初始化项目，由ModelHub XC社区提供模型

Model: bartowski/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,85 @@
+*.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
+ 
+*.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
+
+Tralalabs_Pythia-6.9B-Instruct-v1-Merged-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
+Tralalabs_Pythia-6.9B-Instruct-v1-Merged-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+
+Tralalabs_Pythia-6.9B-Instruct-v1-Merged-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Tralalabs_Pythia-6.9B-Instruct-v1-Merged-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+
+Tralalabs_Pythia-6.9B-Instruct-v1-Merged-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Tralalabs_Pythia-6.9B-Instruct-v1-Merged-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
+
+Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+
+Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+
+Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
+
+Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+
+Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+
+Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+
+Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+
+Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+
+Tralalabs_Pythia-6.9B-Instruct-v1-Merged-bf16.gguf filter=lfs diff=lfs merge=lfs -text
+Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+
+Tralalabs_Pythia-6.9B-Instruct-v1-Merged-imatrix.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,200 @@
+---
+quantized_by: bartowski
+pipeline_tag: text-generation
+base_model: Tralalabs/Pythia-6.9B-Instruct-v1-Merged
+license: apache-2.0
+datasets:
+- timdettmers/openassistant-guanaco
+- allenai/tulu-v2-sft-mixture
+language:
+- en
+- es
+- de
+- ru
+- ja
+- fr
+- pl
+- vi
+- zh
+- hu
+- ko
+- ca
+- eu
+tags:
+- pythia
+- ai
+- agent
+- chat
+- free
+- chatgpt
+- opensource
+- pythia6.9b
+base_model_relation: quantized
+---
+
+## Llamacpp imatrix Quantizations of Pythia-6.9B-Instruct-v1-Merged by Tralalabs
+
+Using <a href="https://github.com/ggml-org/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggml-org/llama.cpp/releases/tag/b9590">b9590</a> for quantization.
+
+Original model: https://huggingface.co/Tralalabs/Pythia-6.9B-Instruct-v1-Merged
+
+All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/82ae9b520227f57d79ba04add13d0d0d)
+
+Run them in your choice of tools:
+
+- [llama.cpp](https://github.com/ggml-org/llama.cpp)
+- [ramalama](https://github.com/containers/ramalama)
+- [LM Studio](https://lmstudio.ai/)
+- [koboldcpp](https://github.com/LostRuins/koboldcpp)
+- [Jan AI](https://www.jan.ai/)
+- [Text Generation Web UI](https://github.com/oobabooga/text-generation-webui)
+- [LoLLMs](https://github.com/ParisNeo/lollms)
+- [Atomic Chat](https://atomic.chat/)
+
+Note: if it's a newly supported model, you may need to wait for an update from the developers.
+
+## Prompt format
+
+No prompt format found, check original model page
+
+## Download a file (not the whole branch) from below:
+
+| Filename | Quant type | File Size | Split | Description |
+| -------- | ---------- | --------- | ----- | ----------- |
+| [Pythia-6.9B-Instruct-v1-Merged-bf16.gguf](https://huggingface.co/bartowski/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-GGUF/blob/main/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-bf16.gguf) | bf16 | 13.72GB | false | Full BF16 weights. |
+| [Pythia-6.9B-Instruct-v1-Merged-Q8_0.gguf](https://huggingface.co/bartowski/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-GGUF/blob/main/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q8_0.gguf) | Q8_0 | 7.29GB | false | Extremely high quality, generally unneeded but max available quant. |
+| [Pythia-6.9B-Instruct-v1-Merged-Q6_K_L.gguf](https://huggingface.co/bartowski/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-GGUF/blob/main/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q6_K_L.gguf) | Q6_K_L | 6.25GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
+| [Pythia-6.9B-Instruct-v1-Merged-Q6_K.gguf](https://huggingface.co/bartowski/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-GGUF/blob/main/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q6_K.gguf) | Q6_K | 6.15GB | false | Very high quality, near perfect, *recommended*. |
+| [Pythia-6.9B-Instruct-v1-Merged-Q5_K_L.gguf](https://huggingface.co/bartowski/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-GGUF/blob/main/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q5_K_L.gguf) | Q5_K_L | 5.69GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
+| [Pythia-6.9B-Instruct-v1-Merged-Q5_K_M.gguf](https://huggingface.co/bartowski/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-GGUF/blob/main/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q5_K_M.gguf) | Q5_K_M | 5.57GB | false | High quality, *recommended*. |
+| [Pythia-6.9B-Instruct-v1-Merged-Q5_K_S.gguf](https://huggingface.co/bartowski/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-GGUF/blob/main/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q5_K_S.gguf) | Q5_K_S | 4.96GB | false | High quality, *recommended*. |
+| [Pythia-6.9B-Instruct-v1-Merged-Q4_K_L.gguf](https://huggingface.co/bartowski/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-GGUF/blob/main/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q4_K_L.gguf) | Q4_K_L | 4.83GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
+| [Pythia-6.9B-Instruct-v1-Merged-Q4_K_M.gguf](https://huggingface.co/bartowski/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-GGUF/blob/main/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q4_K_M.gguf) | Q4_K_M | 4.68GB | false | Good quality, default size for most use cases, *recommended*. |
+| [Pythia-6.9B-Instruct-v1-Merged-Q4_1.gguf](https://huggingface.co/bartowski/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-GGUF/blob/main/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q4_1.gguf) | Q4_1 | 4.33GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
+| [Pythia-6.9B-Instruct-v1-Merged-Q3_K_XL.gguf](https://huggingface.co/bartowski/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-GGUF/blob/main/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q3_K_XL.gguf) | Q3_K_XL | 4.26GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
+| [Pythia-6.9B-Instruct-v1-Merged-Q4_K_S.gguf](https://huggingface.co/bartowski/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-GGUF/blob/main/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q4_K_S.gguf) | Q4_K_S | 4.15GB | false | Slightly lower quality with more space savings, *recommended*. |
+| [Pythia-6.9B-Instruct-v1-Merged-Q3_K_L.gguf](https://huggingface.co/bartowski/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-GGUF/blob/main/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q3_K_L.gguf) | Q3_K_L | 4.08GB | false | Lower quality but usable, good for low RAM availability. |
+| [Pythia-6.9B-Instruct-v1-Merged-Q4_0.gguf](https://huggingface.co/bartowski/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-GGUF/blob/main/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q4_0.gguf) | Q4_0 | 3.93GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
+| [Pythia-6.9B-Instruct-v1-Merged-IQ4_NL.gguf](https://huggingface.co/bartowski/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-GGUF/blob/main/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-IQ4_NL.gguf) | IQ4_NL | 3.92GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
+| [Pythia-6.9B-Instruct-v1-Merged-Q3_K_M.gguf](https://huggingface.co/bartowski/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-GGUF/blob/main/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q3_K_M.gguf) | Q3_K_M | 3.82GB | false | Low quality. |
+| [Pythia-6.9B-Instruct-v1-Merged-IQ4_XS.gguf](https://huggingface.co/bartowski/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-GGUF/blob/main/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-IQ4_XS.gguf) | IQ4_XS | 3.71GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
+| [Pythia-6.9B-Instruct-v1-Merged-IQ3_M.gguf](https://huggingface.co/bartowski/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-GGUF/blob/main/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-IQ3_M.gguf) | IQ3_M | 3.56GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
+| [Pythia-6.9B-Instruct-v1-Merged-Q3_K_S.gguf](https://huggingface.co/bartowski/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-GGUF/blob/main/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q3_K_S.gguf) | Q3_K_S | 3.45GB | false | Low quality, not recommended. |
+| [Pythia-6.9B-Instruct-v1-Merged-IQ3_XS.gguf](https://huggingface.co/bartowski/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-GGUF/blob/main/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-IQ3_XS.gguf) | IQ3_XS | 3.37GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
+| [Pythia-6.9B-Instruct-v1-Merged-IQ3_XXS.gguf](https://huggingface.co/bartowski/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-GGUF/blob/main/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-IQ3_XXS.gguf) | IQ3_XXS | 3.22GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
+| [Pythia-6.9B-Instruct-v1-Merged-Q2_K_L.gguf](https://huggingface.co/bartowski/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-GGUF/blob/main/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q2_K_L.gguf) | Q2_K_L | 3.21GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
+| [Pythia-6.9B-Instruct-v1-Merged-Q2_K.gguf](https://huggingface.co/bartowski/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-GGUF/blob/main/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q2_K.gguf) | Q2_K | 3.01GB | false | Very low quality but surprisingly usable. |
+| [Pythia-6.9B-Instruct-v1-Merged-IQ2_M.gguf](https://huggingface.co/bartowski/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-GGUF/blob/main/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-IQ2_M.gguf) | IQ2_M | 2.69GB | 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
+
+<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/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-GGUF --include "Tralalabs_Pythia-6.9B-Instruct-v1-Merged-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/Tralalabs_Pythia-6.9B-Instruct-v1-Merged-GGUF --include "Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q8_0/*" --local-dir ./
+```
+
+You can either specify a new local-dir (Tralalabs_Pythia-6.9B-Instruct-v1-Merged-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/ggml-org/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/ggml-org/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/ggml-org/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/ggml-org/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

Tralalabs_Pythia-6.9B-Instruct-v1-Merged-IQ2_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5682c15d8b150180f7be32ad7a3763263d4212e7c4f40edba393ee7289694558
+size 2685748000

Tralalabs_Pythia-6.9B-Instruct-v1-Merged-IQ3_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e92dda1b4ce40d23d43c36688c9dd88c2cabeb79ce8089bff597150a14082ff
+size 3557286688

Tralalabs_Pythia-6.9B-Instruct-v1-Merged-IQ3_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8461d5f3d8f99cf9bc01810d0da2479157608ead70df682db6b8bea08b8e0ae5
+size 3374834464

Tralalabs_Pythia-6.9B-Instruct-v1-Merged-IQ3_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7817d77c8845a12d7c7bfbe795def3fde1f1c0d783d5dfbaf14072c233dc0d4c
+size 3221570336

Tralalabs_Pythia-6.9B-Instruct-v1-Merged-IQ4_NL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffde8ecb2216208c43196b98a850890a294890b7a27d571db58cccb2fd402b7e
+size 3918168864

Tralalabs_Pythia-6.9B-Instruct-v1-Merged-IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0694c84ffe6c91aac8c2127f334fe9383f7a4ec842741090fd466d79be3e1779
+size 3710386976

Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28ce61c15776f348b665a8f0749ff27e5f3653ad0aabee93a250bdd9b6e53d94
+size 3009921824

Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q2_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdfd0524b37a9b905c42bbd4b7d511ff7b0203594d85d3b703679dc370806105
+size 3211649824

Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab98cc7526fc4e85ad6486a721eaca7e1ab19f1d308b63e51833ad39a5c37cc9
+size 4075283232

Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7c2c8ffb298ed8f6500cc1a4c058623879a666e6b031731d74ffc4f332cfa2b
+size 3823624992

Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49caaba87885c2dcb05f9bfbfd6eb04bc0af879178c4203f68fabb3ed57d4f68
+size 3450331936

Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q3_K_XL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:525009e398969799a9458b0e087cf810a6b994ca81028e2bb2fbfc19ef4948b5
+size 4256031520

Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d50b6c0c711a9f4b17dfb2968b26b599012b0b1f6146eed4aa439f19f03b4f80
+size 3934946080

Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebea917961311cb58fce56d1fe8a7af2a8577f40068dcad79e1a8457c16d6353
+size 4333732640

Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q4_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48688e7b761c78c160ce5041964cfe12d0ae50549d735e8f86ab227afbd174c5
+size 4830651168

Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386231c04c702d2bb103b4187ed63fbf116841ffd8d44f67ab8a7e84393e8ed2
+size 4677337888

Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56e8a87fcd786fe16f8ccf1cd1d883e6aa6537914d13134c02cd87184679e853
+size 4153049888

Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q5_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50855563978dddd580a88991adae1f0be3812c15e5a4bb361553ed3d0ef10981
+size 5694677792

Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1817cc325f6ed0f8eb59b6333b76e3640e4b2bfe9ac0049981d7a04cf8f1da3e
+size 5567185696

Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43b363ff6fa1e3e2e5cf8116a43c21b8421ecf31b207c61d43d1725faa246c2c
+size 4963205920

Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91e1a5137878bf19a8df779dd1587e97ff4f20de20968d4705b3149c0ba08852
+size 6152463136

Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q6_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ada810ccce782cd47a2336a6ca8a04681ac4454a7473a41d886f5b90bc4b06f
+size 6252520224

Tralalabs_Pythia-6.9B-Instruct-v1-Merged-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:437c34f34428cae1a91b2261f370d4c52a55ee600a04578cdb38d0aa3e27ddf9
+size 7292707616

Tralalabs_Pythia-6.9B-Instruct-v1-Merged-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a28dfcb9a9b3ea4d47279d93b27c7340c44fbc1291275b919bce73c041bbd52
+size 13719822816

Tralalabs_Pythia-6.9B-Instruct-v1-Merged-imatrix.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1b071229666e38a482e7537ca0906d2f38f5e671162fdc5b759ccbc37ce327b
+size 3690080

configuration.json

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