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
+Smaug-Llama-3-70B-Instruct-32K-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Smaug-Llama-3-70B-Instruct-32K-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Smaug-Llama-3-70B-Instruct-32K-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Smaug-Llama-3-70B-Instruct-32K-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Smaug-Llama-3-70B-Instruct-32K-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Smaug-Llama-3-70B-Instruct-32K-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Smaug-Llama-3-70B-Instruct-32K-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Smaug-Llama-3-70B-Instruct-32K-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Smaug-Llama-3-70B-Instruct-32K-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Smaug-Llama-3-70B-Instruct-32K-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Smaug-Llama-3-70B-Instruct-32K-Q6_K/Smaug-Llama-3-70B-Instruct-32K-Q6_K-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+Smaug-Llama-3-70B-Instruct-32K-Q6_K/Smaug-Llama-3-70B-Instruct-32K-Q6_K-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+Smaug-Llama-3-70B-Instruct-32K-Q8_0/Smaug-Llama-3-70B-Instruct-32K-Q8_0-00001-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
+Smaug-Llama-3-70B-Instruct-32K-Q8_0/Smaug-Llama-3-70B-Instruct-32K-Q8_0-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
+Smaug-Llama-3-70B-Instruct-32K-Q8_0/Smaug-Llama-3-70B-Instruct-32K-Q8_0-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,180 @@
+---
+license: llama3
+library_name: transformers
+datasets:
+- aqua_rat
+- microsoft/orca-math-word-problems-200k
+- m-a-p/CodeFeedback-Filtered-Instruction
+base_model: abacusai/Smaug-Llama-3-70B-Instruct-32K
+tags:
+- TensorBlock
+- GGUF
+model-index:
+- name: Smaug-Llama-3-70B-Instruct-32K
+  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: 77.61
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=abacusai/Smaug-Llama-3-70B-Instruct-32K
+      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: 49.07
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=abacusai/Smaug-Llama-3-70B-Instruct-32K
+      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: 21.22
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=abacusai/Smaug-Llama-3-70B-Instruct-32K
+      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: 6.15
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=abacusai/Smaug-Llama-3-70B-Instruct-32K
+      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: 12.43
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=abacusai/Smaug-Llama-3-70B-Instruct-32K
+      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: 41.83
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=abacusai/Smaug-Llama-3-70B-Instruct-32K
+      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>
+
+## abacusai/Smaug-Llama-3-70B-Instruct-32K - GGUF
+
+This repo contains GGUF format model files for [abacusai/Smaug-Llama-3-70B-Instruct-32K](https://huggingface.co/abacusai/Smaug-Llama-3-70B-Instruct-32K).
+
+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
+
+```
+<|begin_of_text|><|start_header_id|>system<|end_header_id|>
+
+{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
+
+{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [Smaug-Llama-3-70B-Instruct-32K-Q2_K.gguf](https://huggingface.co/tensorblock/Smaug-Llama-3-70B-Instruct-32K-GGUF/blob/main/Smaug-Llama-3-70B-Instruct-32K-Q2_K.gguf) | Q2_K | 26.375 GB | smallest, significant quality loss - not recommended for most purposes |
+| [Smaug-Llama-3-70B-Instruct-32K-Q3_K_S.gguf](https://huggingface.co/tensorblock/Smaug-Llama-3-70B-Instruct-32K-GGUF/blob/main/Smaug-Llama-3-70B-Instruct-32K-Q3_K_S.gguf) | Q3_K_S | 30.912 GB | very small, high quality loss |
+| [Smaug-Llama-3-70B-Instruct-32K-Q3_K_M.gguf](https://huggingface.co/tensorblock/Smaug-Llama-3-70B-Instruct-32K-GGUF/blob/main/Smaug-Llama-3-70B-Instruct-32K-Q3_K_M.gguf) | Q3_K_M | 34.267 GB | very small, high quality loss |
+| [Smaug-Llama-3-70B-Instruct-32K-Q3_K_L.gguf](https://huggingface.co/tensorblock/Smaug-Llama-3-70B-Instruct-32K-GGUF/blob/main/Smaug-Llama-3-70B-Instruct-32K-Q3_K_L.gguf) | Q3_K_L | 37.141 GB | small, substantial quality loss |
+| [Smaug-Llama-3-70B-Instruct-32K-Q4_0.gguf](https://huggingface.co/tensorblock/Smaug-Llama-3-70B-Instruct-32K-GGUF/blob/main/Smaug-Llama-3-70B-Instruct-32K-Q4_0.gguf) | Q4_0 | 39.970 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Smaug-Llama-3-70B-Instruct-32K-Q4_K_S.gguf](https://huggingface.co/tensorblock/Smaug-Llama-3-70B-Instruct-32K-GGUF/blob/main/Smaug-Llama-3-70B-Instruct-32K-Q4_K_S.gguf) | Q4_K_S | 40.347 GB | small, greater quality loss |
+| [Smaug-Llama-3-70B-Instruct-32K-Q4_K_M.gguf](https://huggingface.co/tensorblock/Smaug-Llama-3-70B-Instruct-32K-GGUF/blob/main/Smaug-Llama-3-70B-Instruct-32K-Q4_K_M.gguf) | Q4_K_M | 42.520 GB | medium, balanced quality - recommended |
+| [Smaug-Llama-3-70B-Instruct-32K-Q5_0.gguf](https://huggingface.co/tensorblock/Smaug-Llama-3-70B-Instruct-32K-GGUF/blob/main/Smaug-Llama-3-70B-Instruct-32K-Q5_0.gguf) | Q5_0 | 48.657 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Smaug-Llama-3-70B-Instruct-32K-Q5_K_S.gguf](https://huggingface.co/tensorblock/Smaug-Llama-3-70B-Instruct-32K-GGUF/blob/main/Smaug-Llama-3-70B-Instruct-32K-Q5_K_S.gguf) | Q5_K_S | 48.657 GB | large, low quality loss - recommended |
+| [Smaug-Llama-3-70B-Instruct-32K-Q5_K_M.gguf](https://huggingface.co/tensorblock/Smaug-Llama-3-70B-Instruct-32K-GGUF/blob/main/Smaug-Llama-3-70B-Instruct-32K-Q5_K_M.gguf) | Q5_K_M | 49.950 GB | large, very low quality loss - recommended |
+| [Smaug-Llama-3-70B-Instruct-32K-Q8_0](https://huggingface.co/tensorblock/Smaug-Llama-3-70B-Instruct-32K-GGUF/blob/main/Smaug-Llama-3-70B-Instruct-32K-Q8_0) | Q6_K | 74.975 GB | very large, extremely low quality loss |
+| [Smaug-Llama-3-70B-Instruct-32K-Q6_K](https://huggingface.co/tensorblock/Smaug-Llama-3-70B-Instruct-32K-GGUF/blob/main/Smaug-Llama-3-70B-Instruct-32K-Q6_K) | Q8_0 | 57.888 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/Smaug-Llama-3-70B-Instruct-32K-GGUF --include "Smaug-Llama-3-70B-Instruct-32K-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/Smaug-Llama-3-70B-Instruct-32K-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

Smaug-Llama-3-70B-Instruct-32K-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7ce9c7e490c20b11e4ac50827fb6009b0cb53f91cda4244dda719cd41291e40
+size 26375108928

Smaug-Llama-3-70B-Instruct-32K-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baec4b89e3cde03e63e8384e46742e7de4058408978f06a2cdb64ba8dc3baca4
+size 37140592960

Smaug-Llama-3-70B-Instruct-32K-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1d2986af7c47caa46b9a4b6b16722a76e345741ba513bc928ddaa0288d3ae74
+size 34267494720

Smaug-Llama-3-70B-Instruct-32K-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba874ee6ae790b9c2986d8e07f05808a3fccade492dd45f159b076aaf3056fb4
+size 30912051520

Smaug-Llama-3-70B-Instruct-32K-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a03821628d6f728ca0488855462ff2af5c92df5219bd2cf9f115fc42f837de3d
+size 39969732928

Smaug-Llama-3-70B-Instruct-32K-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97dd729c89877a0c0b8849718768bac89c3a9fca1abc822883a8188b174d029d
+size 42520394048

Smaug-Llama-3-70B-Instruct-32K-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d4d18a7afaa0daa80cc42aab81887630600cc74fe9333a8a7e370834e947a33
+size 40347220288

Smaug-Llama-3-70B-Instruct-32K-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb3f022e5dc82d9681f05ecb0ff648a6e6f08237dd92b8f65988fb60b5022427
+size 48657447232

Smaug-Llama-3-70B-Instruct-32K-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56f822e63a0b63592071487298959b3387a7b7d513a9afe0f0eacdd6c3fcbdaa
+size 49949817152

Smaug-Llama-3-70B-Instruct-32K-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad62143d7b80ebccd5e8017349e573ef04be50130912aea8bf0045450bce2b28
+size 48657447232

Smaug-Llama-3-70B-Instruct-32K-Q6_K/Smaug-Llama-3-70B-Instruct-32K-Q6_K-00001-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:033e8d7621302513e0fccef915e2a6a35258853676148d0c4ec655ad9c36b636
+size 34847470976

Smaug-Llama-3-70B-Instruct-32K-Q6_K/Smaug-Llama-3-70B-Instruct-32K-Q6_K-00002-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:073149daead167b4501e0937b16bbd848fd7064b128792ac7bca5550a79d5f0d
+size 23040672928

Smaug-Llama-3-70B-Instruct-32K-Q8_0/Smaug-Llama-3-70B-Instruct-32K-Q8_0-00001-of-00003.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc5dc480f5272a04a4a15604a90704a40dcc633bcccde90adac139634d79e171
+size 34980011424

Smaug-Llama-3-70B-Instruct-32K-Q8_0/Smaug-Llama-3-70B-Instruct-32K-Q8_0-00002-of-00003.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81b415dde2f0dfaa7d4a856daf301ee8b156a975f03ddf92d1f25a35777d8536
+size 34949976384

Smaug-Llama-3-70B-Instruct-32K-Q8_0/Smaug-Llama-3-70B-Instruct-32K-Q8_0-00003-of-00003.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab67a1b497daf1dff5db165a77b0f89c7e40f59bbe100c609590532423a2d119
+size 5045062560