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

MicroLlama-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d1c62c6d4bd252268ee07563c1fbf329dd77aca2011d736ea097b1873045f92
+size 125955808

MicroLlama-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:518737c710080f16210eddf41fe591c33e9e33f117491c3e64376b2adcaef4e2
+size 166418144

MicroLlama-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3726631e6008dd8c06af7eb35e5274cb4c18f8ff9bee2960b5f63c6203fbd8a3
+size 155866848

MicroLlama-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:316e879e372e1448911f8bacc18239840cbd02a2c18960493c5d02f4b44785ac
+size 144520928

MicroLlama-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70d348c6df9ff960d56f727605b14e31229b26b037c92b7171be4ac96228b866
+size 180625120

MicroLlama-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:216db27b323b4c62641b6b608cefd0829c6b085ff178d0dbfaac0bb59a797860
+size 189951712

MicroLlama-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae503fee34f8929bbdd99e60bf8952eded49853ef6a0bd81d0beba2e8efa2a29
+size 181477088

MicroLlama-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e55ca444870e093c4a5c5bccf12739af2039492ba773f4fdae76722f31d0c75
+size 214605536

MicroLlama-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bab25f6b159f8f540627ee38382e880ee57399a9031d88126d1be99a317a68ff
+size 219410144

MicroLlama-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80b757288c27cb1433c532ef15ccd29dda978199ed32b2a335a238eade6f6a42
+size 214605536

MicroLlama-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4500e1525a33f8c315e6b55fabb45aad0c3abecfd83bb147b3ca1b6b495e4cbd
+size 250709728

MicroLlama-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad33f419fa4fc3eef76bd43216fb50dbdd46dc606d3e432033040d7c34264972
+size 324482784

README.md

@@ -0,0 +1,172 @@
+---
+language:
+- en
+license: apache-2.0
+library_name: transformers
+datasets:
+- cerebras/SlimPajama-627B
+metrics:
+- accuracy
+base_model: keeeeenw/MicroLlama
+tags:
+- TensorBlock
+- GGUF
+model-index:
+- name: MicroLlama
+  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: 19.85
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=keeeeenw/MicroLlama
+      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: 2.83
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=keeeeenw/MicroLlama
+      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: 0.0
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=keeeeenw/MicroLlama
+      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: 1.45
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=keeeeenw/MicroLlama
+      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: 4.79
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=keeeeenw/MicroLlama
+      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: 1.53
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=keeeeenw/MicroLlama
+      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>
+
+## keeeeenw/MicroLlama - GGUF
+
+This repo contains GGUF format model files for [keeeeenw/MicroLlama](https://huggingface.co/keeeeenw/MicroLlama).
+
+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 |
+| -------- | ---------- | --------- | ----------- |
+| [MicroLlama-Q2_K.gguf](https://huggingface.co/tensorblock/MicroLlama-GGUF/tree/main/MicroLlama-Q2_K.gguf) | Q2_K | 0.117 GB | smallest, significant quality loss - not recommended for most purposes |
+| [MicroLlama-Q3_K_S.gguf](https://huggingface.co/tensorblock/MicroLlama-GGUF/tree/main/MicroLlama-Q3_K_S.gguf) | Q3_K_S | 0.135 GB | very small, high quality loss |
+| [MicroLlama-Q3_K_M.gguf](https://huggingface.co/tensorblock/MicroLlama-GGUF/tree/main/MicroLlama-Q3_K_M.gguf) | Q3_K_M | 0.145 GB | very small, high quality loss |
+| [MicroLlama-Q3_K_L.gguf](https://huggingface.co/tensorblock/MicroLlama-GGUF/tree/main/MicroLlama-Q3_K_L.gguf) | Q3_K_L | 0.155 GB | small, substantial quality loss |
+| [MicroLlama-Q4_0.gguf](https://huggingface.co/tensorblock/MicroLlama-GGUF/tree/main/MicroLlama-Q4_0.gguf) | Q4_0 | 0.168 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [MicroLlama-Q4_K_S.gguf](https://huggingface.co/tensorblock/MicroLlama-GGUF/tree/main/MicroLlama-Q4_K_S.gguf) | Q4_K_S | 0.169 GB | small, greater quality loss |
+| [MicroLlama-Q4_K_M.gguf](https://huggingface.co/tensorblock/MicroLlama-GGUF/tree/main/MicroLlama-Q4_K_M.gguf) | Q4_K_M | 0.177 GB | medium, balanced quality - recommended |
+| [MicroLlama-Q5_0.gguf](https://huggingface.co/tensorblock/MicroLlama-GGUF/tree/main/MicroLlama-Q5_0.gguf) | Q5_0 | 0.200 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [MicroLlama-Q5_K_S.gguf](https://huggingface.co/tensorblock/MicroLlama-GGUF/tree/main/MicroLlama-Q5_K_S.gguf) | Q5_K_S | 0.200 GB | large, low quality loss - recommended |
+| [MicroLlama-Q5_K_M.gguf](https://huggingface.co/tensorblock/MicroLlama-GGUF/tree/main/MicroLlama-Q5_K_M.gguf) | Q5_K_M | 0.204 GB | large, very low quality loss - recommended |
+| [MicroLlama-Q6_K.gguf](https://huggingface.co/tensorblock/MicroLlama-GGUF/tree/main/MicroLlama-Q6_K.gguf) | Q6_K | 0.233 GB | very large, extremely low quality loss |
+| [MicroLlama-Q8_0.gguf](https://huggingface.co/tensorblock/MicroLlama-GGUF/tree/main/MicroLlama-Q8_0.gguf) | Q8_0 | 0.302 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/MicroLlama-GGUF --include "MicroLlama-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/MicroLlama-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```