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
+gemma-mling-7b-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-mling-7b-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-mling-7b-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-mling-7b-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-mling-7b-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-mling-7b-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-mling-7b-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-mling-7b-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-mling-7b-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-mling-7b-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-mling-7b-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-mling-7b-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,181 @@
+---
+language:
+- ko
+- en
+- zh
+- ja
+license: other
+library_name: transformers
+tags:
+- pytorch
+- TensorBlock
+- GGUF
+license_name: gemma-terms-of-use
+license_link: https://ai.google.dev/gemma/terms
+pipeline_tag: text-generation
+base_model: beomi/gemma-mling-7b
+model-index:
+- name: gemma-mling-7b
+  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: 20.29
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=beomi/gemma-mling-7b
+      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: 17.63
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=beomi/gemma-mling-7b
+      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: 4.15
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=beomi/gemma-mling-7b
+      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: 0.0
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=beomi/gemma-mling-7b
+      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: 6.85
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=beomi/gemma-mling-7b
+      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: 18.14
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=beomi/gemma-mling-7b
+      name: Open LLM Leaderboard
+---
+
+<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>
+
+## beomi/gemma-mling-7b - GGUF
+
+This repo contains GGUF format model files for [beomi/gemma-mling-7b](https://huggingface.co/beomi/gemma-mling-7b).
+
+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).
+
+<div style="text-align: left; margin: 20px 0;">
+    <a href="https://tensorblock.co/waitlist/client" style="display: inline-block; padding: 10px 20px; background-color: #007bff; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
+        Run them on the TensorBlock client using your local machine ↗
+    </a>
+</div>
+
+## Prompt template
+
+```
+
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [gemma-mling-7b-Q2_K.gguf](https://huggingface.co/tensorblock/gemma-mling-7b-GGUF/blob/main/gemma-mling-7b-Q2_K.gguf) | Q2_K | 3.242 GB | smallest, significant quality loss - not recommended for most purposes |
+| [gemma-mling-7b-Q3_K_S.gguf](https://huggingface.co/tensorblock/gemma-mling-7b-GGUF/blob/main/gemma-mling-7b-Q3_K_S.gguf) | Q3_K_S | 3.709 GB | very small, high quality loss |
+| [gemma-mling-7b-Q3_K_M.gguf](https://huggingface.co/tensorblock/gemma-mling-7b-GGUF/blob/main/gemma-mling-7b-Q3_K_M.gguf) | Q3_K_M | 4.069 GB | very small, high quality loss |
+| [gemma-mling-7b-Q3_K_L.gguf](https://huggingface.co/tensorblock/gemma-mling-7b-GGUF/blob/main/gemma-mling-7b-Q3_K_L.gguf) | Q3_K_L | 4.386 GB | small, substantial quality loss |
+| [gemma-mling-7b-Q4_0.gguf](https://huggingface.co/tensorblock/gemma-mling-7b-GGUF/blob/main/gemma-mling-7b-Q4_0.gguf) | Q4_0 | 4.668 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [gemma-mling-7b-Q4_K_S.gguf](https://huggingface.co/tensorblock/gemma-mling-7b-GGUF/blob/main/gemma-mling-7b-Q4_K_S.gguf) | Q4_K_S | 4.700 GB | small, greater quality loss |
+| [gemma-mling-7b-Q4_K_M.gguf](https://huggingface.co/tensorblock/gemma-mling-7b-GGUF/blob/main/gemma-mling-7b-Q4_K_M.gguf) | Q4_K_M | 4.964 GB | medium, balanced quality - recommended |
+| [gemma-mling-7b-Q5_0.gguf](https://huggingface.co/tensorblock/gemma-mling-7b-GGUF/blob/main/gemma-mling-7b-Q5_0.gguf) | Q5_0 | 5.570 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [gemma-mling-7b-Q5_K_S.gguf](https://huggingface.co/tensorblock/gemma-mling-7b-GGUF/blob/main/gemma-mling-7b-Q5_K_S.gguf) | Q5_K_S | 5.570 GB | large, low quality loss - recommended |
+| [gemma-mling-7b-Q5_K_M.gguf](https://huggingface.co/tensorblock/gemma-mling-7b-GGUF/blob/main/gemma-mling-7b-Q5_K_M.gguf) | Q5_K_M | 5.723 GB | large, very low quality loss - recommended |
+| [gemma-mling-7b-Q6_K.gguf](https://huggingface.co/tensorblock/gemma-mling-7b-GGUF/blob/main/gemma-mling-7b-Q6_K.gguf) | Q6_K | 6.529 GB | very large, extremely low quality loss |
+| [gemma-mling-7b-Q8_0.gguf](https://huggingface.co/tensorblock/gemma-mling-7b-GGUF/blob/main/gemma-mling-7b-Q8_0.gguf) | Q8_0 | 8.454 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/gemma-mling-7b-GGUF --include "gemma-mling-7b-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/gemma-mling-7b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

gemma-mling-7b-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29298a0673ef5d18425d5ee186ee8f6240df8be6f489d92536beeb7ca685efb5
+size 3481447360

gemma-mling-7b-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0787935932af399023f5f204da9f2d4342cac95a7f107fcbc730d5b054490944
+size 4709067712

gemma-mling-7b-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90721f314fa9e6af5d9f2a810b30e11c30ae91e05a838a144377e8abb61114d3
+size 4369329088

gemma-mling-7b-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73a7f2d2d538e114ac8630d8dc05b198f978965e35ef2addb4d28d2ea8db2406
+size 3982404544

gemma-mling-7b-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:880037532c7223da9f4309a075226db44b27ac45eeaf7d45d780e03b9be7d8b7
+size 5011844032

gemma-mling-7b-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cd90114f86bf577026007c7562b98fa9f46e5d00919d8130c02bebd150be1d0
+size 5329759168

gemma-mling-7b-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4272fb0270bae4ea9bca0e5b9b74c942a321094b795854b462d34e344352f97
+size 5046447040

gemma-mling-7b-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8d2140318fdc521e5a029cdb501a75c95d41c33a4e0938e191e1d9ea04b0570
+size 5980728256

gemma-mling-7b-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bc580afdcdec63bffec6210f397a0140742e3198ca46e83d92d9a1c2005c1cb
+size 6144502720

gemma-mling-7b-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acab0c9e14bc671ba0ddf5322618e91316cf776f44d03a66817957e4f2c16077
+size 5980728256

gemma-mling-7b-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a4d6377713eb257ce16b9831af70f22e2af15dd6c8f4d1e9a675fc81fb31e72
+size 7010167744

gemma-mling-7b-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c98ff149aa9e286633dc9e9537d15329986d9e4965fb95329466498eff12568
+size 9077844928