commit caa1e2cb4c89cdf1d47deb3f3460b971977706e0 Author: ModelHub XC Date: Wed Aug 19 19:51:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/arcee-ai_AFM-4.5B-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..fc3e4fb --- /dev/null +++ b/README.md @@ -0,0 +1,194 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +base_model_relation: quantized +base_model: arcee-ai/AFM-4.5B +license: apache-2.0 +language: + - en + - es + - fr + - de + - it + - pt + - ru + - ar + - hi + - ko + - zh +--- + +## Llamacpp imatrix Quantizations of AFM-4.5B by arcee-ai + +Using llama.cpp release b6014 for quantization. + +Original model: https://huggingface.co/arcee-ai/AFM-4.5B + +All quants made using imatrix option with dataset combined_all_medium from Ed Addario [here](https://huggingface.co/datasets/eaddario/imatrix-calibration) + +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 + +## Recommended sampling settings + +* temperature: 0.5 +* top_k: 50 +* top_p: 0.95 +* repeat_penalty: 1.1 +* min_p: 0.05 + +Temperature set to 0.5 is the most important here, model tends to over talk with higher. + +## 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 | +| -------- | ---------- | --------- | ----- | ----------- | +| [AFM-4.5B-bf16.gguf](https://huggingface.co/bartowski/arcee-ai_AFM-4.5B-GGUF/blob/main/arcee-ai_AFM-4.5B-bf16.gguf) | bf16 | 9.25GB | false | Full BF16 weights. | +| [AFM-4.5B-Q8_0.gguf](https://huggingface.co/bartowski/arcee-ai_AFM-4.5B-GGUF/blob/main/arcee-ai_AFM-4.5B-Q8_0.gguf) | Q8_0 | 4.92GB | false | Extremely high quality, generally unneeded but max available quant. | +| [AFM-4.5B-Q6_K_L.gguf](https://huggingface.co/bartowski/arcee-ai_AFM-4.5B-GGUF/blob/main/arcee-ai_AFM-4.5B-Q6_K_L.gguf) | Q6_K_L | 3.96GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [AFM-4.5B-Q6_K.gguf](https://huggingface.co/bartowski/arcee-ai_AFM-4.5B-GGUF/blob/main/arcee-ai_AFM-4.5B-Q6_K.gguf) | Q6_K | 3.80GB | false | Very high quality, near perfect, *recommended*. | +| [AFM-4.5B-Q5_K_L.gguf](https://huggingface.co/bartowski/arcee-ai_AFM-4.5B-GGUF/blob/main/arcee-ai_AFM-4.5B-Q5_K_L.gguf) | Q5_K_L | 3.55GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [AFM-4.5B-Q5_K_M.gguf](https://huggingface.co/bartowski/arcee-ai_AFM-4.5B-GGUF/blob/main/arcee-ai_AFM-4.5B-Q5_K_M.gguf) | Q5_K_M | 3.34GB | false | High quality, *recommended*. | +| [AFM-4.5B-Q5_K_S.gguf](https://huggingface.co/bartowski/arcee-ai_AFM-4.5B-GGUF/blob/main/arcee-ai_AFM-4.5B-Q5_K_S.gguf) | Q5_K_S | 3.23GB | false | High quality, *recommended*. | +| [AFM-4.5B-Q4_K_L.gguf](https://huggingface.co/bartowski/arcee-ai_AFM-4.5B-GGUF/blob/main/arcee-ai_AFM-4.5B-Q4_K_L.gguf) | Q4_K_L | 3.16GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [AFM-4.5B-Q4_1.gguf](https://huggingface.co/bartowski/arcee-ai_AFM-4.5B-GGUF/blob/main/arcee-ai_AFM-4.5B-Q4_1.gguf) | Q4_1 | 2.96GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [AFM-4.5B-Q4_K_M.gguf](https://huggingface.co/bartowski/arcee-ai_AFM-4.5B-GGUF/blob/main/arcee-ai_AFM-4.5B-Q4_K_M.gguf) | Q4_K_M | 2.92GB | false | Good quality, default size for most use cases, *recommended*. | +| [AFM-4.5B-Q3_K_XL.gguf](https://huggingface.co/bartowski/arcee-ai_AFM-4.5B-GGUF/blob/main/arcee-ai_AFM-4.5B-Q3_K_XL.gguf) | Q3_K_XL | 2.92GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [AFM-4.5B-Q4_K_S.gguf](https://huggingface.co/bartowski/arcee-ai_AFM-4.5B-GGUF/blob/main/arcee-ai_AFM-4.5B-Q4_K_S.gguf) | Q4_K_S | 2.72GB | false | Slightly lower quality with more space savings, *recommended*. | +| [AFM-4.5B-Q4_0.gguf](https://huggingface.co/bartowski/arcee-ai_AFM-4.5B-GGUF/blob/main/arcee-ai_AFM-4.5B-Q4_0.gguf) | Q4_0 | 2.70GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [AFM-4.5B-IQ4_NL.gguf](https://huggingface.co/bartowski/arcee-ai_AFM-4.5B-GGUF/blob/main/arcee-ai_AFM-4.5B-IQ4_NL.gguf) | IQ4_NL | 2.70GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [AFM-4.5B-Q3_K_L.gguf](https://huggingface.co/bartowski/arcee-ai_AFM-4.5B-GGUF/blob/main/arcee-ai_AFM-4.5B-Q3_K_L.gguf) | Q3_K_L | 2.63GB | false | Lower quality but usable, good for low RAM availability. | +| [AFM-4.5B-IQ4_XS.gguf](https://huggingface.co/bartowski/arcee-ai_AFM-4.5B-GGUF/blob/main/arcee-ai_AFM-4.5B-IQ4_XS.gguf) | IQ4_XS | 2.56GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [AFM-4.5B-Q3_K_M.gguf](https://huggingface.co/bartowski/arcee-ai_AFM-4.5B-GGUF/blob/main/arcee-ai_AFM-4.5B-Q3_K_M.gguf) | Q3_K_M | 2.40GB | false | Low quality. | +| [AFM-4.5B-Q2_K_L.gguf](https://huggingface.co/bartowski/arcee-ai_AFM-4.5B-GGUF/blob/main/arcee-ai_AFM-4.5B-Q2_K_L.gguf) | Q2_K_L | 2.21GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [AFM-4.5B-IQ3_M.gguf](https://huggingface.co/bartowski/arcee-ai_AFM-4.5B-GGUF/blob/main/arcee-ai_AFM-4.5B-IQ3_M.gguf) | IQ3_M | 2.18GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [AFM-4.5B-Q3_K_S.gguf](https://huggingface.co/bartowski/arcee-ai_AFM-4.5B-GGUF/blob/main/arcee-ai_AFM-4.5B-Q3_K_S.gguf) | Q3_K_S | 2.12GB | false | Low quality, not recommended. | +| [AFM-4.5B-IQ3_XS.gguf](https://huggingface.co/bartowski/arcee-ai_AFM-4.5B-GGUF/blob/main/arcee-ai_AFM-4.5B-IQ3_XS.gguf) | IQ3_XS | 2.05GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [AFM-4.5B-IQ3_XXS.gguf](https://huggingface.co/bartowski/arcee-ai_AFM-4.5B-GGUF/blob/main/arcee-ai_AFM-4.5B-IQ3_XXS.gguf) | IQ3_XXS | 1.89GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [AFM-4.5B-Q2_K.gguf](https://huggingface.co/bartowski/arcee-ai_AFM-4.5B-GGUF/blob/main/arcee-ai_AFM-4.5B-Q2_K.gguf) | Q2_K | 1.89GB | false | Very low quality but surprisingly usable. | +| [AFM-4.5B-IQ2_M.gguf](https://huggingface.co/bartowski/arcee-ai_AFM-4.5B-GGUF/blob/main/arcee-ai_AFM-4.5B-IQ2_M.gguf) | IQ2_M | 1.70GB | 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/arcee-ai_AFM-4.5B-GGUF --include "arcee-ai_AFM-4.5B-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/arcee-ai_AFM-4.5B-GGUF --include "arcee-ai_AFM-4.5B-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (arcee-ai_AFM-4.5B-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/arcee-ai_AFM-4.5B-IQ2_M.gguf b/arcee-ai_AFM-4.5B-IQ2_M.gguf new file mode 100644 index 0000000..4a8dcf8 --- /dev/null +++ b/arcee-ai_AFM-4.5B-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dc3b9cf4bb919f7f5bf81daac722c1e8012664bd4283e0111b956adb2f5069b +size 1702141600 diff --git a/arcee-ai_AFM-4.5B-IQ3_M.gguf b/arcee-ai_AFM-4.5B-IQ3_M.gguf new file mode 100644 index 0000000..34181da --- /dev/null +++ b/arcee-ai_AFM-4.5B-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9e4a54d724a0ece69236941e161c9d188f71b07f509fd0a4114be253a6ea913 +size 2183976288 diff --git a/arcee-ai_AFM-4.5B-IQ3_XS.gguf b/arcee-ai_AFM-4.5B-IQ3_XS.gguf new file mode 100644 index 0000000..f27f0ff --- /dev/null +++ b/arcee-ai_AFM-4.5B-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12cc34447242197af011f479a6779abf8adcd377c7abbf8c222dbf3eb0743dbb +size 2054583648 diff --git a/arcee-ai_AFM-4.5B-IQ3_XXS.gguf b/arcee-ai_AFM-4.5B-IQ3_XXS.gguf new file mode 100644 index 0000000..ac36639 --- /dev/null +++ b/arcee-ai_AFM-4.5B-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5d2cef984fb8e47fdb55fd4b719c622aa6a87f03fb748ed3f0e972fddcfc6cf +size 1893834400 diff --git a/arcee-ai_AFM-4.5B-IQ4_NL.gguf b/arcee-ai_AFM-4.5B-IQ4_NL.gguf new file mode 100644 index 0000000..363f6e7 --- /dev/null +++ b/arcee-ai_AFM-4.5B-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c0a31c20c6fe289c85d4c0ca81529d8faef62d56c9381a832f56d7eace0ddc5 +size 2697145344 diff --git a/arcee-ai_AFM-4.5B-IQ4_XS.gguf b/arcee-ai_AFM-4.5B-IQ4_XS.gguf new file mode 100644 index 0000000..a8031bb --- /dev/null +++ b/arcee-ai_AFM-4.5B-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21d047567dfcb92dc9b3db1ba667cb136f7908c0e1b17c6128b4720506678ca1 +size 2564516480 diff --git a/arcee-ai_AFM-4.5B-Q2_K.gguf b/arcee-ai_AFM-4.5B-Q2_K.gguf new file mode 100644 index 0000000..490c2a6 --- /dev/null +++ b/arcee-ai_AFM-4.5B-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:702bb1e84615e3ef38d89f0e7e832669282b64446405cf54c884f5003af91272 +size 1893015648 diff --git a/arcee-ai_AFM-4.5B-Q2_K_L.gguf b/arcee-ai_AFM-4.5B-Q2_K_L.gguf new file mode 100644 index 0000000..389fb1e --- /dev/null +++ b/arcee-ai_AFM-4.5B-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd7386ab7559a59b66e7a657eb36ca908a3179ff24f857de62a69faa100124a2 +size 2213028096 diff --git a/arcee-ai_AFM-4.5B-Q3_K_L.gguf b/arcee-ai_AFM-4.5B-Q3_K_L.gguf new file mode 100644 index 0000000..44fe0e9 --- /dev/null +++ b/arcee-ai_AFM-4.5B-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bbcdca8d1d8cbc9bf57b199fd5739bf87a9cb7a8a345847251795e7d4c30642 +size 2632242528 diff --git a/arcee-ai_AFM-4.5B-Q3_K_M.gguf b/arcee-ai_AFM-4.5B-Q3_K_M.gguf new file mode 100644 index 0000000..30f7510 --- /dev/null +++ b/arcee-ai_AFM-4.5B-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07f8f198598a3ea3ddec88bd08da1eecebec949ff8904858007d2fa58b011e7b +size 2396640608 diff --git a/arcee-ai_AFM-4.5B-Q3_K_S.gguf b/arcee-ai_AFM-4.5B-Q3_K_S.gguf new file mode 100644 index 0000000..7f695f7 --- /dev/null +++ b/arcee-ai_AFM-4.5B-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46279295723cd8fa09f36e206a2a2e0826ab4f7eb0e91c13258f7abe6b703089 +size 2121307488 diff --git a/arcee-ai_AFM-4.5B-Q3_K_XL.gguf b/arcee-ai_AFM-4.5B-Q3_K_XL.gguf new file mode 100644 index 0000000..c189b6f --- /dev/null +++ b/arcee-ai_AFM-4.5B-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:930dc197ccb11781d16502934ee46214e48a9a514a98492e1fcc4568c718bdf4 +size 2918973696 diff --git a/arcee-ai_AFM-4.5B-Q4_0.gguf b/arcee-ai_AFM-4.5B-Q4_0.gguf new file mode 100644 index 0000000..874c4f6 --- /dev/null +++ b/arcee-ai_AFM-4.5B-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f686790a03b16d415d5dfed2f42592f8dd31d09b977358a989aac63981b3dd14 +size 2703043584 diff --git a/arcee-ai_AFM-4.5B-Q4_1.gguf b/arcee-ai_AFM-4.5B-Q4_1.gguf new file mode 100644 index 0000000..30836a8 --- /dev/null +++ b/arcee-ai_AFM-4.5B-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e36821939e87d8bd0e0dc4665871eb6599a3957f2195b8ecb421af05b66c3d8c +size 2959453984 diff --git a/arcee-ai_AFM-4.5B-Q4_K_L.gguf b/arcee-ai_AFM-4.5B-Q4_K_L.gguf new file mode 100644 index 0000000..63a68a5 --- /dev/null +++ b/arcee-ai_AFM-4.5B-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7d3e0d4540d145665778f1437fa2db7174fbb535d70e26404e6da85ff334aa2 +size 3159511296 diff --git a/arcee-ai_AFM-4.5B-Q4_K_M.gguf b/arcee-ai_AFM-4.5B-Q4_K_M.gguf new file mode 100644 index 0000000..18c144d --- /dev/null +++ b/arcee-ai_AFM-4.5B-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f05516b323f581bebae1af2cbf900d83a2569b0a60c54366daf4a9c15ae30d4f +size 2916301824 diff --git a/arcee-ai_AFM-4.5B-Q4_K_S.gguf b/arcee-ai_AFM-4.5B-Q4_K_S.gguf new file mode 100644 index 0000000..0ad0c7f --- /dev/null +++ b/arcee-ai_AFM-4.5B-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f68b38f15070996325da741d356ca0bb62b992e4267e734cace8b800b7943e6c +size 2715495424 diff --git a/arcee-ai_AFM-4.5B-Q5_K_L.gguf b/arcee-ai_AFM-4.5B-Q5_K_L.gguf new file mode 100644 index 0000000..24658e7 --- /dev/null +++ b/arcee-ai_AFM-4.5B-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b966303676fe9167938635d8c22cd0f8666f01016b5d52b4a5cde00c01a9b06 +size 3545846016 diff --git a/arcee-ai_AFM-4.5B-Q5_K_M.gguf b/arcee-ai_AFM-4.5B-Q5_K_M.gguf new file mode 100644 index 0000000..8431588 --- /dev/null +++ b/arcee-ai_AFM-4.5B-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2570a39506b6ae2f01288ddac7bc48a320f199cd6da53ae0df844f527b256e20 +size 3343598144 diff --git a/arcee-ai_AFM-4.5B-Q5_K_S.gguf b/arcee-ai_AFM-4.5B-Q5_K_S.gguf new file mode 100644 index 0000000..f0a8ffe --- /dev/null +++ b/arcee-ai_AFM-4.5B-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a2aa255cb8ec65c17a4543e599bc5465a5122f35b6a637234d0cd4357c88b3e +size 3227660864 diff --git a/arcee-ai_AFM-4.5B-Q6_K.gguf b/arcee-ai_AFM-4.5B-Q6_K.gguf new file mode 100644 index 0000000..066ba27 --- /dev/null +++ b/arcee-ai_AFM-4.5B-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ac5833be0f529be0a056a79e6f9c47b25c536d28ced3d2732048353c7b22fdf +size 3797600512 diff --git a/arcee-ai_AFM-4.5B-Q6_K_L.gguf b/arcee-ai_AFM-4.5B-Q6_K_L.gguf new file mode 100644 index 0000000..cea2205 --- /dev/null +++ b/arcee-ai_AFM-4.5B-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abebad1e6ca91fedac720726e9c7ead03238fd36e42ba093968f6b1d72545725 +size 3956326656 diff --git a/arcee-ai_AFM-4.5B-Q8_0.gguf b/arcee-ai_AFM-4.5B-Q8_0.gguf new file mode 100644 index 0000000..5dee76f --- /dev/null +++ b/arcee-ai_AFM-4.5B-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2de4692fc3404ba302701753f4110610d3d8f88cf49294d5ce0f176e01cc8871 +size 4916265216 diff --git a/arcee-ai_AFM-4.5B-bf16.gguf b/arcee-ai_AFM-4.5B-bf16.gguf new file mode 100644 index 0000000..f6c779b --- /dev/null +++ b/arcee-ai_AFM-4.5B-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdab357e420746fc82efbcb511ca4033e4b2960db6b2622e359c4e2f58f4bea6 +size 9246580128 diff --git a/arcee-ai_AFM-4.5B-imatrix.gguf b/arcee-ai_AFM-4.5B-imatrix.gguf new file mode 100644 index 0000000..7ef232e --- /dev/null +++ b/arcee-ai_AFM-4.5B-imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:834d755fcf23d5197795999946c5218b2ac5e7275c07f94175bc1bef7de638ec +size 4530656 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