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
+TinyMistral-248M-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+TinyMistral-248M-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+TinyMistral-248M-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+TinyMistral-248M-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+TinyMistral-248M-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+TinyMistral-248M-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+TinyMistral-248M-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+TinyMistral-248M-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+TinyMistral-248M-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+TinyMistral-248M-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+TinyMistral-248M-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+TinyMistral-248M-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,84 @@
+---
+license: apache-2.0
+datasets:
+- Skylion007/openwebtext
+- JeanKaddour/minipile
+language:
+- en
+pipeline_tag: text-generation
+inference:
+  parameters:
+    do_sample: true
+    temperature: 0.5
+    top_p: 0.5
+    top_k: 50
+    max_new_tokens: 250
+    repetition_penalty: 1.176
+base_model: Locutusque/TinyMistral-248M
+tags:
+- TensorBlock
+- GGUF
+---
+
+<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>
+
+## Locutusque/TinyMistral-248M - GGUF
+
+This repo contains GGUF format model files for [Locutusque/TinyMistral-248M](https://huggingface.co/Locutusque/TinyMistral-248M).
+
+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 |
+| -------- | ---------- | --------- | ----------- |
+| [TinyMistral-248M-Q2_K.gguf](https://huggingface.co/tensorblock/TinyMistral-248M-GGUF/tree/main/TinyMistral-248M-Q2_K.gguf) | Q2_K | 0.098 GB | smallest, significant quality loss - not recommended for most purposes |
+| [TinyMistral-248M-Q3_K_S.gguf](https://huggingface.co/tensorblock/TinyMistral-248M-GGUF/tree/main/TinyMistral-248M-Q3_K_S.gguf) | Q3_K_S | 0.112 GB | very small, high quality loss |
+| [TinyMistral-248M-Q3_K_M.gguf](https://huggingface.co/tensorblock/TinyMistral-248M-GGUF/tree/main/TinyMistral-248M-Q3_K_M.gguf) | Q3_K_M | 0.120 GB | very small, high quality loss |
+| [TinyMistral-248M-Q3_K_L.gguf](https://huggingface.co/tensorblock/TinyMistral-248M-GGUF/tree/main/TinyMistral-248M-Q3_K_L.gguf) | Q3_K_L | 0.128 GB | small, substantial quality loss |
+| [TinyMistral-248M-Q4_0.gguf](https://huggingface.co/tensorblock/TinyMistral-248M-GGUF/tree/main/TinyMistral-248M-Q4_0.gguf) | Q4_0 | 0.139 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [TinyMistral-248M-Q4_K_S.gguf](https://huggingface.co/tensorblock/TinyMistral-248M-GGUF/tree/main/TinyMistral-248M-Q4_K_S.gguf) | Q4_K_S | 0.139 GB | small, greater quality loss |
+| [TinyMistral-248M-Q4_K_M.gguf](https://huggingface.co/tensorblock/TinyMistral-248M-GGUF/tree/main/TinyMistral-248M-Q4_K_M.gguf) | Q4_K_M | 0.145 GB | medium, balanced quality - recommended |
+| [TinyMistral-248M-Q5_0.gguf](https://huggingface.co/tensorblock/TinyMistral-248M-GGUF/tree/main/TinyMistral-248M-Q5_0.gguf) | Q5_0 | 0.164 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [TinyMistral-248M-Q5_K_S.gguf](https://huggingface.co/tensorblock/TinyMistral-248M-GGUF/tree/main/TinyMistral-248M-Q5_K_S.gguf) | Q5_K_S | 0.164 GB | large, low quality loss - recommended |
+| [TinyMistral-248M-Q5_K_M.gguf](https://huggingface.co/tensorblock/TinyMistral-248M-GGUF/tree/main/TinyMistral-248M-Q5_K_M.gguf) | Q5_K_M | 0.167 GB | large, very low quality loss - recommended |
+| [TinyMistral-248M-Q6_K.gguf](https://huggingface.co/tensorblock/TinyMistral-248M-GGUF/tree/main/TinyMistral-248M-Q6_K.gguf) | Q6_K | 0.190 GB | very large, extremely low quality loss |
+| [TinyMistral-248M-Q8_0.gguf](https://huggingface.co/tensorblock/TinyMistral-248M-GGUF/tree/main/TinyMistral-248M-Q8_0.gguf) | Q8_0 | 0.246 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/TinyMistral-248M-GGUF --include "TinyMistral-248M-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/TinyMistral-248M-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

TinyMistral-248M-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d787955aae1a6eb0a7cb9922991d3c8ac6feb4d2fc16ee0b4b779c45d14df24b
+size 105459232

TinyMistral-248M-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c68f7a12481247514d94334f7487b5b8ea7127b27baf9e41330c4de0053407a5
+size 137222176

TinyMistral-248M-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f73069176b61c23d237ab29e82b35735cf20610dadb818b9bfd6d32a58685f4c
+size 129030176

TinyMistral-248M-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:441b1cc8a58f96a0a426ec27f5ce463b80a0ae08349ec437e52278ff664d7fad
+size 120191008

TinyMistral-248M-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea5d826625059a0a12fb9ca785d8932ff4cf01cb64779523acd5caeff32c8a89
+size 148775616

TinyMistral-248M-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57631147f51d0698ac0d694019401e258d0bcbe3a02bfec8206dc1813900dd6e
+size 155669184

TinyMistral-248M-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3034d3fdcb79defb8eedf4d00c74b40f4683e5e128b1a28162a86d81f351b835
+size 149430976

TinyMistral-248M-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00160ae859370e29b1169fbbfd809e908cefd07a9ee6553beb00a81b1fdfd5f2
+size 175678784

TinyMistral-248M-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:696a0dc676af0c465c3739830dc39795022b8e6baee6b16cc04fcfe5076a6572
+size 179230016

TinyMistral-248M-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddd0a5e65f6ea0a8be762cd5297f33d42a6c3140432a95949a1e8c606394c5fa
+size 175678784

TinyMistral-248M-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ab43d0afd9138241e67cdf99c3702e4c11ef9d0ea63d9c34394dce2b609b103
+size 204263424

TinyMistral-248M-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c68c7cc864b98174392f6e18d35959df007aa0c9cffaac9b675a72aeecd7e4de
+size 264325504