Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,15 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+pythia-1.4b-deduped-v0-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+pythia-1.4b-deduped-v0-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+pythia-1.4b-deduped-v0-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+pythia-1.4b-deduped-v0-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+pythia-1.4b-deduped-v0-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+pythia-1.4b-deduped-v0-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+pythia-1.4b-deduped-v0-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+pythia-1.4b-deduped-v0-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+pythia-1.4b-deduped-v0-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+pythia-1.4b-deduped-v0-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+pythia-1.4b-deduped-v0-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+pythia-1.4b-deduped-v0-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,78 @@
+---
+language:
+- en
+tags:
+- pytorch
+- causal-lm
+- pythia
+- pythia_v0
+- TensorBlock
+- GGUF
+license: apache-2.0
+datasets:
+- EleutherAI/the_pile_deduplicated
+base_model: EleutherAI/pythia-1.4b-deduped-v0
+---
+
+<div style="width: auto; margin-left: auto; margin-right: auto">
+<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
+</div>
+<div style="display: flex; justify-content: space-between; width: 100%;">
+    <div style="display: flex; flex-direction: column; align-items: flex-start;">
+        <p style="margin-top: 0.5em; margin-bottom: 0em;">
+            Feedback and support: TensorBlock's  <a href="https://x.com/tensorblock_aoi">Twitter/X</a>, <a href="https://t.me/TensorBlock">Telegram Group</a> and <a href="https://x.com/tensorblock_aoi">Discord server</a>
+        </p>
+    </div>
+</div>
+
+## EleutherAI/pythia-1.4b-deduped-v0 - GGUF
+
+This repo contains GGUF format model files for [EleutherAI/pythia-1.4b-deduped-v0](https://huggingface.co/EleutherAI/pythia-1.4b-deduped-v0).
+
+The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
+
+## Prompt template
+
+```
+
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [pythia-1.4b-deduped-v0-Q2_K.gguf](https://huggingface.co/tensorblock/pythia-1.4b-deduped-v0-GGUF/tree/main/pythia-1.4b-deduped-v0-Q2_K.gguf) | Q2_K | 0.531 GB | smallest, significant quality loss - not recommended for most purposes |
+| [pythia-1.4b-deduped-v0-Q3_K_S.gguf](https://huggingface.co/tensorblock/pythia-1.4b-deduped-v0-GGUF/tree/main/pythia-1.4b-deduped-v0-Q3_K_S.gguf) | Q3_K_S | 0.607 GB | very small, high quality loss |
+| [pythia-1.4b-deduped-v0-Q3_K_M.gguf](https://huggingface.co/tensorblock/pythia-1.4b-deduped-v0-GGUF/tree/main/pythia-1.4b-deduped-v0-Q3_K_M.gguf) | Q3_K_M | 0.709 GB | very small, high quality loss |
+| [pythia-1.4b-deduped-v0-Q3_K_L.gguf](https://huggingface.co/tensorblock/pythia-1.4b-deduped-v0-GGUF/tree/main/pythia-1.4b-deduped-v0-Q3_K_L.gguf) | Q3_K_L | 0.766 GB | small, substantial quality loss |
+| [pythia-1.4b-deduped-v0-Q4_0.gguf](https://huggingface.co/tensorblock/pythia-1.4b-deduped-v0-GGUF/tree/main/pythia-1.4b-deduped-v0-Q4_0.gguf) | Q4_0 | 0.770 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [pythia-1.4b-deduped-v0-Q4_K_S.gguf](https://huggingface.co/tensorblock/pythia-1.4b-deduped-v0-GGUF/tree/main/pythia-1.4b-deduped-v0-Q4_K_S.gguf) | Q4_K_S | 0.775 GB | small, greater quality loss |
+| [pythia-1.4b-deduped-v0-Q4_K_M.gguf](https://huggingface.co/tensorblock/pythia-1.4b-deduped-v0-GGUF/tree/main/pythia-1.4b-deduped-v0-Q4_K_M.gguf) | Q4_K_M | 0.853 GB | medium, balanced quality - recommended |
+| [pythia-1.4b-deduped-v0-Q5_0.gguf](https://huggingface.co/tensorblock/pythia-1.4b-deduped-v0-GGUF/tree/main/pythia-1.4b-deduped-v0-Q5_0.gguf) | Q5_0 | 0.922 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [pythia-1.4b-deduped-v0-Q5_K_S.gguf](https://huggingface.co/tensorblock/pythia-1.4b-deduped-v0-GGUF/tree/main/pythia-1.4b-deduped-v0-Q5_K_S.gguf) | Q5_K_S | 0.922 GB | large, low quality loss - recommended |
+| [pythia-1.4b-deduped-v0-Q5_K_M.gguf](https://huggingface.co/tensorblock/pythia-1.4b-deduped-v0-GGUF/tree/main/pythia-1.4b-deduped-v0-Q5_K_M.gguf) | Q5_K_M | 0.984 GB | large, very low quality loss - recommended |
+| [pythia-1.4b-deduped-v0-Q6_K.gguf](https://huggingface.co/tensorblock/pythia-1.4b-deduped-v0-GGUF/tree/main/pythia-1.4b-deduped-v0-Q6_K.gguf) | Q6_K | 1.084 GB | very large, extremely low quality loss |
+| [pythia-1.4b-deduped-v0-Q8_0.gguf](https://huggingface.co/tensorblock/pythia-1.4b-deduped-v0-GGUF/tree/main/pythia-1.4b-deduped-v0-Q8_0.gguf) | Q8_0 | 1.403 GB | very large, extremely low quality loss - not recommended |
+
+
+## Downloading instruction
+
+### Command line
+
+Firstly, install Huggingface Client
+
+```shell
+pip install -U "huggingface_hub[cli]"
+```
+
+Then, downoad the individual model file the a local directory
+
+```shell
+huggingface-cli download tensorblock/pythia-1.4b-deduped-v0-GGUF --include "pythia-1.4b-deduped-v0-Q2_K.gguf" --local-dir MY_LOCAL_DIR
+```
+
+If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
+
+```shell
+huggingface-cli download tensorblock/pythia-1.4b-deduped-v0-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

pythia-1.4b-deduped-v0-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5541ef90baa8048af0b4a7cf59f18e38267950a1143dd4d398da7cd1952b153f
+size 570152576

pythia-1.4b-deduped-v0-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61f8e394e01c348ca1f4c8e2c7e6c619c0d2ae7833324bacd67b98365d09eabd
+size 822050432

pythia-1.4b-deduped-v0-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71107f479b399303444e96c8b4ebf15faa466286b6fa5afff0d76e263bb8bcae
+size 761233024

pythia-1.4b-deduped-v0-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7ca297a4a3b622abfbdd0fd13ab6f739a5d3acf09ffb5b7bb8c6822811b9533
+size 652181120

pythia-1.4b-deduped-v0-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3fff20ec624576ee9ace1fd0720157d92d60335089e501ecbbbdf8324b7dafc
+size 826295936

pythia-1.4b-deduped-v0-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c2155e34603f15ca18817c50514c1d59cbc383a1749dcf3385f7023bf215e9b
+size 915949184

pythia-1.4b-deduped-v0-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e92bc9beaf208b6007a6ab1ab95672d67d1a39ca3a4dabc8a4f851a9020fe8f4
+size 832587392

pythia-1.4b-deduped-v0-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e7081f9e2069db9d093cdf4f95079f596c4c30e7563324bdeebfe4b8344ceda
+size 990168704

pythia-1.4b-deduped-v0-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d7b952c65b186668ba1349196a7be08219a4825824f6243195928175dbae55d
+size 1057015424

pythia-1.4b-deduped-v0-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ba9db332cc8f381f4d91abc95cfd72bf8b5444a92921db46eefe6d18cd178ee
+size 990168704

pythia-1.4b-deduped-v0-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e33268e4f6a287979ac4046cd7354c0b01b04267af37306c9cfe727677b24ae4
+size 1164283520

pythia-1.4b-deduped-v0-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9555e61c401dc47e632edd479106ddf3b803b5e314192156fba934dd75d2e43d
+size 1506737792