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
+Refact-1_6B-fim-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Refact-1_6B-fim-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Refact-1_6B-fim-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Refact-1_6B-fim-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Refact-1_6B-fim-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Refact-1_6B-fim-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Refact-1_6B-fim-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Refact-1_6B-fim-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Refact-1_6B-fim-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Refact-1_6B-fim-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Refact-1_6B-fim-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Refact-1_6B-fim-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,340 @@
+---
+pipeline_tag: text-generation
+inference: true
+widget:
+- text: 'def print_hello_world():'
+  example_title: Hello world
+  group: Python
+license: bigscience-openrail-m
+pretrain-datasets:
+- books
+- arxiv
+- c4
+- falcon-refinedweb
+- wiki
+- github-issues
+- stack_markdown
+- self-made dataset of permissive github code
+datasets:
+- bigcode/the-stack-dedup
+- rombodawg/2XUNCENSORED_MegaCodeTraining188k
+- bigcode/commitpackft
+metrics:
+- code_eval
+library_name: transformers
+tags:
+- code
+- TensorBlock
+- GGUF
+language:
+- en
+base_model: smallcloudai/Refact-1_6B-fim
+model-index:
+- name: Refact-1.6B
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: HumanEval
+      type: openai_humaneval
+    metrics:
+    - type: pass@1
+      value: 32.0
+      name: pass@1 (T=0.01)
+      verified: false
+    - type: pass@1
+      value: 31.5
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@10
+      value: 53.0
+      name: pass@10 (T=0.8)
+      verified: false
+    - type: pass@100
+      value: 76.9
+      name: pass@100 (T=0.8)
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      name: HumanEvalSynthesize Python
+      type: bigcode/humanevalpack
+    metrics:
+    - type: pass@1
+      value: 35.8
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: 31.6
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: 29.1
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: -1
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: 26.3
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: -1
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: -1
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: 18.38
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: 12.28
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: 15.12
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: -1
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: 13.17
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: 2.8
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: -1
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: 26.92
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: 26.85
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: 30.76
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: -1
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: 25.94
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: 8.44
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: -1
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: 26.46
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: 17.86
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: 20.94
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: -1
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: 18.78
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: -1
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: -1
+      name: pass@1 (T=0.2)
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      name: MBPP
+      type: mbpp
+    metrics:
+    - type: pass@1
+      value: 31.15
+      name: pass@1 (T=0.01)
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      name: DS-1000 (Overall Completion)
+      type: ds1000
+    metrics:
+    - type: pass@1
+      value: 10.1
+      name: pass@1 (T=0.2)
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      name: MultiPL-HumanEval (C++)
+      type: nuprl/MultiPL-E
+    metrics:
+    - type: pass@1
+      value: 21.61
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: 13.91
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: 9.5
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: 53.57
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: 21.58
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: 13.75
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: 26.88
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: 15.26
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: 23.04
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: 12.1
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: 29.6
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: 13.77
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: 12.68
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: 4.29
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: 19.54
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: 18.33
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: 5.7
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: 17.68
+      name: pass@1 (T=0.2)
+      verified: false
+    - type: pass@1
+      value: 25
+      name: pass@1 (T=0.2)
+      verified: false
+---
+
+<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>
+
+## smallcloudai/Refact-1_6B-fim - GGUF
+
+This repo contains GGUF format model files for [smallcloudai/Refact-1_6B-fim](https://huggingface.co/smallcloudai/Refact-1_6B-fim).
+
+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).
+
+## Prompt template
+
+```
+
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [Refact-1_6B-fim-Q2_K.gguf](https://huggingface.co/tensorblock/Refact-1_6B-fim-GGUF/tree/main/Refact-1_6B-fim-Q2_K.gguf) | Q2_K | 0.581 GB | smallest, significant quality loss - not recommended for most purposes |
+| [Refact-1_6B-fim-Q3_K_S.gguf](https://huggingface.co/tensorblock/Refact-1_6B-fim-GGUF/tree/main/Refact-1_6B-fim-Q3_K_S.gguf) | Q3_K_S | 0.673 GB | very small, high quality loss |
+| [Refact-1_6B-fim-Q3_K_M.gguf](https://huggingface.co/tensorblock/Refact-1_6B-fim-GGUF/tree/main/Refact-1_6B-fim-Q3_K_M.gguf) | Q3_K_M | 0.739 GB | very small, high quality loss |
+| [Refact-1_6B-fim-Q3_K_L.gguf](https://huggingface.co/tensorblock/Refact-1_6B-fim-GGUF/tree/main/Refact-1_6B-fim-Q3_K_L.gguf) | Q3_K_L | 0.795 GB | small, substantial quality loss |
+| [Refact-1_6B-fim-Q4_0.gguf](https://huggingface.co/tensorblock/Refact-1_6B-fim-GGUF/tree/main/Refact-1_6B-fim-Q4_0.gguf) | Q4_0 | 0.857 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Refact-1_6B-fim-Q4_K_S.gguf](https://huggingface.co/tensorblock/Refact-1_6B-fim-GGUF/tree/main/Refact-1_6B-fim-Q4_K_S.gguf) | Q4_K_S | 0.862 GB | small, greater quality loss |
+| [Refact-1_6B-fim-Q4_K_M.gguf](https://huggingface.co/tensorblock/Refact-1_6B-fim-GGUF/tree/main/Refact-1_6B-fim-Q4_K_M.gguf) | Q4_K_M | 0.902 GB | medium, balanced quality - recommended |
+| [Refact-1_6B-fim-Q5_0.gguf](https://huggingface.co/tensorblock/Refact-1_6B-fim-GGUF/tree/main/Refact-1_6B-fim-Q5_0.gguf) | Q5_0 | 1.030 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Refact-1_6B-fim-Q5_K_S.gguf](https://huggingface.co/tensorblock/Refact-1_6B-fim-GGUF/tree/main/Refact-1_6B-fim-Q5_K_S.gguf) | Q5_K_S | 1.030 GB | large, low quality loss - recommended |
+| [Refact-1_6B-fim-Q5_K_M.gguf](https://huggingface.co/tensorblock/Refact-1_6B-fim-GGUF/tree/main/Refact-1_6B-fim-Q5_K_M.gguf) | Q5_K_M | 1.053 GB | large, very low quality loss - recommended |
+| [Refact-1_6B-fim-Q6_K.gguf](https://huggingface.co/tensorblock/Refact-1_6B-fim-GGUF/tree/main/Refact-1_6B-fim-Q6_K.gguf) | Q6_K | 1.214 GB | very large, extremely low quality loss |
+| [Refact-1_6B-fim-Q8_0.gguf](https://huggingface.co/tensorblock/Refact-1_6B-fim-GGUF/tree/main/Refact-1_6B-fim-Q8_0.gguf) | Q8_0 | 1.571 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/Refact-1_6B-fim-GGUF --include "Refact-1_6B-fim-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/Refact-1_6B-fim-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

Refact-1_6B-fim-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4aef77b7d50fb404a7996b91d4c3e25d086acb5e72367c104faf2345d0fd321a
+size 624292704

Refact-1_6B-fim-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74ed06cd2abfd37d3a2f28253aada6b386d0ed2f6f98271d06b72c685d2b1d99
+size 853845856

Refact-1_6B-fim-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df450f57dd07aaa5db23bbdb646858a4fa419605db65463bebb41445105f5a95
+size 793323360

Refact-1_6B-fim-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d1b5814004c90a291a1296cec4d7614b374807abd7a047a01a5da75a1c2d106
+size 723003232

Refact-1_6B-fim-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a52894d28c8a623f784c0a36b925cd9b1b31b4442f23f97510f4376bb4b7ce7
+size 920218464

Refact-1_6B-fim-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9c72df5570778f63a73db038be08c2715969e982519299d02d52a9ee87c5dc2
+size 968338272

Refact-1_6B-fim-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f86b9224327d52022b3954f2b4f01fe497aecee0f3b1fb3595ba478d66e316e
+size 926051168

Refact-1_6B-fim-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2e49cf8348f7560f44045f68e46acb1437b6aa9f5a0aed122bc874ab5ed0324
+size 1105832800

Refact-1_6B-fim-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3cbd25896b50fd426f73dba45f1d7bdf2866ff7a88c063b7204532dafbf12c3
+size 1130621792

Refact-1_6B-fim-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b33b7f1066d850dbdf4da92eabe3993f4753d7fae60c3212bdf8ae6356a82e8
+size 1105832800

Refact-1_6B-fim-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e173a3a37aae820ba93261bf9e1279fbbbd8c5dbdecfb377aff277252ecda0b
+size 1303048032

Refact-1_6B-fim-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37fe15a4fcf79257048316a0635b3a20e6c1b84930ca28944ad5041f2909ac51
+size 1687086944