Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,18 @@ 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
+Llama-3-70B-Orpo-v0.1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-70B-Orpo-v0.1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-70B-Orpo-v0.1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-70B-Orpo-v0.1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-70B-Orpo-v0.1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-70B-Orpo-v0.1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-70B-Orpo-v0.1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-70B-Orpo-v0.1-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-70B-Orpo-v0.1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-70B-Orpo-v0.1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-70B-Orpo-v0.1-Q6_K/Llama-3-70B-Orpo-v0.1-Q6_K-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-70B-Orpo-v0.1-Q6_K/Llama-3-70B-Orpo-v0.1-Q6_K-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-70B-Orpo-v0.1-Q8_0/Llama-3-70B-Orpo-v0.1-Q8_0-00001-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-70B-Orpo-v0.1-Q8_0/Llama-3-70B-Orpo-v0.1-Q8_0-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-70B-Orpo-v0.1-Q8_0/Llama-3-70B-Orpo-v0.1-Q8_0-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text

Llama-3-70B-Orpo-v0.1-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac704ed5ddbf2d45b82818715e903fe298c54f05f26720b3db67033d4735d316
+size 26375127744

Llama-3-70B-Orpo-v0.1-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e1864050fa6348a21a5bbf2f5d7bbc41fe4202040c2b9f2f22cba06ca3f0b47
+size 37140613440

Llama-3-70B-Orpo-v0.1-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4c7668aaebdfcd76d6dc589012f649d5f73bf376ef5ebf33f6f7cfa3c69539a
+size 34267515200

Llama-3-70B-Orpo-v0.1-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ad4394879039f5e5cbf265cd1c33543cdd126201febc8599f1499d603412fb2
+size 30912072000

Llama-3-70B-Orpo-v0.1-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:632e22391fbcec3bba22e25a6d5396f35d6679fcf325ba0f9e7e81cd122e5098
+size 39969755584

Llama-3-70B-Orpo-v0.1-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8a83cddb29ef95c5ee29b4aaaf995652e0ef76ca86f06a7d1c5c0fb6a8e1e7a
+size 42520416704

Llama-3-70B-Orpo-v0.1-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:261d68d66e3c36258251125c351ded91de9d000929ea02f66a10f3302c47b82a
+size 40347242944

Llama-3-70B-Orpo-v0.1-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42241138e1c5b641663586a3b170e7f5f5bf0ab5ad49048da3b74d8d241b8edd
+size 48657471936

Llama-3-70B-Orpo-v0.1-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcac3ed5b36bccb9133b8780ad08aa25bb8cf09e1d2f024803bf755ba65d17ec
+size 49949841856

Llama-3-70B-Orpo-v0.1-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c93cd67429b0bfef01e906c79ba62cd87f89424bc0c7b2a03d0e22e9a2766171
+size 48657471936

Llama-3-70B-Orpo-v0.1-Q6_K/Llama-3-70B-Orpo-v0.1-Q6_K-00001-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36469ffd678f4cf699be9cce50a82ad6dc72aba94199018661f63bfdff310721
+size 34847497824

Llama-3-70B-Orpo-v0.1-Q6_K/Llama-3-70B-Orpo-v0.1-Q6_K-00002-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a14b973d9e7d979a37423b2e0ba7a451dda41bc1c0f78b88967da268de9c7794
+size 23040672928

Llama-3-70B-Orpo-v0.1-Q8_0/Llama-3-70B-Orpo-v0.1-Q8_0-00001-of-00003.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b72cc027393911d36a8c667d38fc8e4c7373eff076a1b0af59b9c3b25c3343ac
+size 34980046208

Llama-3-70B-Orpo-v0.1-Q8_0/Llama-3-70B-Orpo-v0.1-Q8_0-00002-of-00003.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52552a020ec8185c1dee9a8ed06d40728cb9ef77c728e012f1021cf4677f6853
+size 34949976384

Llama-3-70B-Orpo-v0.1-Q8_0/Llama-3-70B-Orpo-v0.1-Q8_0-00003-of-00003.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42914d01bd4ed31b598e9ef7d4821c799faefd3c51569df5ec2e03b3de9ee2ac
+size 5045062560

README.md

@@ -0,0 +1,184 @@
+---
+language:
+- en
+license: llama3
+library_name: transformers
+tags:
+- orpo
+- llama 3
+- rlhf
+- sft
+- TensorBlock
+- GGUF
+base_model: dfurman/Llama-3-70B-Orpo-v0.1
+datasets:
+- mlabonne/orpo-dpo-mix-40k
+model-index:
+- name: Llama-3-70B-Orpo-v0.1
+  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: 20.49
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=dfurman/Llama-3-70B-Orpo-v0.1
+      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: 24.09
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=dfurman/Llama-3-70B-Orpo-v0.1
+      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: 13.52
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=dfurman/Llama-3-70B-Orpo-v0.1
+      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: 1.01
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=dfurman/Llama-3-70B-Orpo-v0.1
+      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: 16.28
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=dfurman/Llama-3-70B-Orpo-v0.1
+      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: 32.14
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=dfurman/Llama-3-70B-Orpo-v0.1
+      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>
+
+## dfurman/Llama-3-70B-Orpo-v0.1 - GGUF
+
+This repo contains GGUF format model files for [dfurman/Llama-3-70B-Orpo-v0.1](https://huggingface.co/dfurman/Llama-3-70B-Orpo-v0.1).
+
+The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4242](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
+
+<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 |
+| -------- | ---------- | --------- | ----------- |
+| [Llama-3-70B-Orpo-v0.1-Q2_K.gguf](https://huggingface.co/tensorblock/Llama-3-70B-Orpo-v0.1-GGUF/blob/main/Llama-3-70B-Orpo-v0.1-Q2_K.gguf) | Q2_K | 26.375 GB | smallest, significant quality loss - not recommended for most purposes |
+| [Llama-3-70B-Orpo-v0.1-Q3_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-70B-Orpo-v0.1-GGUF/blob/main/Llama-3-70B-Orpo-v0.1-Q3_K_S.gguf) | Q3_K_S | 30.912 GB | very small, high quality loss |
+| [Llama-3-70B-Orpo-v0.1-Q3_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-70B-Orpo-v0.1-GGUF/blob/main/Llama-3-70B-Orpo-v0.1-Q3_K_M.gguf) | Q3_K_M | 34.268 GB | very small, high quality loss |
+| [Llama-3-70B-Orpo-v0.1-Q3_K_L.gguf](https://huggingface.co/tensorblock/Llama-3-70B-Orpo-v0.1-GGUF/blob/main/Llama-3-70B-Orpo-v0.1-Q3_K_L.gguf) | Q3_K_L | 37.141 GB | small, substantial quality loss |
+| [Llama-3-70B-Orpo-v0.1-Q4_0.gguf](https://huggingface.co/tensorblock/Llama-3-70B-Orpo-v0.1-GGUF/blob/main/Llama-3-70B-Orpo-v0.1-Q4_0.gguf) | Q4_0 | 39.970 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Llama-3-70B-Orpo-v0.1-Q4_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-70B-Orpo-v0.1-GGUF/blob/main/Llama-3-70B-Orpo-v0.1-Q4_K_S.gguf) | Q4_K_S | 40.347 GB | small, greater quality loss |
+| [Llama-3-70B-Orpo-v0.1-Q4_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-70B-Orpo-v0.1-GGUF/blob/main/Llama-3-70B-Orpo-v0.1-Q4_K_M.gguf) | Q4_K_M | 42.520 GB | medium, balanced quality - recommended |
+| [Llama-3-70B-Orpo-v0.1-Q5_0.gguf](https://huggingface.co/tensorblock/Llama-3-70B-Orpo-v0.1-GGUF/blob/main/Llama-3-70B-Orpo-v0.1-Q5_0.gguf) | Q5_0 | 48.657 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Llama-3-70B-Orpo-v0.1-Q5_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-70B-Orpo-v0.1-GGUF/blob/main/Llama-3-70B-Orpo-v0.1-Q5_K_S.gguf) | Q5_K_S | 48.657 GB | large, low quality loss - recommended |
+| [Llama-3-70B-Orpo-v0.1-Q5_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-70B-Orpo-v0.1-GGUF/blob/main/Llama-3-70B-Orpo-v0.1-Q5_K_M.gguf) | Q5_K_M | 49.950 GB | large, very low quality loss - recommended |
+| [Llama-3-70B-Orpo-v0.1-Q6_K](https://huggingface.co/tensorblock/Llama-3-70B-Orpo-v0.1-GGUF/blob/main/Llama-3-70B-Orpo-v0.1-Q6_K) | Q6_K | 57.888 GB | very large, extremely low quality loss |
+| [Llama-3-70B-Orpo-v0.1-Q8_0](https://huggingface.co/tensorblock/Llama-3-70B-Orpo-v0.1-GGUF/blob/main/Llama-3-70B-Orpo-v0.1-Q8_0) | Q8_0 | 74.975 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/Llama-3-70B-Orpo-v0.1-GGUF --include "Llama-3-70B-Orpo-v0.1-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/Llama-3-70B-Orpo-v0.1-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```