commit 21a1e8740a5d8b3a997d4204b47efeda5c27428c Author: ModelHub XC Date: Sat Jul 18 08:36:06 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/baidu_ERNIE-4.5-0.3B-PT-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..b38478a --- /dev/null +++ b/README.md @@ -0,0 +1,170 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +base_model: baidu/ERNIE-4.5-0.3B-PT +base_model_relation: quantized +license: apache-2.0 +language: +- en +- zh +tags: +- ERNIE4.5 +--- + +## Llamacpp imatrix Quantizations of ERNIE-4.5-0.3B-PT by baidu + +Using llama.cpp release b5780 for quantization. + +Original model: https://huggingface.co/baidu/ERNIE-4.5-0.3B-PT + +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 + +No prompt format found, check original model page + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [ERNIE-4.5-0.3B-PT-bf16.gguf](https://huggingface.co/bartowski/baidu_ERNIE-4.5-0.3B-PT-GGUF/blob/main/baidu_ERNIE-4.5-0.3B-PT-bf16.gguf) | bf16 | 0.72GB | false | Full BF16 weights. | +| [ERNIE-4.5-0.3B-PT-Q8_0.gguf](https://huggingface.co/bartowski/baidu_ERNIE-4.5-0.3B-PT-GGUF/blob/main/baidu_ERNIE-4.5-0.3B-PT-Q8_0.gguf) | Q8_0 | 0.39GB | false | Extremely high quality, generally unneeded but max available quant. | +| [ERNIE-4.5-0.3B-PT-Q6_K_L.gguf](https://huggingface.co/bartowski/baidu_ERNIE-4.5-0.3B-PT-GGUF/blob/main/baidu_ERNIE-4.5-0.3B-PT-Q6_K_L.gguf) | Q6_K_L | 0.32GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [ERNIE-4.5-0.3B-PT-Q6_K.gguf](https://huggingface.co/bartowski/baidu_ERNIE-4.5-0.3B-PT-GGUF/blob/main/baidu_ERNIE-4.5-0.3B-PT-Q6_K.gguf) | Q6_K | 0.30GB | false | Very high quality, near perfect, *recommended*. | +| [ERNIE-4.5-0.3B-PT-Q5_K_L.gguf](https://huggingface.co/bartowski/baidu_ERNIE-4.5-0.3B-PT-GGUF/blob/main/baidu_ERNIE-4.5-0.3B-PT-Q5_K_L.gguf) | Q5_K_L | 0.29GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [ERNIE-4.5-0.3B-PT-Q5_K_M.gguf](https://huggingface.co/bartowski/baidu_ERNIE-4.5-0.3B-PT-GGUF/blob/main/baidu_ERNIE-4.5-0.3B-PT-Q5_K_M.gguf) | Q5_K_M | 0.27GB | false | High quality, *recommended*. | +| [ERNIE-4.5-0.3B-PT-Q4_K_L.gguf](https://huggingface.co/bartowski/baidu_ERNIE-4.5-0.3B-PT-GGUF/blob/main/baidu_ERNIE-4.5-0.3B-PT-Q4_K_L.gguf) | Q4_K_L | 0.27GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [ERNIE-4.5-0.3B-PT-Q5_K_S.gguf](https://huggingface.co/bartowski/baidu_ERNIE-4.5-0.3B-PT-GGUF/blob/main/baidu_ERNIE-4.5-0.3B-PT-Q5_K_S.gguf) | Q5_K_S | 0.26GB | false | High quality, *recommended*. | +| [ERNIE-4.5-0.3B-PT-Q4_1.gguf](https://huggingface.co/bartowski/baidu_ERNIE-4.5-0.3B-PT-GGUF/blob/main/baidu_ERNIE-4.5-0.3B-PT-Q4_1.gguf) | Q4_1 | 0.25GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [ERNIE-4.5-0.3B-PT-Q3_K_XL.gguf](https://huggingface.co/bartowski/baidu_ERNIE-4.5-0.3B-PT-GGUF/blob/main/baidu_ERNIE-4.5-0.3B-PT-Q3_K_XL.gguf) | Q3_K_XL | 0.25GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [ERNIE-4.5-0.3B-PT-Q4_K_M.gguf](https://huggingface.co/bartowski/baidu_ERNIE-4.5-0.3B-PT-GGUF/blob/main/baidu_ERNIE-4.5-0.3B-PT-Q4_K_M.gguf) | Q4_K_M | 0.24GB | false | Good quality, default size for most use cases, *recommended*. | +| [ERNIE-4.5-0.3B-PT-Q4_K_S.gguf](https://huggingface.co/bartowski/baidu_ERNIE-4.5-0.3B-PT-GGUF/blob/main/baidu_ERNIE-4.5-0.3B-PT-Q4_K_S.gguf) | Q4_K_S | 0.23GB | false | Slightly lower quality with more space savings, *recommended*. | +| [ERNIE-4.5-0.3B-PT-Q4_0.gguf](https://huggingface.co/bartowski/baidu_ERNIE-4.5-0.3B-PT-GGUF/blob/main/baidu_ERNIE-4.5-0.3B-PT-Q4_0.gguf) | Q4_0 | 0.23GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [ERNIE-4.5-0.3B-PT-IQ4_NL.gguf](https://huggingface.co/bartowski/baidu_ERNIE-4.5-0.3B-PT-GGUF/blob/main/baidu_ERNIE-4.5-0.3B-PT-IQ4_NL.gguf) | IQ4_NL | 0.23GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [ERNIE-4.5-0.3B-PT-IQ4_XS.gguf](https://huggingface.co/bartowski/baidu_ERNIE-4.5-0.3B-PT-GGUF/blob/main/baidu_ERNIE-4.5-0.3B-PT-IQ4_XS.gguf) | IQ4_XS | 0.23GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [ERNIE-4.5-0.3B-PT-Q3_K_L.gguf](https://huggingface.co/bartowski/baidu_ERNIE-4.5-0.3B-PT-GGUF/blob/main/baidu_ERNIE-4.5-0.3B-PT-Q3_K_L.gguf) | Q3_K_L | 0.22GB | false | Lower quality but usable, good for low RAM availability. | +| [ERNIE-4.5-0.3B-PT-Q3_K_M.gguf](https://huggingface.co/bartowski/baidu_ERNIE-4.5-0.3B-PT-GGUF/blob/main/baidu_ERNIE-4.5-0.3B-PT-Q3_K_M.gguf) | Q3_K_M | 0.21GB | false | Low quality. | +| [ERNIE-4.5-0.3B-PT-IQ3_M.gguf](https://huggingface.co/bartowski/baidu_ERNIE-4.5-0.3B-PT-GGUF/blob/main/baidu_ERNIE-4.5-0.3B-PT-IQ3_M.gguf) | IQ3_M | 0.21GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [ERNIE-4.5-0.3B-PT-Q2_K_L.gguf](https://huggingface.co/bartowski/baidu_ERNIE-4.5-0.3B-PT-GGUF/blob/main/baidu_ERNIE-4.5-0.3B-PT-Q2_K_L.gguf) | Q2_K_L | 0.21GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [ERNIE-4.5-0.3B-PT-Q3_K_S.gguf](https://huggingface.co/bartowski/baidu_ERNIE-4.5-0.3B-PT-GGUF/blob/main/baidu_ERNIE-4.5-0.3B-PT-Q3_K_S.gguf) | Q3_K_S | 0.20GB | false | Low quality, not recommended. | +| [ERNIE-4.5-0.3B-PT-IQ3_XS.gguf](https://huggingface.co/bartowski/baidu_ERNIE-4.5-0.3B-PT-GGUF/blob/main/baidu_ERNIE-4.5-0.3B-PT-IQ3_XS.gguf) | IQ3_XS | 0.19GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [ERNIE-4.5-0.3B-PT-Q2_K.gguf](https://huggingface.co/bartowski/baidu_ERNIE-4.5-0.3B-PT-GGUF/blob/main/baidu_ERNIE-4.5-0.3B-PT-Q2_K.gguf) | Q2_K | 0.18GB | false | Very low quality but surprisingly usable. | +| [ERNIE-4.5-0.3B-PT-IQ3_XXS.gguf](https://huggingface.co/bartowski/baidu_ERNIE-4.5-0.3B-PT-GGUF/blob/main/baidu_ERNIE-4.5-0.3B-PT-IQ3_XXS.gguf) | IQ3_XXS | 0.17GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [ERNIE-4.5-0.3B-PT-IQ2_M.gguf](https://huggingface.co/bartowski/baidu_ERNIE-4.5-0.3B-PT-GGUF/blob/main/baidu_ERNIE-4.5-0.3B-PT-IQ2_M.gguf) | IQ2_M | 0.16GB | 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/baidu_ERNIE-4.5-0.3B-PT-GGUF --include "baidu_ERNIE-4.5-0.3B-PT-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/baidu_ERNIE-4.5-0.3B-PT-GGUF --include "baidu_ERNIE-4.5-0.3B-PT-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (baidu_ERNIE-4.5-0.3B-PT-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/baidu_ERNIE-4.5-0.3B-PT-IQ2_M.gguf b/baidu_ERNIE-4.5-0.3B-PT-IQ2_M.gguf new file mode 100644 index 0000000..29dc70c --- /dev/null +++ b/baidu_ERNIE-4.5-0.3B-PT-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ecf95f233b4759c425a53a842837807f63f715021b7bf2e522d02de1f8bc183 +size 162921792 diff --git a/baidu_ERNIE-4.5-0.3B-PT-IQ3_M.gguf b/baidu_ERNIE-4.5-0.3B-PT-IQ3_M.gguf new file mode 100644 index 0000000..6ed93b0 --- /dev/null +++ b/baidu_ERNIE-4.5-0.3B-PT-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaba77400a2d306401ebb6ff3971cff39a8b9891b2fc2bc223b211328a3fe475 +size 205372736 diff --git a/baidu_ERNIE-4.5-0.3B-PT-IQ3_XS.gguf b/baidu_ERNIE-4.5-0.3B-PT-IQ3_XS.gguf new file mode 100644 index 0000000..4b54fac --- /dev/null +++ b/baidu_ERNIE-4.5-0.3B-PT-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f61cbfde659667a604c790c9c904069f3c851020b26bf2a513d5324eff6736a +size 193699136 diff --git a/baidu_ERNIE-4.5-0.3B-PT-IQ3_XXS.gguf b/baidu_ERNIE-4.5-0.3B-PT-IQ3_XXS.gguf new file mode 100644 index 0000000..83496ea --- /dev/null +++ b/baidu_ERNIE-4.5-0.3B-PT-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95fc76a4f5bf18649eff631ae71008f2f9a7a9c56954297f43b0bb9551870b79 +size 172850496 diff --git a/baidu_ERNIE-4.5-0.3B-PT-IQ4_NL.gguf b/baidu_ERNIE-4.5-0.3B-PT-IQ4_NL.gguf new file mode 100644 index 0000000..8f75519 --- /dev/null +++ b/baidu_ERNIE-4.5-0.3B-PT-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:562b77fb7934a5cee86511241641d53d90bb881ef13366f780e26aba47418962 +size 233327936 diff --git a/baidu_ERNIE-4.5-0.3B-PT-IQ4_XS.gguf b/baidu_ERNIE-4.5-0.3B-PT-IQ4_XS.gguf new file mode 100644 index 0000000..6cccb9f --- /dev/null +++ b/baidu_ERNIE-4.5-0.3B-PT-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a519dc523a06d18281ef1669cdc33bfc36c803ea1a9ac44978a9bba91bec318 +size 225512768 diff --git a/baidu_ERNIE-4.5-0.3B-PT-Q2_K.gguf b/baidu_ERNIE-4.5-0.3B-PT-Q2_K.gguf new file mode 100644 index 0000000..82b5dcb --- /dev/null +++ b/baidu_ERNIE-4.5-0.3B-PT-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bf2a5285f05d842d33933e94734f4a86d6374ec608117567a4a94b5e49252eb +size 183708992 diff --git a/baidu_ERNIE-4.5-0.3B-PT-Q2_K_L.gguf b/baidu_ERNIE-4.5-0.3B-PT-Q2_K_L.gguf new file mode 100644 index 0000000..53fd472 --- /dev/null +++ b/baidu_ERNIE-4.5-0.3B-PT-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74db7731d046c20061d981b2a228f8568ed1243e9308d494f8b16d48002fb743 +size 209358144 diff --git a/baidu_ERNIE-4.5-0.3B-PT-Q3_K_L.gguf b/baidu_ERNIE-4.5-0.3B-PT-Q3_K_L.gguf new file mode 100644 index 0000000..d3e51d7 --- /dev/null +++ b/baidu_ERNIE-4.5-0.3B-PT-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2f8c86feef6881b8efd79646e4e10980ccc5522290e303d9c695dde6246f9f6 +size 224443712 diff --git a/baidu_ERNIE-4.5-0.3B-PT-Q3_K_M.gguf b/baidu_ERNIE-4.5-0.3B-PT-Q3_K_M.gguf new file mode 100644 index 0000000..696b7ff --- /dev/null +++ b/baidu_ERNIE-4.5-0.3B-PT-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11be02af050d9e97f34705676b11975baebd27a5ba1a16f8138f01b49154e04d +size 212516160 diff --git a/baidu_ERNIE-4.5-0.3B-PT-Q3_K_S.gguf b/baidu_ERNIE-4.5-0.3B-PT-Q3_K_S.gguf new file mode 100644 index 0000000..65ec2b2 --- /dev/null +++ b/baidu_ERNIE-4.5-0.3B-PT-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bf6f07f5dcbfb7211cd929933a0fbf311a2fea5a9d008ee84cc4a355f71a2bb +size 198896960 diff --git a/baidu_ERNIE-4.5-0.3B-PT-Q3_K_XL.gguf b/baidu_ERNIE-4.5-0.3B-PT-Q3_K_XL.gguf new file mode 100644 index 0000000..d92d96c --- /dev/null +++ b/baidu_ERNIE-4.5-0.3B-PT-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf94b694b93d694cca8762e5a31ffb84f156190a500e3a00925809a83dad3563 +size 250092864 diff --git a/baidu_ERNIE-4.5-0.3B-PT-Q4_0.gguf b/baidu_ERNIE-4.5-0.3B-PT-Q4_0.gguf new file mode 100644 index 0000000..50f76eb --- /dev/null +++ b/baidu_ERNIE-4.5-0.3B-PT-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bf8b8beba6490eebcf3166527251dffc584e9675d140d2d6ec075ec3f1a096e +size 233131328 diff --git a/baidu_ERNIE-4.5-0.3B-PT-Q4_1.gguf b/baidu_ERNIE-4.5-0.3B-PT-Q4_1.gguf new file mode 100644 index 0000000..a57366d --- /dev/null +++ b/baidu_ERNIE-4.5-0.3B-PT-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7618d0072882d466ccba1edf487b8d5ead48a6a1a476a6c04a26741a9eadea1 +size 248663360 diff --git a/baidu_ERNIE-4.5-0.3B-PT-Q4_K_L.gguf b/baidu_ERNIE-4.5-0.3B-PT-Q4_K_L.gguf new file mode 100644 index 0000000..aa3bc00 --- /dev/null +++ b/baidu_ERNIE-4.5-0.3B-PT-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a54b13f493285dd20f4c0362bb105426403ec6e4073eaff437e9e172d76ff67 +size 266294592 diff --git a/baidu_ERNIE-4.5-0.3B-PT-Q4_K_M.gguf b/baidu_ERNIE-4.5-0.3B-PT-Q4_K_M.gguf new file mode 100644 index 0000000..8b409ab --- /dev/null +++ b/baidu_ERNIE-4.5-0.3B-PT-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e0da893e699ea83712e427bba797da04dbad1e614950f16f60143eb25ebb368 +size 240645440 diff --git a/baidu_ERNIE-4.5-0.3B-PT-Q4_K_S.gguf b/baidu_ERNIE-4.5-0.3B-PT-Q4_K_S.gguf new file mode 100644 index 0000000..68a1702 --- /dev/null +++ b/baidu_ERNIE-4.5-0.3B-PT-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad637c12885b8dc7c6034fe9e398e06e10f8bcb668593bf594d4005ad449a1f6 +size 233655616 diff --git a/baidu_ERNIE-4.5-0.3B-PT-Q5_K_L.gguf b/baidu_ERNIE-4.5-0.3B-PT-Q5_K_L.gguf new file mode 100644 index 0000000..de64432 --- /dev/null +++ b/baidu_ERNIE-4.5-0.3B-PT-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9215311bda3c72424dc041c7da505859b4781e411d76a2b268c52cf7c7a0ab85 +size 294311232 diff --git a/baidu_ERNIE-4.5-0.3B-PT-Q5_K_M.gguf b/baidu_ERNIE-4.5-0.3B-PT-Q5_K_M.gguf new file mode 100644 index 0000000..a6eda5d --- /dev/null +++ b/baidu_ERNIE-4.5-0.3B-PT-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f90033a8b48e5ae4e37b4e8264192b75d6c4012762748dbef36845f9a3656cd +size 268662080 diff --git a/baidu_ERNIE-4.5-0.3B-PT-Q5_K_S.gguf b/baidu_ERNIE-4.5-0.3B-PT-Q5_K_S.gguf new file mode 100644 index 0000000..51de815 --- /dev/null +++ b/baidu_ERNIE-4.5-0.3B-PT-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:419cd2554f54ab9c4e24b970d642a7850490992eeb0c0761f95ec64e99c184b1 +size 264588608 diff --git a/baidu_ERNIE-4.5-0.3B-PT-Q6_K.gguf b/baidu_ERNIE-4.5-0.3B-PT-Q6_K.gguf new file mode 100644 index 0000000..9dc4840 --- /dev/null +++ b/baidu_ERNIE-4.5-0.3B-PT-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:408b184c75806c1a0eeab865350fc71c2b98a41e6cf0b50ca74d65786737bf5c +size 298429760 diff --git a/baidu_ERNIE-4.5-0.3B-PT-Q6_K_L.gguf b/baidu_ERNIE-4.5-0.3B-PT-Q6_K_L.gguf new file mode 100644 index 0000000..7693139 --- /dev/null +++ b/baidu_ERNIE-4.5-0.3B-PT-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb0fcec15eae1029339fd3049ff12dc7779c296c4a44a7375e64dd6d21c1f523 +size 324078912 diff --git a/baidu_ERNIE-4.5-0.3B-PT-Q8_0.gguf b/baidu_ERNIE-4.5-0.3B-PT-Q8_0.gguf new file mode 100644 index 0000000..3be79fc --- /dev/null +++ b/baidu_ERNIE-4.5-0.3B-PT-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:022ce1cfc46a2818a96b8a683aec0944047cac6745f35aa5a2a48729a58caa74 +size 385789248 diff --git a/baidu_ERNIE-4.5-0.3B-PT-bf16.gguf b/baidu_ERNIE-4.5-0.3B-PT-bf16.gguf new file mode 100644 index 0000000..044d9e6 --- /dev/null +++ b/baidu_ERNIE-4.5-0.3B-PT-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14ab719827deb4670b3a17b16d8aaa3a16a0eb5ad410e7181c14302b98e12c28 +size 723954720 diff --git a/baidu_ERNIE-4.5-0.3B-PT.imatrix b/baidu_ERNIE-4.5-0.3B-PT.imatrix new file mode 100644 index 0000000..705181d Binary files /dev/null and b/baidu_ERNIE-4.5-0.3B-PT.imatrix differ 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