commit feb1341df494cacdea6b34fe04e03c276addb909 Author: ModelHub XC Date: Fri Aug 7 19:05:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/alamios_Mistral-Small-3.1-DRAFT-0.5B-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..7236d0c --- /dev/null +++ b/README.md @@ -0,0 +1,182 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +license: apache-2.0 +base_model_relation: quantized +language: +- en +- fr +- de +- es +- it +- pt +base_model: alamios/Mistral-Small-3.1-DRAFT-0.5B +datasets: +- alamios/Mistral-Small-24B-Instruct-2501-Conversations +tags: +- qwen +- qwen2.5 +- mistral +- mistral-small +- mistral-small-3.1 +--- + +## Llamacpp imatrix Quantizations of Mistral-Small-3.1-DRAFT-0.5B by alamios + +Using llama.cpp release b4944 for quantization. + +Original model: https://huggingface.co/alamios/Mistral-Small-3.1-DRAFT-0.5B + +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 + +``` +[SYSTEM_PROMPT]{system_prompt}[/SYSTEM_PROMPT][INST]{prompt}[/INST] +``` + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [Mistral-Small-3.1-DRAFT-0.5B-bf16.gguf](https://huggingface.co/bartowski/alamios_Mistral-Small-3.1-DRAFT-0.5B-GGUF/blob/main/alamios_Mistral-Small-3.1-DRAFT-0.5B-bf16.gguf) | bf16 | 1.19GB | false | Full BF16 weights. | +| [Mistral-Small-3.1-DRAFT-0.5B-Q8_0.gguf](https://huggingface.co/bartowski/alamios_Mistral-Small-3.1-DRAFT-0.5B-GGUF/blob/main/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q8_0.gguf) | Q8_0 | 0.64GB | false | Extremely high quality, generally unneeded but max available quant. | +| [Mistral-Small-3.1-DRAFT-0.5B-Q6_K_L.gguf](https://huggingface.co/bartowski/alamios_Mistral-Small-3.1-DRAFT-0.5B-GGUF/blob/main/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q6_K_L.gguf) | Q6_K_L | 0.61GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [Mistral-Small-3.1-DRAFT-0.5B-Q6_K.gguf](https://huggingface.co/bartowski/alamios_Mistral-Small-3.1-DRAFT-0.5B-GGUF/blob/main/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q6_K.gguf) | Q6_K | 0.61GB | false | Very high quality, near perfect, *recommended*. | +| [Mistral-Small-3.1-DRAFT-0.5B-Q5_K_L.gguf](https://huggingface.co/bartowski/alamios_Mistral-Small-3.1-DRAFT-0.5B-GGUF/blob/main/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q5_K_L.gguf) | Q5_K_L | 0.53GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [Mistral-Small-3.1-DRAFT-0.5B-Q4_K_L.gguf](https://huggingface.co/bartowski/alamios_Mistral-Small-3.1-DRAFT-0.5B-GGUF/blob/main/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q4_K_L.gguf) | Q4_K_L | 0.50GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [Mistral-Small-3.1-DRAFT-0.5B-Q5_K_M.gguf](https://huggingface.co/bartowski/alamios_Mistral-Small-3.1-DRAFT-0.5B-GGUF/blob/main/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q5_K_M.gguf) | Q5_K_M | 0.49GB | false | High quality, *recommended*. | +| [Mistral-Small-3.1-DRAFT-0.5B-Q5_K_S.gguf](https://huggingface.co/bartowski/alamios_Mistral-Small-3.1-DRAFT-0.5B-GGUF/blob/main/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q5_K_S.gguf) | Q5_K_S | 0.48GB | false | High quality, *recommended*. | +| [Mistral-Small-3.1-DRAFT-0.5B-Q3_K_XL.gguf](https://huggingface.co/bartowski/alamios_Mistral-Small-3.1-DRAFT-0.5B-GGUF/blob/main/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q3_K_XL.gguf) | Q3_K_XL | 0.48GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [Mistral-Small-3.1-DRAFT-0.5B-Q4_K_M.gguf](https://huggingface.co/bartowski/alamios_Mistral-Small-3.1-DRAFT-0.5B-GGUF/blob/main/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q4_K_M.gguf) | Q4_K_M | 0.46GB | false | Good quality, default size for most use cases, *recommended*. | +| [Mistral-Small-3.1-DRAFT-0.5B-Q4_K_S.gguf](https://huggingface.co/bartowski/alamios_Mistral-Small-3.1-DRAFT-0.5B-GGUF/blob/main/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q4_K_S.gguf) | Q4_K_S | 0.45GB | false | Slightly lower quality with more space savings, *recommended*. | +| [Mistral-Small-3.1-DRAFT-0.5B-Q2_K_L.gguf](https://huggingface.co/bartowski/alamios_Mistral-Small-3.1-DRAFT-0.5B-GGUF/blob/main/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q2_K_L.gguf) | Q2_K_L | 0.45GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [Mistral-Small-3.1-DRAFT-0.5B-Q4_1.gguf](https://huggingface.co/bartowski/alamios_Mistral-Small-3.1-DRAFT-0.5B-GGUF/blob/main/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q4_1.gguf) | Q4_1 | 0.43GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [Mistral-Small-3.1-DRAFT-0.5B-Q3_K_L.gguf](https://huggingface.co/bartowski/alamios_Mistral-Small-3.1-DRAFT-0.5B-GGUF/blob/main/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q3_K_L.gguf) | Q3_K_L | 0.42GB | false | Lower quality but usable, good for low RAM availability. | +| [Mistral-Small-3.1-DRAFT-0.5B-Q4_0.gguf](https://huggingface.co/bartowski/alamios_Mistral-Small-3.1-DRAFT-0.5B-GGUF/blob/main/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q4_0.gguf) | Q4_0 | 0.40GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [Mistral-Small-3.1-DRAFT-0.5B-IQ4_NL.gguf](https://huggingface.co/bartowski/alamios_Mistral-Small-3.1-DRAFT-0.5B-GGUF/blob/main/alamios_Mistral-Small-3.1-DRAFT-0.5B-IQ4_NL.gguf) | IQ4_NL | 0.40GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [Mistral-Small-3.1-DRAFT-0.5B-IQ4_XS.gguf](https://huggingface.co/bartowski/alamios_Mistral-Small-3.1-DRAFT-0.5B-GGUF/blob/main/alamios_Mistral-Small-3.1-DRAFT-0.5B-IQ4_XS.gguf) | IQ4_XS | 0.40GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Mistral-Small-3.1-DRAFT-0.5B-Q3_K_M.gguf](https://huggingface.co/bartowski/alamios_Mistral-Small-3.1-DRAFT-0.5B-GGUF/blob/main/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q3_K_M.gguf) | Q3_K_M | 0.40GB | false | Low quality. | +| [Mistral-Small-3.1-DRAFT-0.5B-IQ3_M.gguf](https://huggingface.co/bartowski/alamios_Mistral-Small-3.1-DRAFT-0.5B-GGUF/blob/main/alamios_Mistral-Small-3.1-DRAFT-0.5B-IQ3_M.gguf) | IQ3_M | 0.39GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [Mistral-Small-3.1-DRAFT-0.5B-Q3_K_S.gguf](https://huggingface.co/bartowski/alamios_Mistral-Small-3.1-DRAFT-0.5B-GGUF/blob/main/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q3_K_S.gguf) | Q3_K_S | 0.39GB | false | Low quality, not recommended. | +| [Mistral-Small-3.1-DRAFT-0.5B-IQ3_XS.gguf](https://huggingface.co/bartowski/alamios_Mistral-Small-3.1-DRAFT-0.5B-GGUF/blob/main/alamios_Mistral-Small-3.1-DRAFT-0.5B-IQ3_XS.gguf) | IQ3_XS | 0.39GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [Mistral-Small-3.1-DRAFT-0.5B-Q2_K.gguf](https://huggingface.co/bartowski/alamios_Mistral-Small-3.1-DRAFT-0.5B-GGUF/blob/main/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q2_K.gguf) | Q2_K | 0.39GB | false | Very low quality but surprisingly usable. | +| [Mistral-Small-3.1-DRAFT-0.5B-IQ3_XXS.gguf](https://huggingface.co/bartowski/alamios_Mistral-Small-3.1-DRAFT-0.5B-GGUF/blob/main/alamios_Mistral-Small-3.1-DRAFT-0.5B-IQ3_XXS.gguf) | IQ3_XXS | 0.38GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [Mistral-Small-3.1-DRAFT-0.5B-IQ2_M.gguf](https://huggingface.co/bartowski/alamios_Mistral-Small-3.1-DRAFT-0.5B-GGUF/blob/main/alamios_Mistral-Small-3.1-DRAFT-0.5B-IQ2_M.gguf) | IQ2_M | 0.38GB | 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/alamios_Mistral-Small-3.1-DRAFT-0.5B-GGUF --include "alamios_Mistral-Small-3.1-DRAFT-0.5B-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/alamios_Mistral-Small-3.1-DRAFT-0.5B-GGUF --include "alamios_Mistral-Small-3.1-DRAFT-0.5B-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (alamios_Mistral-Small-3.1-DRAFT-0.5B-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/alamios_Mistral-Small-3.1-DRAFT-0.5B-IQ2_M.gguf b/alamios_Mistral-Small-3.1-DRAFT-0.5B-IQ2_M.gguf new file mode 100644 index 0000000..7bdc909 --- /dev/null +++ b/alamios_Mistral-Small-3.1-DRAFT-0.5B-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d91015b79b10dda15798c02d72a9aad3a388ef45b5eeee7031c3cb3b09b717b +size 376725632 diff --git a/alamios_Mistral-Small-3.1-DRAFT-0.5B-IQ3_M.gguf b/alamios_Mistral-Small-3.1-DRAFT-0.5B-IQ3_M.gguf new file mode 100644 index 0000000..a482ace --- /dev/null +++ b/alamios_Mistral-Small-3.1-DRAFT-0.5B-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f11bf905c62ebb84565e7cfda79edf718d13f2c6bc885426b91effa3d153db73 +size 390880640 diff --git a/alamios_Mistral-Small-3.1-DRAFT-0.5B-IQ3_XS.gguf b/alamios_Mistral-Small-3.1-DRAFT-0.5B-IQ3_XS.gguf new file mode 100644 index 0000000..2d95f59 --- /dev/null +++ b/alamios_Mistral-Small-3.1-DRAFT-0.5B-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbd6cb2fcba38800553d9e3530f3d06819399bd409bba32739766f2bb220c8ed +size 386735744 diff --git a/alamios_Mistral-Small-3.1-DRAFT-0.5B-IQ3_XXS.gguf b/alamios_Mistral-Small-3.1-DRAFT-0.5B-IQ3_XXS.gguf new file mode 100644 index 0000000..9242067 --- /dev/null +++ b/alamios_Mistral-Small-3.1-DRAFT-0.5B-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9668832c673e6581552f4884a1996710668b99536fa64c159b60691d5d632363 +size 381832832 diff --git a/alamios_Mistral-Small-3.1-DRAFT-0.5B-IQ4_NL.gguf b/alamios_Mistral-Small-3.1-DRAFT-0.5B-IQ4_NL.gguf new file mode 100644 index 0000000..ba706c6 --- /dev/null +++ b/alamios_Mistral-Small-3.1-DRAFT-0.5B-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:735955bcfe610b212da2ea4bca8a233115da3c9be8033faa3e83e8934182dc27 +size 400799360 diff --git a/alamios_Mistral-Small-3.1-DRAFT-0.5B-IQ4_XS.gguf b/alamios_Mistral-Small-3.1-DRAFT-0.5B-IQ4_XS.gguf new file mode 100644 index 0000000..51e94b0 --- /dev/null +++ b/alamios_Mistral-Small-3.1-DRAFT-0.5B-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff486e95b8c3eff8ea2ec44f52c50033d74cce3e94582a14133fee81c3e53863 +size 397530752 diff --git a/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q2_K.gguf b/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q2_K.gguf new file mode 100644 index 0000000..9e61590 --- /dev/null +++ b/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05104d4c6605bb717ada6d7b377c4eba7ba022694d3cbfe60cceebb21b208424 +size 386735744 diff --git a/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q2_K_L.gguf b/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q2_K_L.gguf new file mode 100644 index 0000000..54964dc --- /dev/null +++ b/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:061ef7812175cd1dab825ac52a2662a28c70fff2b672fe1421b872328c329121 +size 445456000 diff --git a/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q3_K_L.gguf b/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q3_K_L.gguf new file mode 100644 index 0000000..d4abf73 --- /dev/null +++ b/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea1ed867dfd92cb08b13793faddd9651dc8e05862eb5467469f7965532c03c95 +size 417486464 diff --git a/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q3_K_M.gguf b/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q3_K_M.gguf new file mode 100644 index 0000000..a926e36 --- /dev/null +++ b/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6a6fe4beedcc39a39090e0f84d3d260335be35537d4232a7950851d598466f7 +size 403594880 diff --git a/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q3_K_S.gguf b/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q3_K_S.gguf new file mode 100644 index 0000000..fe73ac9 --- /dev/null +++ b/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:724a4c4559f9a9a2fc805016cfb1561c9667d88e7dcef9f8c04be3155a3fb733 +size 386391680 diff --git a/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q3_K_XL.gguf b/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q3_K_XL.gguf new file mode 100644 index 0000000..8b143f7 --- /dev/null +++ b/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2045e53e1a4d8c43582c7897b054a8951cde3e8bb0b84cf1c96125fc27774c79 +size 476206720 diff --git a/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q4_0.gguf b/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q4_0.gguf new file mode 100644 index 0000000..9efe3c7 --- /dev/null +++ b/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d37a5d011f7bd765c71853a2bf8222b8ad76c6135c3eda01028e5bd51088002 +size 401100416 diff --git a/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q4_1.gguf b/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q4_1.gguf new file mode 100644 index 0000000..b8826e7 --- /dev/null +++ b/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:381c7e27f86806b42c932ea8289af646b5808cb9b2885e30dbf3e9c96d08f25c +size 429987456 diff --git a/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q4_K_L.gguf b/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q4_K_L.gguf new file mode 100644 index 0000000..bdedf39 --- /dev/null +++ b/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13bd9b5ce4aea8904535e32449660f2a2c6ecb494f3eabe7558e386a1679ba11 +size 504656512 diff --git a/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q4_K_M.gguf b/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q4_K_M.gguf new file mode 100644 index 0000000..9c471ec --- /dev/null +++ b/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60c67c7f3a5c6410c460b742ff9698b91980d9bb0519a91bcc0a3065fbd4aadd +size 460616320 diff --git a/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q4_K_S.gguf b/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q4_K_S.gguf new file mode 100644 index 0000000..1ecaf1d --- /dev/null +++ b/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0613349b423922b7beba1baea7c1d178603dfeccf3d67c4f69be16a7dfea93cc +size 448280192 diff --git a/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q5_K_L.gguf b/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q5_K_L.gguf new file mode 100644 index 0000000..ad806b4 --- /dev/null +++ b/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:594d477e6ef495fd58a3c78e9426f83e6fb2eb6cbe96ce92ea9f966949ef1c26 +size 526934656 diff --git a/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q5_K_M.gguf b/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q5_K_M.gguf new file mode 100644 index 0000000..1b6fb88 --- /dev/null +++ b/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5fb002325b471fcbfca15fe99b482a98bcdfaa2137ae56a3a655a609d1b3d1c +size 490234496 diff --git a/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q5_K_S.gguf b/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q5_K_S.gguf new file mode 100644 index 0000000..cc14397 --- /dev/null +++ b/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5575f80ac1105b3a50658b4eead83d92781140bc10042b483d710c172bd056df +size 482858624 diff --git a/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q6_K.gguf b/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q6_K.gguf new file mode 100644 index 0000000..7bd2c49 --- /dev/null +++ b/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:989c2b171ea55153c3e7991fe3280adb7075ae95826733c827a2ad488864399a +size 612585088 diff --git a/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q6_K_L.gguf b/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q6_K_L.gguf new file mode 100644 index 0000000..7bd2c49 --- /dev/null +++ b/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:989c2b171ea55153c3e7991fe3280adb7075ae95826733c827a2ad488864399a +size 612585088 diff --git a/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q8_0.gguf b/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q8_0.gguf new file mode 100644 index 0000000..8b302b4 --- /dev/null +++ b/alamios_Mistral-Small-3.1-DRAFT-0.5B-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8745bf4640a2350de1a3b8cb7e87ab634358be5ea7491e9977aa58882287b6d +size 637916800 diff --git a/alamios_Mistral-Small-3.1-DRAFT-0.5B-bf16.gguf b/alamios_Mistral-Small-3.1-DRAFT-0.5B-bf16.gguf new file mode 100644 index 0000000..01cabac --- /dev/null +++ b/alamios_Mistral-Small-3.1-DRAFT-0.5B-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:457342d1546ba780d6db91e201486fd3f744493fdf3e68aaf691bcea1bfe78b6 +size 1193579872 diff --git a/alamios_Mistral-Small-3.1-DRAFT-0.5B.imatrix b/alamios_Mistral-Small-3.1-DRAFT-0.5B.imatrix new file mode 100644 index 0000000..0fec0f1 Binary files /dev/null and b/alamios_Mistral-Small-3.1-DRAFT-0.5B.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