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
+ToRoLaMa-7b-v1.0-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+ToRoLaMa-7b-v1.0-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+ToRoLaMa-7b-v1.0-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+ToRoLaMa-7b-v1.0-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+ToRoLaMa-7b-v1.0-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+ToRoLaMa-7b-v1.0-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+ToRoLaMa-7b-v1.0-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+ToRoLaMa-7b-v1.0-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+ToRoLaMa-7b-v1.0-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+ToRoLaMa-7b-v1.0-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+ToRoLaMa-7b-v1.0-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+ToRoLaMa-7b-v1.0-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,183 @@
+---
+language:
+- vi
+- en
+license: llama2
+pipeline_tag: text-generation
+tags:
+- TensorBlock
+- GGUF
+base_model: allbyai/ToRoLaMa-7b-v1.0
+model-index:
+- name: ToRoLaMa-7b-v1.0
+  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: 51.71
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=allbyai/ToRoLaMa-7b-v1.0
+      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: 73.82
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=allbyai/ToRoLaMa-7b-v1.0
+      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: 45.34
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=allbyai/ToRoLaMa-7b-v1.0
+      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: 44.89
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=allbyai/ToRoLaMa-7b-v1.0
+      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: 70.09
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=allbyai/ToRoLaMa-7b-v1.0
+      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: 1.36
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=allbyai/ToRoLaMa-7b-v1.0
+      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>
+
+## allbyai/ToRoLaMa-7b-v1.0 - GGUF
+
+This repo contains GGUF format model files for [allbyai/ToRoLaMa-7b-v1.0](https://huggingface.co/allbyai/ToRoLaMa-7b-v1.0).
+
+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
+
+```
+
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [ToRoLaMa-7b-v1.0-Q2_K.gguf](https://huggingface.co/tensorblock/ToRoLaMa-7b-v1.0-GGUF/blob/main/ToRoLaMa-7b-v1.0-Q2_K.gguf) | Q2_K | 2.600 GB | smallest, significant quality loss - not recommended for most purposes |
+| [ToRoLaMa-7b-v1.0-Q3_K_S.gguf](https://huggingface.co/tensorblock/ToRoLaMa-7b-v1.0-GGUF/blob/main/ToRoLaMa-7b-v1.0-Q3_K_S.gguf) | Q3_K_S | 3.022 GB | very small, high quality loss |
+| [ToRoLaMa-7b-v1.0-Q3_K_M.gguf](https://huggingface.co/tensorblock/ToRoLaMa-7b-v1.0-GGUF/blob/main/ToRoLaMa-7b-v1.0-Q3_K_M.gguf) | Q3_K_M | 3.372 GB | very small, high quality loss |
+| [ToRoLaMa-7b-v1.0-Q3_K_L.gguf](https://huggingface.co/tensorblock/ToRoLaMa-7b-v1.0-GGUF/blob/main/ToRoLaMa-7b-v1.0-Q3_K_L.gguf) | Q3_K_L | 3.671 GB | small, substantial quality loss |
+| [ToRoLaMa-7b-v1.0-Q4_0.gguf](https://huggingface.co/tensorblock/ToRoLaMa-7b-v1.0-GGUF/blob/main/ToRoLaMa-7b-v1.0-Q4_0.gguf) | Q4_0 | 3.907 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [ToRoLaMa-7b-v1.0-Q4_K_S.gguf](https://huggingface.co/tensorblock/ToRoLaMa-7b-v1.0-GGUF/blob/main/ToRoLaMa-7b-v1.0-Q4_K_S.gguf) | Q4_K_S | 3.938 GB | small, greater quality loss |
+| [ToRoLaMa-7b-v1.0-Q4_K_M.gguf](https://huggingface.co/tensorblock/ToRoLaMa-7b-v1.0-GGUF/blob/main/ToRoLaMa-7b-v1.0-Q4_K_M.gguf) | Q4_K_M | 4.162 GB | medium, balanced quality - recommended |
+| [ToRoLaMa-7b-v1.0-Q5_0.gguf](https://huggingface.co/tensorblock/ToRoLaMa-7b-v1.0-GGUF/blob/main/ToRoLaMa-7b-v1.0-Q5_0.gguf) | Q5_0 | 4.740 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [ToRoLaMa-7b-v1.0-Q5_K_S.gguf](https://huggingface.co/tensorblock/ToRoLaMa-7b-v1.0-GGUF/blob/main/ToRoLaMa-7b-v1.0-Q5_K_S.gguf) | Q5_K_S | 4.740 GB | large, low quality loss - recommended |
+| [ToRoLaMa-7b-v1.0-Q5_K_M.gguf](https://huggingface.co/tensorblock/ToRoLaMa-7b-v1.0-GGUF/blob/main/ToRoLaMa-7b-v1.0-Q5_K_M.gguf) | Q5_K_M | 4.872 GB | large, very low quality loss - recommended |
+| [ToRoLaMa-7b-v1.0-Q6_K.gguf](https://huggingface.co/tensorblock/ToRoLaMa-7b-v1.0-GGUF/blob/main/ToRoLaMa-7b-v1.0-Q6_K.gguf) | Q6_K | 5.626 GB | very large, extremely low quality loss |
+| [ToRoLaMa-7b-v1.0-Q8_0.gguf](https://huggingface.co/tensorblock/ToRoLaMa-7b-v1.0-GGUF/blob/main/ToRoLaMa-7b-v1.0-Q8_0.gguf) | Q8_0 | 7.286 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/ToRoLaMa-7b-v1.0-GGUF --include "ToRoLaMa-7b-v1.0-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/ToRoLaMa-7b-v1.0-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

ToRoLaMa-7b-v1.0-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53695d856d093443b8daee5502740bbe6ea6759f83992502bfd94b71dfb4d4ac
+size 2600474208

ToRoLaMa-7b-v1.0-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb698ac2900376243e53cfb08cb74fe3cbbb0f2454ebcfb175be55d07349917
+size 3670671552

ToRoLaMa-7b-v1.0-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ecfa12aaa40bdaa57b338ffefb454096edda3712fb637e50a82c581694a5d8e
+size 3371565248

ToRoLaMa-7b-v1.0-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70ec0f6ceb746074e56ac16a4b895159a437a79f8b14ede21c41ff5074013419
+size 3021865152

ToRoLaMa-7b-v1.0-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9bd703dc4d1ec597955a6ac0d12191719662c94b9695128b473aad5af5a2cec
+size 3907148448

ToRoLaMa-7b-v1.0-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20d154d6101bc07269a88b1cec21b252079d91d1be69769bada22aeb1af649e5
+size 4162345632

ToRoLaMa-7b-v1.0-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d4acbc0a7bf1c97db8f4d975ecbf57ed157b25bf5901232b7e8d57210563ce0
+size 3938081440

ToRoLaMa-7b-v1.0-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3ed0ce066d1ba64e3daeda5f2fb323c2ccc954f43b04553b7dc11367faca539
+size 4740356256

ToRoLaMa-7b-v1.0-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad4ab0a6da3b6366082a7bc77bc9f431910c908077288d0c66f622cfa9d6e03b
+size 4871821472

ToRoLaMa-7b-v1.0-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d6293789bb66407157134b335d34cc0ebc01faa85653bd7612794bbf6ba654f
+size 4740356256

ToRoLaMa-7b-v1.0-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7394f83523906567adc3de8a877b3f562a72a5ffe5e245f45dea72f7cbffb5fc
+size 5625639552

ToRoLaMa-7b-v1.0-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d37a0fc9770f7307f09c92420818d983da94887dd6ba3fde2cadd75989a4dbf
+size 7285912256