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
+NeuralLLaMa-3-8b-ORPO-v0.3-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralLLaMa-3-8b-ORPO-v0.3-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralLLaMa-3-8b-ORPO-v0.3-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralLLaMa-3-8b-ORPO-v0.3-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralLLaMa-3-8b-ORPO-v0.3-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralLLaMa-3-8b-ORPO-v0.3-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralLLaMa-3-8b-ORPO-v0.3-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralLLaMa-3-8b-ORPO-v0.3-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralLLaMa-3-8b-ORPO-v0.3-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralLLaMa-3-8b-ORPO-v0.3-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralLLaMa-3-8b-ORPO-v0.3-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralLLaMa-3-8b-ORPO-v0.3-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

NeuralLLaMa-3-8b-ORPO-v0.3-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5413c25f9fc42f72a4f1229a089d399686fed2ea2cdf87fe3867f6bfef954256
+size 3179141120

NeuralLLaMa-3-8b-ORPO-v0.3-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be42c796fe4e48945d2b0c4d144571090e79469c8fa4210f6e57d8ef520f5a6c
+size 4321966912

NeuralLLaMa-3-8b-ORPO-v0.3-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2750bf31b9a8633511c45e9f297f8dedcb67e9d8168c43bd4c0686e53fd2dac0
+size 4018928448

NeuralLLaMa-3-8b-ORPO-v0.3-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05ac184de39037517be33741ce2385cd43b34542dc7dab5488a3b29a04829aba
+size 3664509760

NeuralLLaMa-3-8b-ORPO-v0.3-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f4074f061665d8997bd3578b3fda060eec07b96ac845da16a78b81fe8a4d996
+size 4661223296

NeuralLLaMa-3-8b-ORPO-v0.3-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c33435748d119760d6e5afd2609c2d8297ae64cb42cc6658ee64a2a3478b99c
+size 4920745856

NeuralLLaMa-3-8b-ORPO-v0.3-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37b12d5efe0a868e26304ec107a269f76886e50b22fd13a55b6466ca277d2b02
+size 4692680576

NeuralLLaMa-3-8b-ORPO-v0.3-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fc9651b4ffc5a21f2fe5227ee1e271f6291eff19a65dd3d46a54555119dc105
+size 5599306624

NeuralLLaMa-3-8b-ORPO-v0.3-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ef9e0d7d066622a22cf06351dee14cb319d747c45301e8e5ce4218f2ec3e493
+size 5733000064

NeuralLLaMa-3-8b-ORPO-v0.3-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c2892064b7514c05d168b8c49f65508a9e73ce03768f3cab0933e221290c24e
+size 5599306624

NeuralLLaMa-3-8b-ORPO-v0.3-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d5d2d609d199261a103511533b1d5cb11ee09ee86f49b8da6e00f852e990a7d
+size 6596020160

NeuralLLaMa-3-8b-ORPO-v0.3-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4806d2bcb1e52dbb66cc56259f02fbb71056ea5cf35af58d45c5bfc7bc3022fc
+size 8540788544

README.md

@@ -0,0 +1,179 @@
+---
+license: apache-2.0
+datasets:
+- mlabonne/orpo-dpo-mix-40k
+base_model: Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3
+tags:
+- TensorBlock
+- GGUF
+model-index:
+- name: NeuralLLaMa-3-8b-ORPO-v0.3
+  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: 69.54
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3
+      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: 84.9
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3
+      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: 68.39
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3
+      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: 60.82
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3
+      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: 79.4
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3
+      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: 72.93
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3
+      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>
+
+## Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3 - GGUF
+
+This repo contains GGUF format model files for [Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3](https://huggingface.co/Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3).
+
+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
+
+```
+<|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 |
+| -------- | ---------- | --------- | ----------- |
+| [NeuralLLaMa-3-8b-ORPO-v0.3-Q2_K.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.3-GGUF/tree/main/NeuralLLaMa-3-8b-ORPO-v0.3-Q2_K.gguf) | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
+| [NeuralLLaMa-3-8b-ORPO-v0.3-Q3_K_S.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.3-GGUF/tree/main/NeuralLLaMa-3-8b-ORPO-v0.3-Q3_K_S.gguf) | Q3_K_S | 3.413 GB | very small, high quality loss |
+| [NeuralLLaMa-3-8b-ORPO-v0.3-Q3_K_M.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.3-GGUF/tree/main/NeuralLLaMa-3-8b-ORPO-v0.3-Q3_K_M.gguf) | Q3_K_M | 3.743 GB | very small, high quality loss |
+| [NeuralLLaMa-3-8b-ORPO-v0.3-Q3_K_L.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.3-GGUF/tree/main/NeuralLLaMa-3-8b-ORPO-v0.3-Q3_K_L.gguf) | Q3_K_L | 4.025 GB | small, substantial quality loss |
+| [NeuralLLaMa-3-8b-ORPO-v0.3-Q4_0.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.3-GGUF/tree/main/NeuralLLaMa-3-8b-ORPO-v0.3-Q4_0.gguf) | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [NeuralLLaMa-3-8b-ORPO-v0.3-Q4_K_S.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.3-GGUF/tree/main/NeuralLLaMa-3-8b-ORPO-v0.3-Q4_K_S.gguf) | Q4_K_S | 4.370 GB | small, greater quality loss |
+| [NeuralLLaMa-3-8b-ORPO-v0.3-Q4_K_M.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.3-GGUF/tree/main/NeuralLLaMa-3-8b-ORPO-v0.3-Q4_K_M.gguf) | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
+| [NeuralLLaMa-3-8b-ORPO-v0.3-Q5_0.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.3-GGUF/tree/main/NeuralLLaMa-3-8b-ORPO-v0.3-Q5_0.gguf) | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [NeuralLLaMa-3-8b-ORPO-v0.3-Q5_K_S.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.3-GGUF/tree/main/NeuralLLaMa-3-8b-ORPO-v0.3-Q5_K_S.gguf) | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
+| [NeuralLLaMa-3-8b-ORPO-v0.3-Q5_K_M.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.3-GGUF/tree/main/NeuralLLaMa-3-8b-ORPO-v0.3-Q5_K_M.gguf) | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
+| [NeuralLLaMa-3-8b-ORPO-v0.3-Q6_K.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.3-GGUF/tree/main/NeuralLLaMa-3-8b-ORPO-v0.3-Q6_K.gguf) | Q6_K | 6.143 GB | very large, extremely low quality loss |
+| [NeuralLLaMa-3-8b-ORPO-v0.3-Q8_0.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.3-GGUF/tree/main/NeuralLLaMa-3-8b-ORPO-v0.3-Q8_0.gguf) | Q8_0 | 7.954 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/NeuralLLaMa-3-8b-ORPO-v0.3-GGUF --include "NeuralLLaMa-3-8b-ORPO-v0.3-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/NeuralLLaMa-3-8b-ORPO-v0.3-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```