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
+saiga_llama3_8b-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+saiga_llama3_8b-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+saiga_llama3_8b-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+saiga_llama3_8b-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+saiga_llama3_8b-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+saiga_llama3_8b-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+saiga_llama3_8b-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+saiga_llama3_8b-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+saiga_llama3_8b-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+saiga_llama3_8b-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+saiga_llama3_8b-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+saiga_llama3_8b-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,80 @@
+---
+language:
+- ru
+datasets:
+- IlyaGusev/saiga_scored
+license: other
+license_name: llama3
+license_link: https://llama.meta.com/llama3/license/
+base_model: IlyaGusev/saiga_llama3_8b
+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>
+
+## IlyaGusev/saiga_llama3_8b - GGUF
+
+This repo contains GGUF format model files for [IlyaGusev/saiga_llama3_8b](https://huggingface.co/IlyaGusev/saiga_llama3_8b).
+
+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
+
+```
+<|begin_of_text|><|start_header_id|>system<|end_header_id|>
+
+{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
+
+{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [saiga_llama3_8b-Q2_K.gguf](https://huggingface.co/tensorblock/saiga_llama3_8b-GGUF/tree/main/saiga_llama3_8b-Q2_K.gguf) | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
+| [saiga_llama3_8b-Q3_K_S.gguf](https://huggingface.co/tensorblock/saiga_llama3_8b-GGUF/tree/main/saiga_llama3_8b-Q3_K_S.gguf) | Q3_K_S | 3.413 GB | very small, high quality loss |
+| [saiga_llama3_8b-Q3_K_M.gguf](https://huggingface.co/tensorblock/saiga_llama3_8b-GGUF/tree/main/saiga_llama3_8b-Q3_K_M.gguf) | Q3_K_M | 3.743 GB | very small, high quality loss |
+| [saiga_llama3_8b-Q3_K_L.gguf](https://huggingface.co/tensorblock/saiga_llama3_8b-GGUF/tree/main/saiga_llama3_8b-Q3_K_L.gguf) | Q3_K_L | 4.025 GB | small, substantial quality loss |
+| [saiga_llama3_8b-Q4_0.gguf](https://huggingface.co/tensorblock/saiga_llama3_8b-GGUF/tree/main/saiga_llama3_8b-Q4_0.gguf) | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [saiga_llama3_8b-Q4_K_S.gguf](https://huggingface.co/tensorblock/saiga_llama3_8b-GGUF/tree/main/saiga_llama3_8b-Q4_K_S.gguf) | Q4_K_S | 4.370 GB | small, greater quality loss |
+| [saiga_llama3_8b-Q4_K_M.gguf](https://huggingface.co/tensorblock/saiga_llama3_8b-GGUF/tree/main/saiga_llama3_8b-Q4_K_M.gguf) | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
+| [saiga_llama3_8b-Q5_0.gguf](https://huggingface.co/tensorblock/saiga_llama3_8b-GGUF/tree/main/saiga_llama3_8b-Q5_0.gguf) | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [saiga_llama3_8b-Q5_K_S.gguf](https://huggingface.co/tensorblock/saiga_llama3_8b-GGUF/tree/main/saiga_llama3_8b-Q5_K_S.gguf) | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
+| [saiga_llama3_8b-Q5_K_M.gguf](https://huggingface.co/tensorblock/saiga_llama3_8b-GGUF/tree/main/saiga_llama3_8b-Q5_K_M.gguf) | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
+| [saiga_llama3_8b-Q6_K.gguf](https://huggingface.co/tensorblock/saiga_llama3_8b-GGUF/tree/main/saiga_llama3_8b-Q6_K.gguf) | Q6_K | 6.143 GB | very large, extremely low quality loss |
+| [saiga_llama3_8b-Q8_0.gguf](https://huggingface.co/tensorblock/saiga_llama3_8b-GGUF/tree/main/saiga_llama3_8b-Q8_0.gguf) | Q8_0 | 7.954 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/saiga_llama3_8b-GGUF --include "saiga_llama3_8b-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/saiga_llama3_8b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

saiga_llama3_8b-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f776e621044c1fbe5081c42e6e1ce2f4e444d562f7902b74a41705ef1967ee0
+size 3179131648

saiga_llama3_8b-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42755ba0e5bd282d9ad850f3687dbf2b7e0bf3ef80a712fa132db4cc313da29d
+size 4321956608

saiga_llama3_8b-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8869fa12983ceb76611e49ec3c3d616e2e71795ac2ef7df20808c7beaa2ee1f2
+size 4018918144

saiga_llama3_8b-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dbf8479d3b5e18bfae35b407359243c1f6a0ce34550cb44d547a65d45a4d9ba
+size 3664499456

saiga_llama3_8b-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1a914f9535f47a42a5dc59e681931b1a468ca8b38e90cd81622da3ceb0e18d2
+size 4661211904

saiga_llama3_8b-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c77b7f05ad52b5d36e47dbec9e1f131ec530252db91f80424fc5aa1d30780435
+size 4920734464

saiga_llama3_8b-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9e579686d9bf552e7db86501be63cfe64ea2690eda0dd4fcd2d24b5628212bd
+size 4692669184

saiga_llama3_8b-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17756c05870ace1c64e2ca0d4a222e1ef88690757be2d1a56e2b269f0816fe24
+size 5599294208

saiga_llama3_8b-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:870d2f3967d60e2f43f5f45c0f56b476f4e9e3657706d024b500ed77b1d3ee8e
+size 5732987648

saiga_llama3_8b-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:101688208d89c1d721c179375da9f7855b1ed915d89058e12b89b2c3882b3321
+size 5599294208

saiga_llama3_8b-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c590f0dd8f44e4f54fa61019b8d2a22afb41225e26a53e4d6917a89f4b41be4
+size 6596006656

saiga_llama3_8b-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:391b7853a712fb0b25c10de6464fe2ca1272a4c396f353f5db0a5f9bade9422c
+size 8540771072