tencent_Hunyuan-7B-Instruct-Q5_K_S.gguf b/tencent_Hunyuan-7B-Instruct-Q5_K_S.gguf new file mode 100644 index 0000000..4c53416 --- /dev/null +++ b/tencent_Hunyuan-7B-Instruct-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34207625291f3255000b4faa5a8b11a82f860e109374fd83c4255b4aae570f1f +size 5234885632 diff --git a/tencent_Hunyuan-7B-Instruct-Q6_K.gguf b/tencent_Hunyuan-7B-Instruct-Q6_K.gguf new file mode 100644 index 0000000..f16f2b7 --- /dev/null +++ b/tencent_Hunyuan-7B-Instruct-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bd4185982694560988e5f684e0e1d2f0743e6addc002ce12ef1e1a34e962d5c +size 6161826816 diff --git a/tencent_Hunyuan-7B-Instruct-Q6_K_L.gguf b/tencent_Hunyuan-7B-Instruct-Q6_K_L.gguf new file mode 100644 index 0000000..f72ec9b --- /dev/null +++ b/tencent_Hunyuan-7B-Instruct-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21f08d206e48645c091fc99231e8b4a218cdd93103d09049b76115fb2136a275 +size 6288968480 diff --git a/tencent_Hunyuan-7B-Instruct-Q8_0.gguf b/tencent_Hunyuan-7B-Instruct-Q8_0.gguf new file mode 100644 index 0000000..540e9b4 --- /dev/null +++ b/tencent_Hunyuan-7B-Instruct-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:815b1d7a7528d5857c427bcfda08e4919458b7d29787243d58d2eb9dc90d51b7 +size 7979272992 diff --git a/tencent_Hunyuan-7B-Instruct-bf16.gguf b/tencent_Hunyuan-7B-Instruct-bf16.gguf new file mode 100644 index 0000000..bec2c50 --- /dev/null +++ b/tencent_Hunyuan-7B-Instruct-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:401e9be1527797bbbea1af39709684a8d2cf1b5f4b80fae8129bd93db2ce1124 +size 15014548224 diff --git a/tencent_Hunyuan-7B-Instruct-imatrix.gguf b/tencent_Hunyuan-7B-Instruct-imatrix.gguf new file mode 100644 index 0000000..fd2575c --- /dev/null +++ b/tencent_Hunyuan-7B-Instruct-imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1580f854945695e5edc0a5314c061c3846925b5b405c4bfde5b9a3cdf11b460c +size 5015232