初始化项目，由ModelHub XC社区提供模型

Model: bartowski/Trappu_Magnum-Picaro-0.7-v2-12b-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,49 @@
+*.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
+
+Trappu_Magnum-Picaro-0.7-v2-12b.imatrix filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,273 @@
+---
+quantized_by: bartowski
+pipeline_tag: text-generation
+license: apache-2.0
+base_model: Trappu/Magnum-Picaro-0.7-v2-12b
+base_model_relation: quantized
+tags:
+- merge
+- mergekit
+- lazymergekit
+- anthracite-org/magnum-v2-12b
+- Trappu/Nemo-Picaro-12B
+model-index:
+- name: Magnum-Picaro-0.7-v2-12b
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 30.03
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Trappu/Magnum-Picaro-0.7-v2-12b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 35.75
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Trappu/Magnum-Picaro-0.7-v2-12b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 4.76
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Trappu/Magnum-Picaro-0.7-v2-12b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 9.73
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Trappu/Magnum-Picaro-0.7-v2-12b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 19.56
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Trappu/Magnum-Picaro-0.7-v2-12b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 28.67
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Trappu/Magnum-Picaro-0.7-v2-12b
+      name: Open LLM Leaderboard
+---
+
+## Llamacpp imatrix Quantizations of Magnum-Picaro-0.7-v2-12b by Trappu
+
+Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b5074">b5074</a> for quantization.
+
+Original model: https://huggingface.co/Trappu/Magnum-Picaro-0.7-v2-12b
+
+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 |
+| -------- | ---------- | --------- | ----- | ----------- |
+| [Magnum-Picaro-0.7-v2-12b-bf16.gguf](https://huggingface.co/bartowski/Trappu_Magnum-Picaro-0.7-v2-12b-GGUF/blob/main/Trappu_Magnum-Picaro-0.7-v2-12b-bf16.gguf) | bf16 | 24.50GB | false | Full BF16 weights. |
+| [Magnum-Picaro-0.7-v2-12b-Q8_0.gguf](https://huggingface.co/bartowski/Trappu_Magnum-Picaro-0.7-v2-12b-GGUF/blob/main/Trappu_Magnum-Picaro-0.7-v2-12b-Q8_0.gguf) | Q8_0 | 13.02GB | false | Extremely high quality, generally unneeded but max available quant. |
+| [Magnum-Picaro-0.7-v2-12b-Q6_K_L.gguf](https://huggingface.co/bartowski/Trappu_Magnum-Picaro-0.7-v2-12b-GGUF/blob/main/Trappu_Magnum-Picaro-0.7-v2-12b-Q6_K_L.gguf) | Q6_K_L | 10.38GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
+| [Magnum-Picaro-0.7-v2-12b-Q6_K.gguf](https://huggingface.co/bartowski/Trappu_Magnum-Picaro-0.7-v2-12b-GGUF/blob/main/Trappu_Magnum-Picaro-0.7-v2-12b-Q6_K.gguf) | Q6_K | 10.06GB | false | Very high quality, near perfect, *recommended*. |
+| [Magnum-Picaro-0.7-v2-12b-Q5_K_L.gguf](https://huggingface.co/bartowski/Trappu_Magnum-Picaro-0.7-v2-12b-GGUF/blob/main/Trappu_Magnum-Picaro-0.7-v2-12b-Q5_K_L.gguf) | Q5_K_L | 9.14GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
+| [Magnum-Picaro-0.7-v2-12b-Q5_K_M.gguf](https://huggingface.co/bartowski/Trappu_Magnum-Picaro-0.7-v2-12b-GGUF/blob/main/Trappu_Magnum-Picaro-0.7-v2-12b-Q5_K_M.gguf) | Q5_K_M | 8.73GB | false | High quality, *recommended*. |
+| [Magnum-Picaro-0.7-v2-12b-Q5_K_S.gguf](https://huggingface.co/bartowski/Trappu_Magnum-Picaro-0.7-v2-12b-GGUF/blob/main/Trappu_Magnum-Picaro-0.7-v2-12b-Q5_K_S.gguf) | Q5_K_S | 8.52GB | false | High quality, *recommended*. |
+| [Magnum-Picaro-0.7-v2-12b-Q4_K_L.gguf](https://huggingface.co/bartowski/Trappu_Magnum-Picaro-0.7-v2-12b-GGUF/blob/main/Trappu_Magnum-Picaro-0.7-v2-12b-Q4_K_L.gguf) | Q4_K_L | 7.98GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
+| [Magnum-Picaro-0.7-v2-12b-Q4_1.gguf](https://huggingface.co/bartowski/Trappu_Magnum-Picaro-0.7-v2-12b-GGUF/blob/main/Trappu_Magnum-Picaro-0.7-v2-12b-Q4_1.gguf) | Q4_1 | 7.80GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
+| [Magnum-Picaro-0.7-v2-12b-Q4_K_M.gguf](https://huggingface.co/bartowski/Trappu_Magnum-Picaro-0.7-v2-12b-GGUF/blob/main/Trappu_Magnum-Picaro-0.7-v2-12b-Q4_K_M.gguf) | Q4_K_M | 7.48GB | false | Good quality, default size for most use cases, *recommended*. |
+| [Magnum-Picaro-0.7-v2-12b-Q3_K_XL.gguf](https://huggingface.co/bartowski/Trappu_Magnum-Picaro-0.7-v2-12b-GGUF/blob/main/Trappu_Magnum-Picaro-0.7-v2-12b-Q3_K_XL.gguf) | Q3_K_XL | 7.15GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
+| [Magnum-Picaro-0.7-v2-12b-Q4_K_S.gguf](https://huggingface.co/bartowski/Trappu_Magnum-Picaro-0.7-v2-12b-GGUF/blob/main/Trappu_Magnum-Picaro-0.7-v2-12b-Q4_K_S.gguf) | Q4_K_S | 7.12GB | false | Slightly lower quality with more space savings, *recommended*. |
+| [Magnum-Picaro-0.7-v2-12b-IQ4_NL.gguf](https://huggingface.co/bartowski/Trappu_Magnum-Picaro-0.7-v2-12b-GGUF/blob/main/Trappu_Magnum-Picaro-0.7-v2-12b-IQ4_NL.gguf) | IQ4_NL | 7.10GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
+| [Magnum-Picaro-0.7-v2-12b-Q4_0.gguf](https://huggingface.co/bartowski/Trappu_Magnum-Picaro-0.7-v2-12b-GGUF/blob/main/Trappu_Magnum-Picaro-0.7-v2-12b-Q4_0.gguf) | Q4_0 | 7.09GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
+| [Magnum-Picaro-0.7-v2-12b-IQ4_XS.gguf](https://huggingface.co/bartowski/Trappu_Magnum-Picaro-0.7-v2-12b-GGUF/blob/main/Trappu_Magnum-Picaro-0.7-v2-12b-IQ4_XS.gguf) | IQ4_XS | 6.74GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
+| [Magnum-Picaro-0.7-v2-12b-Q3_K_L.gguf](https://huggingface.co/bartowski/Trappu_Magnum-Picaro-0.7-v2-12b-GGUF/blob/main/Trappu_Magnum-Picaro-0.7-v2-12b-Q3_K_L.gguf) | Q3_K_L | 6.56GB | false | Lower quality but usable, good for low RAM availability. |
+| [Magnum-Picaro-0.7-v2-12b-Q3_K_M.gguf](https://huggingface.co/bartowski/Trappu_Magnum-Picaro-0.7-v2-12b-GGUF/blob/main/Trappu_Magnum-Picaro-0.7-v2-12b-Q3_K_M.gguf) | Q3_K_M | 6.08GB | false | Low quality. |
+| [Magnum-Picaro-0.7-v2-12b-IQ3_M.gguf](https://huggingface.co/bartowski/Trappu_Magnum-Picaro-0.7-v2-12b-GGUF/blob/main/Trappu_Magnum-Picaro-0.7-v2-12b-IQ3_M.gguf) | IQ3_M | 5.72GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
+| [Magnum-Picaro-0.7-v2-12b-Q3_K_S.gguf](https://huggingface.co/bartowski/Trappu_Magnum-Picaro-0.7-v2-12b-GGUF/blob/main/Trappu_Magnum-Picaro-0.7-v2-12b-Q3_K_S.gguf) | Q3_K_S | 5.53GB | false | Low quality, not recommended. |
+| [Magnum-Picaro-0.7-v2-12b-Q2_K_L.gguf](https://huggingface.co/bartowski/Trappu_Magnum-Picaro-0.7-v2-12b-GGUF/blob/main/Trappu_Magnum-Picaro-0.7-v2-12b-Q2_K_L.gguf) | Q2_K_L | 5.45GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
+| [Magnum-Picaro-0.7-v2-12b-IQ3_XS.gguf](https://huggingface.co/bartowski/Trappu_Magnum-Picaro-0.7-v2-12b-GGUF/blob/main/Trappu_Magnum-Picaro-0.7-v2-12b-IQ3_XS.gguf) | IQ3_XS | 5.31GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
+| [Magnum-Picaro-0.7-v2-12b-IQ3_XXS.gguf](https://huggingface.co/bartowski/Trappu_Magnum-Picaro-0.7-v2-12b-GGUF/blob/main/Trappu_Magnum-Picaro-0.7-v2-12b-IQ3_XXS.gguf) | IQ3_XXS | 4.95GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
+| [Magnum-Picaro-0.7-v2-12b-Q2_K.gguf](https://huggingface.co/bartowski/Trappu_Magnum-Picaro-0.7-v2-12b-GGUF/blob/main/Trappu_Magnum-Picaro-0.7-v2-12b-Q2_K.gguf) | Q2_K | 4.79GB | false | Very low quality but surprisingly usable. |
+| [Magnum-Picaro-0.7-v2-12b-IQ2_M.gguf](https://huggingface.co/bartowski/Trappu_Magnum-Picaro-0.7-v2-12b-GGUF/blob/main/Trappu_Magnum-Picaro-0.7-v2-12b-IQ2_M.gguf) | IQ2_M | 4.44GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
+| [Magnum-Picaro-0.7-v2-12b-IQ2_S.gguf](https://huggingface.co/bartowski/Trappu_Magnum-Picaro-0.7-v2-12b-GGUF/blob/main/Trappu_Magnum-Picaro-0.7-v2-12b-IQ2_S.gguf) | IQ2_S | 4.14GB | false | Low quality, uses SOTA techniques to be 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
+
+<details>
+  <summary>Click to view download instructions</summary>
+
+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/Trappu_Magnum-Picaro-0.7-v2-12b-GGUF --include "Trappu_Magnum-Picaro-0.7-v2-12b-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/Trappu_Magnum-Picaro-0.7-v2-12b-GGUF --include "Trappu_Magnum-Picaro-0.7-v2-12b-Q8_0/*" --local-dir ./
+```
+
+You can either specify a new local-dir (Trappu_Magnum-Picaro-0.7-v2-12b-Q8_0) or download them all in place (./)
+
+</details>
+
+## 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.
+
+<details>
+  <summary>Click to view Q4_0_X_X information (deprecated</summary>
+
+I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking.
+
+<details>
+  <summary>Click to view benchmarks on an AVX2 system (EPYC7702)</summary>
+
+| 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
+
+</details>
+
+</details>
+
+## Which file should I choose?
+
+<details>
+  <summary>Click here for details</summary>
+
+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.
+
+</details>
+
+## 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

Trappu_Magnum-Picaro-0.7-v2-12b-IQ2_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba238a68f64c1a61a5ea6d918fedb60122bc44b6657373ee0ac19937ee5e0c53
+size 4435023616

Trappu_Magnum-Picaro-0.7-v2-12b-IQ2_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2716641cbd9204ad66dbe81da0b3c716ef9712279f77f518e95965f4bc26b097
+size 4138473216

Trappu_Magnum-Picaro-0.7-v2-12b-IQ3_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:929858438a19e942a3e68ba719338a107ab0c52c4061403d1c655fcd02ae1b4a
+size 5722232576

Trappu_Magnum-Picaro-0.7-v2-12b-IQ3_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd49fb335888b2bb5838ca1729842728cd38a3b95eb0891eb961c31fb1aead81
+size 5306488576

Trappu_Magnum-Picaro-0.7-v2-12b-IQ3_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f17a3886a93f8c1d68f74e4581e363c58cea18de846d9a757af06c60360c4f2
+size 4945385216

Trappu_Magnum-Picaro-0.7-v2-12b-IQ4_NL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c970b4dfabbed46ea8fcf796ccd7cee8933fa1bfec333b52e5401ee9e2ac35b3
+size 7097915136

Trappu_Magnum-Picaro-0.7-v2-12b-IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f8ddf2fe320a416ed27984bd2875c945318c84c4f38c932b3b391bd3cfb87ba
+size 6742710016

Trappu_Magnum-Picaro-0.7-v2-12b-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e95aed0d0f8936917d27a4ec3d410a15ba02e8c2c0896c4b05ac481d2d37ecb1
+size 4791047936

Trappu_Magnum-Picaro-0.7-v2-12b-Q2_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c7fba994ef88a27c53f615c27f33ebeb4d642155f40fa5e5c8db79d99b4ec05
+size 5446407936

Trappu_Magnum-Picaro-0.7-v2-12b-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12c06442df797ce25abca02ece60df1f3479d05304446aae2da3b8735d85fda7
+size 6561502976

Trappu_Magnum-Picaro-0.7-v2-12b-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:475310b4f78c469076cb43157bc1dac2334c94b60d798fea1d3efb8907e6c75c
+size 6083090176

Trappu_Magnum-Picaro-0.7-v2-12b-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e18bafdfa61144208c24cad6389c3bac6754c7dcf0fbf9e0abe731a26c35f66d
+size 5534226176

Trappu_Magnum-Picaro-0.7-v2-12b-Q3_K_XL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faf94d19530be3adb75c4a9dba5cbb9b05f666e75093a6dd3305674db2d8c1ba
+size 7148705536

Trappu_Magnum-Picaro-0.7-v2-12b-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdcdd53b0fb8af95a5b320311891a4b2b9430a7687816b222c70cd246a5f2875
+size 7094638336

Trappu_Magnum-Picaro-0.7-v2-12b-Q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b9dcc012fff4818f8bbabfcec4761e29eb1cb6619598888436fe035ca935910
+size 7795218176

Trappu_Magnum-Picaro-0.7-v2-12b-Q4_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0047cc30b1178e97368addec3465ae2d620da3416b43d5e4551aa0f8062cc576
+size 7975278336

Trappu_Magnum-Picaro-0.7-v2-12b-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:989839dd7eab997a70eb8430b9df1138f9b0f35d58299d5007e6555a4a4a7f4c
+size 7477204736

Trappu_Magnum-Picaro-0.7-v2-12b-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc2112264b50882ca8dbd3f999f190b5dbdfdeacaaf491dc538710ea59df02de
+size 7120197376

Trappu_Magnum-Picaro-0.7-v2-12b-Q5_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c15808402e216778a4648f5cb62882921c96a560f1eb04959a747fb9465caa8a
+size 9141819136

Trappu_Magnum-Picaro-0.7-v2-12b-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31afcdf2f6682f7fa46971b9391399c750afa4fb7f9f6e91aadf69196d046f08
+size 8727631616

Trappu_Magnum-Picaro-0.7-v2-12b-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53f15b2fb287c9118faed8cfda77b2c393cb37c25051cf66ea7f7c8851cf3159
+size 8518735616

Trappu_Magnum-Picaro-0.7-v2-12b-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed83a7c03e58f62528075e8a71844f0c7dcb17382d1bc6a407c888aa0eaba102
+size 10056210176

Trappu_Magnum-Picaro-0.7-v2-12b-Q6_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02d63a4b09417ad965c45ceb6116276bd93f9e4ec36d9aa6554b0edf01bf74d2
+size 10381268736

Trappu_Magnum-Picaro-0.7-v2-12b-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:712f3372a291e2922d7e74348b0842b25f2c423e7278294f0063feae0b7c1b83
+size 13022369536

Trappu_Magnum-Picaro-0.7-v2-12b-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:951a4a6476be270c47d6e565de2296c9c319f805e7bf95e1220a265375b38ca8
+size 24504276448

Trappu_Magnum-Picaro-0.7-v2-12b.imatrix

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e31fcba22e232f3360c34122dcef319e63ea6c3bb1b1e6e3a84691b7529a102b
+size 7054418

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}