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
+orca_mini_3b-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+orca_mini_3b-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+orca_mini_3b-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+orca_mini_3b-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+orca_mini_3b-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+orca_mini_3b-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+orca_mini_3b-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+orca_mini_3b-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+orca_mini_3b-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+orca_mini_3b-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+orca_mini_3b-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+orca_mini_3b-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,181 @@
+---
+language:
+- en
+license: cc-by-nc-sa-4.0
+library_name: transformers
+datasets:
+- psmathur/alpaca_orca
+- psmathur/dolly-v2_orca
+- psmathur/WizardLM_Orca
+pipeline_tag: text-generation
+tags:
+- TensorBlock
+- GGUF
+base_model: pankajmathur/orca_mini_3b
+model-index:
+- name: orca_mini_3b
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 41.55
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_3b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 61.52
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_3b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 26.79
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_3b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 42.42
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_3b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 61.8
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_3b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 0.08
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_3b
+      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>
+
+## pankajmathur/orca_mini_3b - GGUF
+
+This repo contains GGUF format model files for [pankajmathur/orca_mini_3b](https://huggingface.co/pankajmathur/orca_mini_3b).
+
+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 |
+| -------- | ---------- | --------- | ----------- |
+| [orca_mini_3b-Q2_K.gguf](https://huggingface.co/tensorblock/orca_mini_3b-GGUF/tree/main/orca_mini_3b-Q2_K.gguf) | Q2_K | 1.844 GB | smallest, significant quality loss - not recommended for most purposes |
+| [orca_mini_3b-Q3_K_S.gguf](https://huggingface.co/tensorblock/orca_mini_3b-GGUF/tree/main/orca_mini_3b-Q3_K_S.gguf) | Q3_K_S | 1.844 GB | very small, high quality loss |
+| [orca_mini_3b-Q3_K_M.gguf](https://huggingface.co/tensorblock/orca_mini_3b-GGUF/tree/main/orca_mini_3b-Q3_K_M.gguf) | Q3_K_M | 1.992 GB | very small, high quality loss |
+| [orca_mini_3b-Q3_K_L.gguf](https://huggingface.co/tensorblock/orca_mini_3b-GGUF/tree/main/orca_mini_3b-Q3_K_L.gguf) | Q3_K_L | 2.062 GB | small, substantial quality loss |
+| [orca_mini_3b-Q4_0.gguf](https://huggingface.co/tensorblock/orca_mini_3b-GGUF/tree/main/orca_mini_3b-Q4_0.gguf) | Q4_0 | 1.844 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [orca_mini_3b-Q4_K_S.gguf](https://huggingface.co/tensorblock/orca_mini_3b-GGUF/tree/main/orca_mini_3b-Q4_K_S.gguf) | Q4_K_S | 2.238 GB | small, greater quality loss |
+| [orca_mini_3b-Q4_K_M.gguf](https://huggingface.co/tensorblock/orca_mini_3b-GGUF/tree/main/orca_mini_3b-Q4_K_M.gguf) | Q4_K_M | 2.403 GB | medium, balanced quality - recommended |
+| [orca_mini_3b-Q5_0.gguf](https://huggingface.co/tensorblock/orca_mini_3b-GGUF/tree/main/orca_mini_3b-Q5_0.gguf) | Q5_0 | 2.231 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [orca_mini_3b-Q5_K_S.gguf](https://huggingface.co/tensorblock/orca_mini_3b-GGUF/tree/main/orca_mini_3b-Q5_K_S.gguf) | Q5_K_S | 2.424 GB | large, low quality loss - recommended |
+| [orca_mini_3b-Q5_K_M.gguf](https://huggingface.co/tensorblock/orca_mini_3b-GGUF/tree/main/orca_mini_3b-Q5_K_M.gguf) | Q5_K_M | 2.568 GB | large, very low quality loss - recommended |
+| [orca_mini_3b-Q6_K.gguf](https://huggingface.co/tensorblock/orca_mini_3b-GGUF/tree/main/orca_mini_3b-Q6_K.gguf) | Q6_K | 3.392 GB | very large, extremely low quality loss |
+| [orca_mini_3b-Q8_0.gguf](https://huggingface.co/tensorblock/orca_mini_3b-GGUF/tree/main/orca_mini_3b-Q8_0.gguf) | Q8_0 | 3.392 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/orca_mini_3b-GGUF --include "orca_mini_3b-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/orca_mini_3b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

orca_mini_3b-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ac976b234615a9b0a033a668233e8b3ed42b0e8282e9a5f817f27cd8cd05c17
+size 1979947328

orca_mini_3b-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2993099a0f8f1d23403a2effe6d50885744981d9cc5488be551d141725e52612
+size 2214571328

orca_mini_3b-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0aef8bacb98f5be99e415290b01d00d4ad99ba52b7083cbc6ec1fa39553c9d7
+size 2139371328

orca_mini_3b-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afb35842efcdfd7377757a68ba4573d763f56e6454355fda8bb40a60e4ae7054
+size 1979947328

orca_mini_3b-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4ab261409abb1e340910723c6b4b1496cb7633e19811a5876411a3c25e5db95
+size 1979947328

orca_mini_3b-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9a39f203a2310c3bb77a9a7075c84f2ec4d4ccb7ce7b831c3c62cb2ae2cfd33
+size 2580139328

orca_mini_3b-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c46e5f1a573b2e5eb7f0c659acbd20d1f3d773de026f3e12fc26bd6eae0830e2
+size 2403179328

orca_mini_3b-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74e8ebc32591015a112f9f4996f5370468c6021455481ef4924194057cb3c8c1
+size 2395435328

orca_mini_3b-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:734cd6a7813d0d4d0428aaa843cd4454200b37ca2345e929fbc96cf4c254a520
+size 2757099328

orca_mini_3b-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74bb205e1076f54fb2a1810d742b94016b477fa6b7b50009cbdbcdc5e1747d0a
+size 2603179328

orca_mini_3b-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aea225a5aa915962a8d29b8faba6543db0c4e8ab564d5679aa347602bdfd8414
+size 3641899328

orca_mini_3b-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc682a8c013ee33ec08dc0e0c2abdc9aec4cf63ee94988cc59ff08b5a5895fae
+size 3641899328