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

FluentlyLM-Prinum-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85fa3a41086e3eb8d72716604ce203545f5a2bc5a05823ec5b1c357520dfc109
+size 12313099584

FluentlyLM-Prinum-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6572a2b289ded31c696fd23a9f3ec18b33af993efebb7092b7cf7eb94a7f4de1
+size 17247079744

FluentlyLM-Prinum-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a73ca4420fc0e2a64bf4ed3dae7b18fad515f6cfa1c8c4377eab7445bd55c717
+size 15935049024

FluentlyLM-Prinum-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b1d818f1b09442c4bc25e0d0ba1f432fd27187ed2af80e1f4991d4509b8052d
+size 14392331584

FluentlyLM-Prinum-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d10ded8f6ff774e85cfb5ae4224e82f6fdae477ae827fce6657169817a9e625c
+size 18640231744

FluentlyLM-Prinum-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d79317073caccbab1e13203494b007f83f9b0282b9fa25ca0eef05c118ef356f
+size 19851337024

FluentlyLM-Prinum-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:407dc72645189d3779fdb6cba36e7a9ca35790a78c02c77e142c09ab8dee70a4
+size 18784410944

FluentlyLM-Prinum-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51833616d5b2843bde5b2fda6eb4739e5a71b6b746b065fbbc2b1ff92c6cd510
+size 22638255424

FluentlyLM-Prinum-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e775618df29e474685ddaa20f9b01a46bf78d54e61ce753118031955478202f
+size 23262158144

FluentlyLM-Prinum-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d35a902ecf5ac18a3941115e8bd6a6bb9f64b3b07b6c1fd103d4931c867f1bb
+size 22638255424

FluentlyLM-Prinum-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33ecfc2810967e79ae3dfcd21f4570a47019f63d112d293a3d6cee520358fe36
+size 26886155584

FluentlyLM-Prinum-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b58a430ac28f3199553d0d1ee3bd604d17f3d8f0c9a5f2eb22c10fb16e38122
+size 34820885824

README.md

@@ -0,0 +1,204 @@
+---
+language:
+- en
+- fr
+- es
+- ru
+- zh
+- ja
+- fa
+- code
+license: mit
+library_name: transformers
+tags:
+- fluently-lm
+- fluently
+- prinum
+- instruct
+- trained
+- math
+- roleplay
+- reasoning
+- axolotl
+- unsloth
+- argilla
+- qwen2
+- TensorBlock
+- GGUF
+datasets:
+- fluently-sets/ultraset
+- fluently-sets/ultrathink
+- fluently-sets/reasoning-1-1k
+- fluently-sets/MATH-500-Overall
+inference: true
+pipeline_tag: text-generation
+base_model: fluently-lm/FluentlyLM-Prinum
+model-index:
+- name: FluentlyLM-Prinum
+  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: 80.9
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fluently-lm/FluentlyLM-Prinum
+      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: 59.48
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fluently-lm/FluentlyLM-Prinum
+      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: 54.0
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fluently-lm/FluentlyLM-Prinum
+      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: 18.23
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fluently-lm/FluentlyLM-Prinum
+      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: 17.26
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fluently-lm/FluentlyLM-Prinum
+      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: 53.42
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fluently-lm/FluentlyLM-Prinum
+      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>
+
+## fluently-lm/FluentlyLM-Prinum - GGUF
+
+This repo contains GGUF format model files for [fluently-lm/FluentlyLM-Prinum](https://huggingface.co/fluently-lm/FluentlyLM-Prinum).
+
+The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4823](https://github.com/ggml-org/llama.cpp/commit/5bbe6a9fe9a8796a9389c85accec89dbc4d91e39).
+
+<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
+
+```
+<|im_start|>system
+{system_prompt}<|im_end|>
+<|im_start|>user
+{prompt}<|im_end|>
+<|im_start|>assistant
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [FluentlyLM-Prinum-Q2_K.gguf](https://huggingface.co/tensorblock/FluentlyLM-Prinum-GGUF/blob/main/FluentlyLM-Prinum-Q2_K.gguf) | Q2_K | 12.313 GB | smallest, significant quality loss - not recommended for most purposes |
+| [FluentlyLM-Prinum-Q3_K_S.gguf](https://huggingface.co/tensorblock/FluentlyLM-Prinum-GGUF/blob/main/FluentlyLM-Prinum-Q3_K_S.gguf) | Q3_K_S | 14.392 GB | very small, high quality loss |
+| [FluentlyLM-Prinum-Q3_K_M.gguf](https://huggingface.co/tensorblock/FluentlyLM-Prinum-GGUF/blob/main/FluentlyLM-Prinum-Q3_K_M.gguf) | Q3_K_M | 15.935 GB | very small, high quality loss |
+| [FluentlyLM-Prinum-Q3_K_L.gguf](https://huggingface.co/tensorblock/FluentlyLM-Prinum-GGUF/blob/main/FluentlyLM-Prinum-Q3_K_L.gguf) | Q3_K_L | 17.247 GB | small, substantial quality loss |
+| [FluentlyLM-Prinum-Q4_0.gguf](https://huggingface.co/tensorblock/FluentlyLM-Prinum-GGUF/blob/main/FluentlyLM-Prinum-Q4_0.gguf) | Q4_0 | 18.640 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [FluentlyLM-Prinum-Q4_K_S.gguf](https://huggingface.co/tensorblock/FluentlyLM-Prinum-GGUF/blob/main/FluentlyLM-Prinum-Q4_K_S.gguf) | Q4_K_S | 18.784 GB | small, greater quality loss |
+| [FluentlyLM-Prinum-Q4_K_M.gguf](https://huggingface.co/tensorblock/FluentlyLM-Prinum-GGUF/blob/main/FluentlyLM-Prinum-Q4_K_M.gguf) | Q4_K_M | 19.851 GB | medium, balanced quality - recommended |
+| [FluentlyLM-Prinum-Q5_0.gguf](https://huggingface.co/tensorblock/FluentlyLM-Prinum-GGUF/blob/main/FluentlyLM-Prinum-Q5_0.gguf) | Q5_0 | 22.638 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [FluentlyLM-Prinum-Q5_K_S.gguf](https://huggingface.co/tensorblock/FluentlyLM-Prinum-GGUF/blob/main/FluentlyLM-Prinum-Q5_K_S.gguf) | Q5_K_S | 22.638 GB | large, low quality loss - recommended |
+| [FluentlyLM-Prinum-Q5_K_M.gguf](https://huggingface.co/tensorblock/FluentlyLM-Prinum-GGUF/blob/main/FluentlyLM-Prinum-Q5_K_M.gguf) | Q5_K_M | 23.262 GB | large, very low quality loss - recommended |
+| [FluentlyLM-Prinum-Q6_K.gguf](https://huggingface.co/tensorblock/FluentlyLM-Prinum-GGUF/blob/main/FluentlyLM-Prinum-Q6_K.gguf) | Q6_K | 26.886 GB | very large, extremely low quality loss |
+| [FluentlyLM-Prinum-Q8_0.gguf](https://huggingface.co/tensorblock/FluentlyLM-Prinum-GGUF/blob/main/FluentlyLM-Prinum-Q8_0.gguf) | Q8_0 | 34.821 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/FluentlyLM-Prinum-GGUF --include "FluentlyLM-Prinum-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/FluentlyLM-Prinum-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```