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

NeuralMonarch-7B-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e5fd1fecbdf57088f0c222bbc35cd24db36adef811c3bacea037c62e93e2cc7
+size 2719243008

NeuralMonarch-7B-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dea4d7cf2c8dce7ce772be056a69f1b3ec308cd0993080546ee6021930c3de5
+size 3822025472

NeuralMonarch-7B-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48ba65c169ba471155449c05d2300710e20095999f7565d564710e1929bef932
+size 3518987008

NeuralMonarch-7B-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:344a046f3ea8ddcc9c3a3eac1de7d691320cf131aebbcc771dff8fa2085472d2
+size 3164568320

NeuralMonarch-7B-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99b0b3f20be4fffd9bc14d983c87222266e4737a16c890b80c84ed21620070e5
+size 4108917504

NeuralMonarch-7B-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:848ba0785eaf7a2494b202d9b92da7d192c1bd454002cc23f1cfa3093b3db68a
+size 4368440064

NeuralMonarch-7B-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c29ba03b30857bad3a8fbf06ab07d14842706c2485a394d518351ad54fda1cc
+size 4140374784

NeuralMonarch-7B-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69949e0b73b6313ee54d9e7fb0f4f03a38b1e7a14f7717afee1f136e9c65f682
+size 4997716736

NeuralMonarch-7B-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba44606cf09d66dc450e4ed9d20f17c50a17f5128f6eb71ed87b07ab5265ca7d
+size 5131410176

NeuralMonarch-7B-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:814e73b7e5812cb5c82ea5d51035b362aa1b5ea69db6642ab92b69c0b42efe68
+size 4997716736

NeuralMonarch-7B-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb3dcbd25abf0191a6e3028a9621f0b063223fb2552c703246019cead22f1f96
+size 5942065920

NeuralMonarch-7B-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e63e8dc502aa8783e3c050f5731a2fcb424e3628be834abc8fa05b6800798ca
+size 7695858432

README.md

@@ -0,0 +1,186 @@
+---
+language:
+- en
+license: cc-by-nc-4.0
+tags:
+- merge
+- lazymergekit
+- dpo
+- rlhf
+- TensorBlock
+- GGUF
+dataset:
+- mlabonne/truthy-dpo-v0.1
+- mlabonne/distilabel-intel-orca-dpo-pairs
+base_model: mlabonne/NeuralMonarch-7B
+model-index:
+- name: NeuralMonarch-7B
+  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: 73.21
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralMonarch-7B
+      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: 89.09
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralMonarch-7B
+      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: 64.41
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralMonarch-7B
+      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: 77.79
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralMonarch-7B
+      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: 84.61
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralMonarch-7B
+      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: 67.78
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralMonarch-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>
+
+## mlabonne/NeuralMonarch-7B - GGUF
+
+This repo contains GGUF format model files for [mlabonne/NeuralMonarch-7B](https://huggingface.co/mlabonne/NeuralMonarch-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).
+
+## Prompt template
+
+```
+<s>system
+{system_prompt}</s>
+<s>user
+{prompt}</s>
+<s>assistant
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [NeuralMonarch-7B-Q2_K.gguf](https://huggingface.co/tensorblock/NeuralMonarch-7B-GGUF/tree/main/NeuralMonarch-7B-Q2_K.gguf) | Q2_K | 2.532 GB | smallest, significant quality loss - not recommended for most purposes |
+| [NeuralMonarch-7B-Q3_K_S.gguf](https://huggingface.co/tensorblock/NeuralMonarch-7B-GGUF/tree/main/NeuralMonarch-7B-Q3_K_S.gguf) | Q3_K_S | 2.947 GB | very small, high quality loss |
+| [NeuralMonarch-7B-Q3_K_M.gguf](https://huggingface.co/tensorblock/NeuralMonarch-7B-GGUF/tree/main/NeuralMonarch-7B-Q3_K_M.gguf) | Q3_K_M | 3.277 GB | very small, high quality loss |
+| [NeuralMonarch-7B-Q3_K_L.gguf](https://huggingface.co/tensorblock/NeuralMonarch-7B-GGUF/tree/main/NeuralMonarch-7B-Q3_K_L.gguf) | Q3_K_L | 3.560 GB | small, substantial quality loss |
+| [NeuralMonarch-7B-Q4_0.gguf](https://huggingface.co/tensorblock/NeuralMonarch-7B-GGUF/tree/main/NeuralMonarch-7B-Q4_0.gguf) | Q4_0 | 3.827 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [NeuralMonarch-7B-Q4_K_S.gguf](https://huggingface.co/tensorblock/NeuralMonarch-7B-GGUF/tree/main/NeuralMonarch-7B-Q4_K_S.gguf) | Q4_K_S | 3.856 GB | small, greater quality loss |
+| [NeuralMonarch-7B-Q4_K_M.gguf](https://huggingface.co/tensorblock/NeuralMonarch-7B-GGUF/tree/main/NeuralMonarch-7B-Q4_K_M.gguf) | Q4_K_M | 4.068 GB | medium, balanced quality - recommended |
+| [NeuralMonarch-7B-Q5_0.gguf](https://huggingface.co/tensorblock/NeuralMonarch-7B-GGUF/tree/main/NeuralMonarch-7B-Q5_0.gguf) | Q5_0 | 4.654 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [NeuralMonarch-7B-Q5_K_S.gguf](https://huggingface.co/tensorblock/NeuralMonarch-7B-GGUF/tree/main/NeuralMonarch-7B-Q5_K_S.gguf) | Q5_K_S | 4.654 GB | large, low quality loss - recommended |
+| [NeuralMonarch-7B-Q5_K_M.gguf](https://huggingface.co/tensorblock/NeuralMonarch-7B-GGUF/tree/main/NeuralMonarch-7B-Q5_K_M.gguf) | Q5_K_M | 4.779 GB | large, very low quality loss - recommended |
+| [NeuralMonarch-7B-Q6_K.gguf](https://huggingface.co/tensorblock/NeuralMonarch-7B-GGUF/tree/main/NeuralMonarch-7B-Q6_K.gguf) | Q6_K | 5.534 GB | very large, extremely low quality loss |
+| [NeuralMonarch-7B-Q8_0.gguf](https://huggingface.co/tensorblock/NeuralMonarch-7B-GGUF/tree/main/NeuralMonarch-7B-Q8_0.gguf) | Q8_0 | 7.167 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/NeuralMonarch-7B-GGUF --include "NeuralMonarch-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/NeuralMonarch-7B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```