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
+RedPajama-INCITE-Chat-Instruct-3B-V1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+RedPajama-INCITE-Chat-Instruct-3B-V1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+RedPajama-INCITE-Chat-Instruct-3B-V1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+RedPajama-INCITE-Chat-Instruct-3B-V1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+RedPajama-INCITE-Chat-Instruct-3B-V1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+RedPajama-INCITE-Chat-Instruct-3B-V1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+RedPajama-INCITE-Chat-Instruct-3B-V1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+RedPajama-INCITE-Chat-Instruct-3B-V1-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+RedPajama-INCITE-Chat-Instruct-3B-V1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+RedPajama-INCITE-Chat-Instruct-3B-V1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+RedPajama-INCITE-Chat-Instruct-3B-V1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+RedPajama-INCITE-Chat-Instruct-3B-V1-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,189 @@
+---
+language:
+- en
+license: apache-2.0
+library_name: transformers
+datasets:
+- togethercomputer/RedPajama-Data-1T
+- databricks/databricks-dolly-15k
+- OpenAssistant/oasst1
+- Muennighoff/natural-instructions
+- Muennighoff/P3
+pipeline_tag: text-generation
+tags:
+- TensorBlock
+- GGUF
+base_model: acrastt/RedPajama-INCITE-Chat-Instruct-3B-V1
+model-index:
+- name: RedPajama-INCITE-Chat-Instruct-3B-V1
+  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: 42.58
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/RedPajama-INCITE-Chat-Instruct-3B-V1
+      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: 67.48
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/RedPajama-INCITE-Chat-Instruct-3B-V1
+      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: 25.99
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/RedPajama-INCITE-Chat-Instruct-3B-V1
+      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: 33.62
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/RedPajama-INCITE-Chat-Instruct-3B-V1
+      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: 64.8
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/RedPajama-INCITE-Chat-Instruct-3B-V1
+      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: 0.91
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/RedPajama-INCITE-Chat-Instruct-3B-V1
+      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>
+
+## acrastt/RedPajama-INCITE-Chat-Instruct-3B-V1 - GGUF
+
+This repo contains GGUF format model files for [acrastt/RedPajama-INCITE-Chat-Instruct-3B-V1](https://huggingface.co/acrastt/RedPajama-INCITE-Chat-Instruct-3B-V1).
+
+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).
+
+<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 |
+| -------- | ---------- | --------- | ----------- |
+| [RedPajama-INCITE-Chat-Instruct-3B-V1-Q2_K.gguf](https://huggingface.co/tensorblock/RedPajama-INCITE-Chat-Instruct-3B-V1-GGUF/blob/main/RedPajama-INCITE-Chat-Instruct-3B-V1-Q2_K.gguf) | Q2_K | 1.012 GB | smallest, significant quality loss - not recommended for most purposes |
+| [RedPajama-INCITE-Chat-Instruct-3B-V1-Q3_K_S.gguf](https://huggingface.co/tensorblock/RedPajama-INCITE-Chat-Instruct-3B-V1-GGUF/blob/main/RedPajama-INCITE-Chat-Instruct-3B-V1-Q3_K_S.gguf) | Q3_K_S | 1.163 GB | very small, high quality loss |
+| [RedPajama-INCITE-Chat-Instruct-3B-V1-Q3_K_M.gguf](https://huggingface.co/tensorblock/RedPajama-INCITE-Chat-Instruct-3B-V1-GGUF/blob/main/RedPajama-INCITE-Chat-Instruct-3B-V1-Q3_K_M.gguf) | Q3_K_M | 1.377 GB | very small, high quality loss |
+| [RedPajama-INCITE-Chat-Instruct-3B-V1-Q3_K_L.gguf](https://huggingface.co/tensorblock/RedPajama-INCITE-Chat-Instruct-3B-V1-GGUF/blob/main/RedPajama-INCITE-Chat-Instruct-3B-V1-Q3_K_L.gguf) | Q3_K_L | 1.493 GB | small, substantial quality loss |
+| [RedPajama-INCITE-Chat-Instruct-3B-V1-Q4_0.gguf](https://huggingface.co/tensorblock/RedPajama-INCITE-Chat-Instruct-3B-V1-GGUF/blob/main/RedPajama-INCITE-Chat-Instruct-3B-V1-Q4_0.gguf) | Q4_0 | 1.490 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [RedPajama-INCITE-Chat-Instruct-3B-V1-Q4_K_S.gguf](https://huggingface.co/tensorblock/RedPajama-INCITE-Chat-Instruct-3B-V1-GGUF/blob/main/RedPajama-INCITE-Chat-Instruct-3B-V1-Q4_K_S.gguf) | Q4_K_S | 1.502 GB | small, greater quality loss |
+| [RedPajama-INCITE-Chat-Instruct-3B-V1-Q4_K_M.gguf](https://huggingface.co/tensorblock/RedPajama-INCITE-Chat-Instruct-3B-V1-GGUF/blob/main/RedPajama-INCITE-Chat-Instruct-3B-V1-Q4_K_M.gguf) | Q4_K_M | 1.664 GB | medium, balanced quality - recommended |
+| [RedPajama-INCITE-Chat-Instruct-3B-V1-Q5_0.gguf](https://huggingface.co/tensorblock/RedPajama-INCITE-Chat-Instruct-3B-V1-GGUF/blob/main/RedPajama-INCITE-Chat-Instruct-3B-V1-Q5_0.gguf) | Q5_0 | 1.798 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [RedPajama-INCITE-Chat-Instruct-3B-V1-Q5_K_S.gguf](https://huggingface.co/tensorblock/RedPajama-INCITE-Chat-Instruct-3B-V1-GGUF/blob/main/RedPajama-INCITE-Chat-Instruct-3B-V1-Q5_K_S.gguf) | Q5_K_S | 1.798 GB | large, low quality loss - recommended |
+| [RedPajama-INCITE-Chat-Instruct-3B-V1-Q5_K_M.gguf](https://huggingface.co/tensorblock/RedPajama-INCITE-Chat-Instruct-3B-V1-GGUF/blob/main/RedPajama-INCITE-Chat-Instruct-3B-V1-Q5_K_M.gguf) | Q5_K_M | 1.928 GB | large, very low quality loss - recommended |
+| [RedPajama-INCITE-Chat-Instruct-3B-V1-Q6_K.gguf](https://huggingface.co/tensorblock/RedPajama-INCITE-Chat-Instruct-3B-V1-GGUF/blob/main/RedPajama-INCITE-Chat-Instruct-3B-V1-Q6_K.gguf) | Q6_K | 2.126 GB | very large, extremely low quality loss |
+| [RedPajama-INCITE-Chat-Instruct-3B-V1-Q8_0.gguf](https://huggingface.co/tensorblock/RedPajama-INCITE-Chat-Instruct-3B-V1-GGUF/blob/main/RedPajama-INCITE-Chat-Instruct-3B-V1-Q8_0.gguf) | Q8_0 | 2.751 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/RedPajama-INCITE-Chat-Instruct-3B-V1-GGUF --include "RedPajama-INCITE-Chat-Instruct-3B-V1-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/RedPajama-INCITE-Chat-Instruct-3B-V1-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

RedPajama-INCITE-Chat-Instruct-3B-V1-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:368d2c5013474ac61fb237da703b0548755741d2388b0f84f76cdfeb91eb4181
+size 1086593760

RedPajama-INCITE-Chat-Instruct-3B-V1-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffe8f46265ff648310d8fe112ca31bf3d0400caba5a38d05bc065aa3d03f1513
+size 1602694880

RedPajama-INCITE-Chat-Instruct-3B-V1-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eeb453a615e303377ed7b14b2226ae4f72ce0c73be16815a99ab5b753d8cd25e
+size 1478176480

RedPajama-INCITE-Chat-Instruct-3B-V1-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24d337a287d0a4adcf97d8300b74790bcc402cf5994e0c0524262936b3c10c9d
+size 1248800480

RedPajama-INCITE-Chat-Instruct-3B-V1-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c36dfc26e8a81ea350afc96d5e9f4f2624d9353f75c857b64d1ba8cb211b3e7
+size 1600180960

RedPajama-INCITE-Chat-Instruct-3B-V1-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55cdb53257f545584459367662e1995f1694c5840239d3ccbf86e9b1d2deb503
+size 1786958560

RedPajama-INCITE-Chat-Instruct-3B-V1-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:340475f094be5721b38d2a10920c5e77c094a363fe85cde99de44b291ff3dfb7
+size 1613288160

RedPajama-INCITE-Chat-Instruct-3B-V1-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1151bf98e0fdb0cbedb467f99b14daea10a5b23f201435eb908b1ea09b14457
+size 1930892000

RedPajama-INCITE-Chat-Instruct-3B-V1-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f73cd13054f5e013bcd22f0aba995cf3d7fde2375b83bc7f3f3cb151d10e3bcc
+size 2070156000

RedPajama-INCITE-Chat-Instruct-3B-V1-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:074509a529a70f3ef6252bd393d7e36871548a8619f7eece9348e924cbd84059
+size 1930892000

RedPajama-INCITE-Chat-Instruct-3B-V1-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8db08e6e41c0193a958d6b234b2ea07688c43c7ef98444e37c8a58b13e063ab8
+size 2282272480

RedPajama-INCITE-Chat-Instruct-3B-V1-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2da9537f2338bf96a20a08e8a80e98c46e8449cd665856d5113e0791cf7bd0e9
+size 2954292960