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
+megatron_1.1_MoE_2x7B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+megatron_1.1_MoE_2x7B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+megatron_1.1_MoE_2x7B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+megatron_1.1_MoE_2x7B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+megatron_1.1_MoE_2x7B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+megatron_1.1_MoE_2x7B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+megatron_1.1_MoE_2x7B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+megatron_1.1_MoE_2x7B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+megatron_1.1_MoE_2x7B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+megatron_1.1_MoE_2x7B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+megatron_1.1_MoE_2x7B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+megatron_1.1_MoE_2x7B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,183 @@
+---
+license: apache-2.0
+tags:
+- frankenmoe
+- merge
+- MoE
+- Mixtral
+- TensorBlock
+- GGUF
+base_model: Eurdem/megatron_1.1_MoE_2x7B
+model-index:
+- name: megatron_1.1_MoE_2x7B
+  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: 65.53
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Eurdem/megatron_1.1_MoE_2x7B
+      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: 84.52
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Eurdem/megatron_1.1_MoE_2x7B
+      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: 65.02
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Eurdem/megatron_1.1_MoE_2x7B
+      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: 51.58
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Eurdem/megatron_1.1_MoE_2x7B
+      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: 81.53
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Eurdem/megatron_1.1_MoE_2x7B
+      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: 71.49
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Eurdem/megatron_1.1_MoE_2x7B
+      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>
+
+## Eurdem/megatron_1.1_MoE_2x7B - GGUF
+
+This repo contains GGUF format model files for [Eurdem/megatron_1.1_MoE_2x7B](https://huggingface.co/Eurdem/megatron_1.1_MoE_2x7B).
+
+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
+
+```
+<s>GPT4 Correct System: {system_prompt}<|end_of_turn|>GPT4 Correct User: {prompt}<|end_of_turn|>GPT4 Correct Assistant:
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [megatron_1.1_MoE_2x7B-Q2_K.gguf](https://huggingface.co/tensorblock/megatron_1.1_MoE_2x7B-GGUF/blob/main/megatron_1.1_MoE_2x7B-Q2_K.gguf) | Q2_K | 4.761 GB | smallest, significant quality loss - not recommended for most purposes |
+| [megatron_1.1_MoE_2x7B-Q3_K_S.gguf](https://huggingface.co/tensorblock/megatron_1.1_MoE_2x7B-GGUF/blob/main/megatron_1.1_MoE_2x7B-Q3_K_S.gguf) | Q3_K_S | 5.588 GB | very small, high quality loss |
+| [megatron_1.1_MoE_2x7B-Q3_K_M.gguf](https://huggingface.co/tensorblock/megatron_1.1_MoE_2x7B-GGUF/blob/main/megatron_1.1_MoE_2x7B-Q3_K_M.gguf) | Q3_K_M | 6.207 GB | very small, high quality loss |
+| [megatron_1.1_MoE_2x7B-Q3_K_L.gguf](https://huggingface.co/tensorblock/megatron_1.1_MoE_2x7B-GGUF/blob/main/megatron_1.1_MoE_2x7B-Q3_K_L.gguf) | Q3_K_L | 6.730 GB | small, substantial quality loss |
+| [megatron_1.1_MoE_2x7B-Q4_0.gguf](https://huggingface.co/tensorblock/megatron_1.1_MoE_2x7B-GGUF/blob/main/megatron_1.1_MoE_2x7B-Q4_0.gguf) | Q4_0 | 7.281 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [megatron_1.1_MoE_2x7B-Q4_K_S.gguf](https://huggingface.co/tensorblock/megatron_1.1_MoE_2x7B-GGUF/blob/main/megatron_1.1_MoE_2x7B-Q4_K_S.gguf) | Q4_K_S | 7.342 GB | small, greater quality loss |
+| [megatron_1.1_MoE_2x7B-Q4_K_M.gguf](https://huggingface.co/tensorblock/megatron_1.1_MoE_2x7B-GGUF/blob/main/megatron_1.1_MoE_2x7B-Q4_K_M.gguf) | Q4_K_M | 7.783 GB | medium, balanced quality - recommended |
+| [megatron_1.1_MoE_2x7B-Q5_0.gguf](https://huggingface.co/tensorblock/megatron_1.1_MoE_2x7B-GGUF/blob/main/megatron_1.1_MoE_2x7B-Q5_0.gguf) | Q5_0 | 8.874 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [megatron_1.1_MoE_2x7B-Q5_K_S.gguf](https://huggingface.co/tensorblock/megatron_1.1_MoE_2x7B-GGUF/blob/main/megatron_1.1_MoE_2x7B-Q5_K_S.gguf) | Q5_K_S | 8.874 GB | large, low quality loss - recommended |
+| [megatron_1.1_MoE_2x7B-Q5_K_M.gguf](https://huggingface.co/tensorblock/megatron_1.1_MoE_2x7B-GGUF/blob/main/megatron_1.1_MoE_2x7B-Q5_K_M.gguf) | Q5_K_M | 9.133 GB | large, very low quality loss - recommended |
+| [megatron_1.1_MoE_2x7B-Q6_K.gguf](https://huggingface.co/tensorblock/megatron_1.1_MoE_2x7B-GGUF/blob/main/megatron_1.1_MoE_2x7B-Q6_K.gguf) | Q6_K | 10.567 GB | very large, extremely low quality loss |
+| [megatron_1.1_MoE_2x7B-Q8_0.gguf](https://huggingface.co/tensorblock/megatron_1.1_MoE_2x7B-GGUF/blob/main/megatron_1.1_MoE_2x7B-Q8_0.gguf) | Q8_0 | 13.686 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/megatron_1.1_MoE_2x7B-GGUF --include "megatron_1.1_MoE_2x7B-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/megatron_1.1_MoE_2x7B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

megatron_1.1_MoE_2x7B-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cc467f5bb4453621f7aee0ad316f6a999b81f42ca04502eed608fe3393a7f5e
+size 4760833056

megatron_1.1_MoE_2x7B-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0ecb28bb59e462b905c1471efb1192da6e0f7fc3b2ceae1800b872be79df086
+size 6729740128

megatron_1.1_MoE_2x7B-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ce398520d5e8f9addb73d9eb73ebb20d792713dab65b7d3957c68cba81d4a12
+size 6206500704

megatron_1.1_MoE_2x7B-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0040b95f07370ea9c526a7a6158c2a3e5e7a9807bd43031a742504ed2672a98e
+size 5587840864

megatron_1.1_MoE_2x7B-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b94bb414d73ca75d4f81f6658979f658e315c7bbefab85d4bee6aa4f5e24a8b
+size 7280874400

megatron_1.1_MoE_2x7B-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:914e94be22eddb0f3b465b6424c287049256c6ecd7e0d2e786a10f1206278e0c
+size 7782618016

megatron_1.1_MoE_2x7B-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f5a3ff94f37b9e379f96860a40ab65b5b642ee46f4f74fd0486fbf29f3a3261
+size 7341691808

megatron_1.1_MoE_2x7B-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf074bebd7a680ffeac5d02cfdfc212296ce539b49dfd6d31ece143572f0be4a
+size 8874317728

megatron_1.1_MoE_2x7B-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4da7138835748e6ecd4a0ce2e6e61906a8b626f48df94c4c3f9adedc395ab1b
+size 9132791712

megatron_1.1_MoE_2x7B-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8913f0d3ccd51747ecf2c5f02f89a4a87d6bbca0bb3ef45b26a43c54cbbe45e3
+size 8874317728

megatron_1.1_MoE_2x7B-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ae210628dd9c9630a8dfdf17e02f07bcbf5bf5c4601c9cafb8c2993267589ad
+size 10567351264

megatron_1.1_MoE_2x7B-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1ff3e99a06d0fc801a54e874ea9df8525977a9327c8d70bdbdbadf2b70a323b
+size 13686393696