commit 6eacfc074d248cb05975b372598395b3857589a7 Author: ModelHub XC Date: Sat Aug 8 21:01:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/SUFE-AIFLM-Lab_Fin-R1-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..9ff684b --- /dev/null +++ b/README.md @@ -0,0 +1,170 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +base_model: SUFE-AIFLM-Lab/Fin-R1 +base_model_relation: quantized +--- + +## Llamacpp imatrix Quantizations of Fin-R1 by SUFE-AIFLM-Lab + +Using llama.cpp release b4944 for quantization. + +Original model: https://huggingface.co/SUFE-AIFLM-Lab/Fin-R1 + +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 + +``` +<|im_start|>system +{system_prompt}<|im_end|> +<|im_start|>user +{prompt}<|im_end|> +<|im_start|>assistant +``` + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [Fin-R1-bf16.gguf](https://huggingface.co/bartowski/SUFE-AIFLM-Lab_Fin-R1-GGUF/blob/main/SUFE-AIFLM-Lab_Fin-R1-bf16.gguf) | bf16 | 15.24GB | false | Full BF16 weights. | +| [Fin-R1-Q8_0.gguf](https://huggingface.co/bartowski/SUFE-AIFLM-Lab_Fin-R1-GGUF/blob/main/SUFE-AIFLM-Lab_Fin-R1-Q8_0.gguf) | Q8_0 | 8.10GB | false | Extremely high quality, generally unneeded but max available quant. | +| [Fin-R1-Q6_K_L.gguf](https://huggingface.co/bartowski/SUFE-AIFLM-Lab_Fin-R1-GGUF/blob/main/SUFE-AIFLM-Lab_Fin-R1-Q6_K_L.gguf) | Q6_K_L | 6.52GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [Fin-R1-Q6_K.gguf](https://huggingface.co/bartowski/SUFE-AIFLM-Lab_Fin-R1-GGUF/blob/main/SUFE-AIFLM-Lab_Fin-R1-Q6_K.gguf) | Q6_K | 6.25GB | false | Very high quality, near perfect, *recommended*. | +| [Fin-R1-Q5_K_L.gguf](https://huggingface.co/bartowski/SUFE-AIFLM-Lab_Fin-R1-GGUF/blob/main/SUFE-AIFLM-Lab_Fin-R1-Q5_K_L.gguf) | Q5_K_L | 5.78GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [Fin-R1-Q5_K_M.gguf](https://huggingface.co/bartowski/SUFE-AIFLM-Lab_Fin-R1-GGUF/blob/main/SUFE-AIFLM-Lab_Fin-R1-Q5_K_M.gguf) | Q5_K_M | 5.44GB | false | High quality, *recommended*. | +| [Fin-R1-Q5_K_S.gguf](https://huggingface.co/bartowski/SUFE-AIFLM-Lab_Fin-R1-GGUF/blob/main/SUFE-AIFLM-Lab_Fin-R1-Q5_K_S.gguf) | Q5_K_S | 5.32GB | false | High quality, *recommended*. | +| [Fin-R1-Q4_K_L.gguf](https://huggingface.co/bartowski/SUFE-AIFLM-Lab_Fin-R1-GGUF/blob/main/SUFE-AIFLM-Lab_Fin-R1-Q4_K_L.gguf) | Q4_K_L | 5.09GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [Fin-R1-Q4_1.gguf](https://huggingface.co/bartowski/SUFE-AIFLM-Lab_Fin-R1-GGUF/blob/main/SUFE-AIFLM-Lab_Fin-R1-Q4_1.gguf) | Q4_1 | 4.87GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [Fin-R1-Q4_K_M.gguf](https://huggingface.co/bartowski/SUFE-AIFLM-Lab_Fin-R1-GGUF/blob/main/SUFE-AIFLM-Lab_Fin-R1-Q4_K_M.gguf) | Q4_K_M | 4.68GB | false | Good quality, default size for most use cases, *recommended*. | +| [Fin-R1-Q3_K_XL.gguf](https://huggingface.co/bartowski/SUFE-AIFLM-Lab_Fin-R1-GGUF/blob/main/SUFE-AIFLM-Lab_Fin-R1-Q3_K_XL.gguf) | Q3_K_XL | 4.57GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [Fin-R1-Q4_K_S.gguf](https://huggingface.co/bartowski/SUFE-AIFLM-Lab_Fin-R1-GGUF/blob/main/SUFE-AIFLM-Lab_Fin-R1-Q4_K_S.gguf) | Q4_K_S | 4.46GB | false | Slightly lower quality with more space savings, *recommended*. | +| [Fin-R1-Q4_0.gguf](https://huggingface.co/bartowski/SUFE-AIFLM-Lab_Fin-R1-GGUF/blob/main/SUFE-AIFLM-Lab_Fin-R1-Q4_0.gguf) | Q4_0 | 4.44GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [Fin-R1-IQ4_NL.gguf](https://huggingface.co/bartowski/SUFE-AIFLM-Lab_Fin-R1-GGUF/blob/main/SUFE-AIFLM-Lab_Fin-R1-IQ4_NL.gguf) | IQ4_NL | 4.44GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [Fin-R1-IQ4_XS.gguf](https://huggingface.co/bartowski/SUFE-AIFLM-Lab_Fin-R1-GGUF/blob/main/SUFE-AIFLM-Lab_Fin-R1-IQ4_XS.gguf) | IQ4_XS | 4.22GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Fin-R1-Q3_K_L.gguf](https://huggingface.co/bartowski/SUFE-AIFLM-Lab_Fin-R1-GGUF/blob/main/SUFE-AIFLM-Lab_Fin-R1-Q3_K_L.gguf) | Q3_K_L | 4.09GB | false | Lower quality but usable, good for low RAM availability. | +| [Fin-R1-Q3_K_M.gguf](https://huggingface.co/bartowski/SUFE-AIFLM-Lab_Fin-R1-GGUF/blob/main/SUFE-AIFLM-Lab_Fin-R1-Q3_K_M.gguf) | Q3_K_M | 3.81GB | false | Low quality. | +| [Fin-R1-IQ3_M.gguf](https://huggingface.co/bartowski/SUFE-AIFLM-Lab_Fin-R1-GGUF/blob/main/SUFE-AIFLM-Lab_Fin-R1-IQ3_M.gguf) | IQ3_M | 3.57GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [Fin-R1-Q2_K_L.gguf](https://huggingface.co/bartowski/SUFE-AIFLM-Lab_Fin-R1-GGUF/blob/main/SUFE-AIFLM-Lab_Fin-R1-Q2_K_L.gguf) | Q2_K_L | 3.55GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [Fin-R1-Q3_K_S.gguf](https://huggingface.co/bartowski/SUFE-AIFLM-Lab_Fin-R1-GGUF/blob/main/SUFE-AIFLM-Lab_Fin-R1-Q3_K_S.gguf) | Q3_K_S | 3.49GB | false | Low quality, not recommended. | +| [Fin-R1-IQ3_XS.gguf](https://huggingface.co/bartowski/SUFE-AIFLM-Lab_Fin-R1-GGUF/blob/main/SUFE-AIFLM-Lab_Fin-R1-IQ3_XS.gguf) | IQ3_XS | 3.35GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [Fin-R1-IQ3_XXS.gguf](https://huggingface.co/bartowski/SUFE-AIFLM-Lab_Fin-R1-GGUF/blob/main/SUFE-AIFLM-Lab_Fin-R1-IQ3_XXS.gguf) | IQ3_XXS | 3.11GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [Fin-R1-Q2_K.gguf](https://huggingface.co/bartowski/SUFE-AIFLM-Lab_Fin-R1-GGUF/blob/main/SUFE-AIFLM-Lab_Fin-R1-Q2_K.gguf) | Q2_K | 3.02GB | false | Very low quality but surprisingly usable. | +| [Fin-R1-IQ2_M.gguf](https://huggingface.co/bartowski/SUFE-AIFLM-Lab_Fin-R1-GGUF/blob/main/SUFE-AIFLM-Lab_Fin-R1-IQ2_M.gguf) | IQ2_M | 2.78GB | 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/SUFE-AIFLM-Lab_Fin-R1-GGUF --include "SUFE-AIFLM-Lab_Fin-R1-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/SUFE-AIFLM-Lab_Fin-R1-GGUF --include "SUFE-AIFLM-Lab_Fin-R1-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (SUFE-AIFLM-Lab_Fin-R1-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/SUFE-AIFLM-Lab_Fin-R1-IQ2_M.gguf b/SUFE-AIFLM-Lab_Fin-R1-IQ2_M.gguf new file mode 100644 index 0000000..50897b9 --- /dev/null +++ b/SUFE-AIFLM-Lab_Fin-R1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e92c3779e43ccd33c32c11d82b9432e8f05421796395e5d63e26a6d775dd7451 +size 2780342336 diff --git a/SUFE-AIFLM-Lab_Fin-R1-IQ3_M.gguf b/SUFE-AIFLM-Lab_Fin-R1-IQ3_M.gguf new file mode 100644 index 0000000..1a14fae --- /dev/null +++ b/SUFE-AIFLM-Lab_Fin-R1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba72629b704fdeed5565dbd808e7e6771094b72e7f49538432218042df8e5bf3 +size 3574011968 diff --git a/SUFE-AIFLM-Lab_Fin-R1-IQ3_XS.gguf b/SUFE-AIFLM-Lab_Fin-R1-IQ3_XS.gguf new file mode 100644 index 0000000..13f9400 --- /dev/null +++ b/SUFE-AIFLM-Lab_Fin-R1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dbd84f972766fc213242881e20c6fa92dbdbd9bc9ddd32c4f080d186847fa52 +size 3346255936 diff --git a/SUFE-AIFLM-Lab_Fin-R1-IQ3_XXS.gguf b/SUFE-AIFLM-Lab_Fin-R1-IQ3_XXS.gguf new file mode 100644 index 0000000..e51c9b7 --- /dev/null +++ b/SUFE-AIFLM-Lab_Fin-R1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e97c7196285f97f54d625b9ea52e837166313f967f98f31e43e98777bd513f5 +size 3114514496 diff --git a/SUFE-AIFLM-Lab_Fin-R1-IQ4_NL.gguf b/SUFE-AIFLM-Lab_Fin-R1-IQ4_NL.gguf new file mode 100644 index 0000000..64e027f --- /dev/null +++ b/SUFE-AIFLM-Lab_Fin-R1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf4e469fe5fd03ab99722b8adaaee8917c9d84f5cb416a6095540f7711003cea +size 4437813312 diff --git a/SUFE-AIFLM-Lab_Fin-R1-IQ4_XS.gguf b/SUFE-AIFLM-Lab_Fin-R1-IQ4_XS.gguf new file mode 100644 index 0000000..01e7bfc --- /dev/null +++ b/SUFE-AIFLM-Lab_Fin-R1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d12ea70387c78f3bc45cac7ee9bb42c02540efe07d91109c01d16ee13a5bef7 +size 4218472512 diff --git a/SUFE-AIFLM-Lab_Fin-R1-Q2_K.gguf b/SUFE-AIFLM-Lab_Fin-R1-Q2_K.gguf new file mode 100644 index 0000000..3e16277 --- /dev/null +++ b/SUFE-AIFLM-Lab_Fin-R1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dc6b522010eef3d71133de8dd3e16a40167f09ec53e7843de7a226d3bf16856 +size 3015940160 diff --git a/SUFE-AIFLM-Lab_Fin-R1-Q2_K_L.gguf b/SUFE-AIFLM-Lab_Fin-R1-Q2_K_L.gguf new file mode 100644 index 0000000..f6fe87b --- /dev/null +++ b/SUFE-AIFLM-Lab_Fin-R1-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d9edc78ccc948eb3ea126f587c3b421fd773fad3b560a47df569d54f242f443 +size 3548164160 diff --git a/SUFE-AIFLM-Lab_Fin-R1-Q3_K_L.gguf b/SUFE-AIFLM-Lab_Fin-R1-Q3_K_L.gguf new file mode 100644 index 0000000..623a8b2 --- /dev/null +++ b/SUFE-AIFLM-Lab_Fin-R1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4a9c365c411650e751ddb2b42964183b5f8ee3730c65476e7cf0034c3cbc975 +size 4088459328 diff --git a/SUFE-AIFLM-Lab_Fin-R1-Q3_K_M.gguf b/SUFE-AIFLM-Lab_Fin-R1-Q3_K_M.gguf new file mode 100644 index 0000000..5036ecb --- /dev/null +++ b/SUFE-AIFLM-Lab_Fin-R1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c20b70ebec99c987ffc950db112b704f966b407685b4685b559a56998a995efe +size 3808391232 diff --git a/SUFE-AIFLM-Lab_Fin-R1-Q3_K_S.gguf b/SUFE-AIFLM-Lab_Fin-R1-Q3_K_S.gguf new file mode 100644 index 0000000..7157dc0 --- /dev/null +++ b/SUFE-AIFLM-Lab_Fin-R1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3595900ee8058dcb4692a149602e815c54f193c5f0deb260d107d666f82f602d +size 3492368448 diff --git a/SUFE-AIFLM-Lab_Fin-R1-Q3_K_XL.gguf b/SUFE-AIFLM-Lab_Fin-R1-Q3_K_XL.gguf new file mode 100644 index 0000000..0af9fba --- /dev/null +++ b/SUFE-AIFLM-Lab_Fin-R1-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc64327f1387c442dfba695129bf7e3120abd66688b08730e7960460a044158c +size 4565332032 diff --git a/SUFE-AIFLM-Lab_Fin-R1-Q4_0.gguf b/SUFE-AIFLM-Lab_Fin-R1-Q4_0.gguf new file mode 100644 index 0000000..819e1e9 --- /dev/null +++ b/SUFE-AIFLM-Lab_Fin-R1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4f0538a7a9335765df02b518dbc2800110705227a5a5303148fdda5cf45e384 +size 4444121152 diff --git a/SUFE-AIFLM-Lab_Fin-R1-Q4_1.gguf b/SUFE-AIFLM-Lab_Fin-R1-Q4_1.gguf new file mode 100644 index 0000000..2bc6f3e --- /dev/null +++ b/SUFE-AIFLM-Lab_Fin-R1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f33cf03e9e7cf67be942420cd5a994b67d5b668a2137234d6d758e25ad629f40 +size 4873283648 diff --git a/SUFE-AIFLM-Lab_Fin-R1-Q4_K_L.gguf b/SUFE-AIFLM-Lab_Fin-R1-Q4_K_L.gguf new file mode 100644 index 0000000..fe7ba3f --- /dev/null +++ b/SUFE-AIFLM-Lab_Fin-R1-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bf5fe7b6581a7723e1f4370e80d920a5690204ce0d9bb3b259eba8a1debe6c2 +size 5087563840 diff --git a/SUFE-AIFLM-Lab_Fin-R1-Q4_K_M.gguf b/SUFE-AIFLM-Lab_Fin-R1-Q4_K_M.gguf new file mode 100644 index 0000000..63ae20b --- /dev/null +++ b/SUFE-AIFLM-Lab_Fin-R1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d50f16c5149b4dc103c68e249a136ab7c82f7569a7df707a2d6150bff5994c33 +size 4683073600 diff --git a/SUFE-AIFLM-Lab_Fin-R1-Q4_K_S.gguf b/SUFE-AIFLM-Lab_Fin-R1-Q4_K_S.gguf new file mode 100644 index 0000000..6fdf996 --- /dev/null +++ b/SUFE-AIFLM-Lab_Fin-R1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d01f8a5729dc573f79e4c7df44d68e3d564264f0df887881fa875e6a7c07970 +size 4457769024 diff --git a/SUFE-AIFLM-Lab_Fin-R1-Q5_K_L.gguf b/SUFE-AIFLM-Lab_Fin-R1-Q5_K_L.gguf new file mode 100644 index 0000000..a509d70 --- /dev/null +++ b/SUFE-AIFLM-Lab_Fin-R1-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3fdc73c30cc697052332d69f8c60f6754a2409746ccd8760a2c2ea448bf4d40 +size 5781196864 diff --git a/SUFE-AIFLM-Lab_Fin-R1-Q5_K_M.gguf b/SUFE-AIFLM-Lab_Fin-R1-Q5_K_M.gguf new file mode 100644 index 0000000..2ff5178 --- /dev/null +++ b/SUFE-AIFLM-Lab_Fin-R1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7377236ecdda291058a6c096ac4f3b19764de70efc23a537d30782e22bdb430 +size 5444831296 diff --git a/SUFE-AIFLM-Lab_Fin-R1-Q5_K_S.gguf b/SUFE-AIFLM-Lab_Fin-R1-Q5_K_S.gguf new file mode 100644 index 0000000..f48339b --- /dev/null +++ b/SUFE-AIFLM-Lab_Fin-R1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcff7bc7289aa2450e13dd5bc2cd5c4f3a496aa408c1891e42f4f224e34dacb2 +size 5315176512 diff --git a/SUFE-AIFLM-Lab_Fin-R1-Q6_K.gguf b/SUFE-AIFLM-Lab_Fin-R1-Q6_K.gguf new file mode 100644 index 0000000..01e4d1d --- /dev/null +++ b/SUFE-AIFLM-Lab_Fin-R1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10a9f2315b98ef67ad8ea34750da125566f8d24c0075a5df2cb3845e6a2fa177 +size 6254198848 diff --git a/SUFE-AIFLM-Lab_Fin-R1-Q6_K_L.gguf b/SUFE-AIFLM-Lab_Fin-R1-Q6_K_L.gguf new file mode 100644 index 0000000..61f52ef --- /dev/null +++ b/SUFE-AIFLM-Lab_Fin-R1-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f96f7d8d0b53dba92237a837c5be8654cf9a30157b6a5029417d8a7d443136d3 +size 6518181952 diff --git a/SUFE-AIFLM-Lab_Fin-R1-Q8_0.gguf b/SUFE-AIFLM-Lab_Fin-R1-Q8_0.gguf new file mode 100644 index 0000000..79b034d --- /dev/null +++ b/SUFE-AIFLM-Lab_Fin-R1-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:999b13aec7a6703d2fa108cabda180427e1223dcec9e525c29a1d894863b1a66 +size 8098525248 diff --git a/SUFE-AIFLM-Lab_Fin-R1-bf16.gguf b/SUFE-AIFLM-Lab_Fin-R1-bf16.gguf new file mode 100644 index 0000000..6e3e27e --- /dev/null +++ b/SUFE-AIFLM-Lab_Fin-R1-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc82da151a956ca1612bacc93a94467e27c8f81bca32a8b1cec16d785730a764 +size 15237852992 diff --git a/SUFE-AIFLM-Lab_Fin-R1.imatrix b/SUFE-AIFLM-Lab_Fin-R1.imatrix new file mode 100644 index 0000000..6272017 Binary files /dev/null and b/SUFE-AIFLM-Lab_Fin-R1.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