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
+open_llama_3b_code_instruct_0.1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+open_llama_3b_code_instruct_0.1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+open_llama_3b_code_instruct_0.1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+open_llama_3b_code_instruct_0.1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+open_llama_3b_code_instruct_0.1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+open_llama_3b_code_instruct_0.1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+open_llama_3b_code_instruct_0.1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+open_llama_3b_code_instruct_0.1-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+open_llama_3b_code_instruct_0.1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+open_llama_3b_code_instruct_0.1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+open_llama_3b_code_instruct_0.1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+open_llama_3b_code_instruct_0.1-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,262 @@
+---
+language:
+- en
+license: apache-2.0
+library_name: transformers
+tags:
+- transformers
+- TensorBlock
+- GGUF
+datasets:
+- mwitiderrick/AlpacaCode
+base_model: mwitiderrick/open_llama_3b_code_instruct_0.1
+inference: true
+model_type: llama
+prompt_template: '### Instruction:\n
+
+  {prompt}
+
+  ### Response:
+
+  '
+created_by: mwitiderrick
+pipeline_tag: text-generation
+model-index:
+- name: mwitiderrick/open_llama_3b_instruct_v_0.2
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: hellaswag
+      type: hellaswag
+    metrics:
+    - type: hellaswag (0-Shot)
+      value: 0.6581
+      name: hellaswag(0-Shot)
+  - task:
+      type: text-generation
+    dataset:
+      name: winogrande
+      type: winogrande
+    metrics:
+    - type: winogrande (0-Shot)
+      value: 0.6267
+      name: winogrande(0-Shot)
+  - task:
+      type: text-generation
+    dataset:
+      name: arc_challenge
+      type: arc_challenge
+    metrics:
+    - type: arc_challenge (0-Shot)
+      value: 0.3712
+      name: arc_challenge(0-Shot)
+    source:
+      url: https://huggingface.co/mwitiderrick/open_llama_3b_instruct_v_0.2
+      name: open_llama_3b_instruct_v_0.2 model card
+  - 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: 41.21
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mwitiderrick/open_llama_3b_code_instruct_0.1
+      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: 66.96
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mwitiderrick/open_llama_3b_code_instruct_0.1
+      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: 27.82
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mwitiderrick/open_llama_3b_code_instruct_0.1
+      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: 35.01
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mwitiderrick/open_llama_3b_code_instruct_0.1
+      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: 65.43
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mwitiderrick/open_llama_3b_code_instruct_0.1
+      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: 1.9
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mwitiderrick/open_llama_3b_code_instruct_0.1
+      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>
+
+## mwitiderrick/open_llama_3b_code_instruct_0.1 - GGUF
+
+This repo contains GGUF format model files for [mwitiderrick/open_llama_3b_code_instruct_0.1](https://huggingface.co/mwitiderrick/open_llama_3b_code_instruct_0.1).
+
+The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b5165](https://github.com/ggml-org/llama.cpp/commit/1d735c0b4fa0551c51c2f4ac888dd9a01f447985).
+
+## Our projects
+<table border="1" cellspacing="0" cellpadding="10">
+<tr>
+  <th style="font-size: 25px;">Awesome MCP Servers</th>
+  <th style="font-size: 25px;">TensorBlock Studio</th>
+</tr>
+  <tr>
+    <th><img src="https://imgur.com/2Xov7B7.jpeg" alt="Project A" width="450"/></th>
+    <th><img src="https://imgur.com/pJcmF5u.jpeg" alt="Project B" width="450"/></th>
+  </tr>
+  <tr>
+    <th>A comprehensive collection of Model Context Protocol (MCP) servers.</th>
+    <th>A lightweight, open, and extensible multi-LLM interaction studio.</th>
+  </tr>
+<tr>
+  <th>
+    <a href="https://github.com/TensorBlock/awesome-mcp-servers" target="_blank" style="
+      display: inline-block;
+      padding: 8px 16px;
+      background-color: #FF7F50;
+      color: white;
+      text-decoration: none;
+      border-radius: 6px;
+      font-weight: bold;
+      font-family: sans-serif;
+    ">👀 See what we built 👀</a>
+  </th>
+  <th>
+    <a href="https://github.com/TensorBlock/TensorBlock-Studio" target="_blank" style="
+      display: inline-block;
+      padding: 8px 16px;
+      background-color: #FF7F50;
+      color: white;
+      text-decoration: none;
+      border-radius: 6px;
+      font-weight: bold;
+      font-family: sans-serif;
+    ">👀 See what we built 👀</a>
+  </th>
+</tr>
+</table>
+
+## Prompt template
+
+```
+Unable to determine prompt format automatically. Please check the original model repository for the correct prompt format.
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [open_llama_3b_code_instruct_0.1-Q2_K.gguf](https://huggingface.co/tensorblock/mwitiderrick_open_llama_3b_code_instruct_0.1-GGUF/blob/main/open_llama_3b_code_instruct_0.1-Q2_K.gguf) | Q2_K | 1.980 GB | smallest, significant quality loss - not recommended for most purposes |
+| [open_llama_3b_code_instruct_0.1-Q3_K_S.gguf](https://huggingface.co/tensorblock/mwitiderrick_open_llama_3b_code_instruct_0.1-GGUF/blob/main/open_llama_3b_code_instruct_0.1-Q3_K_S.gguf) | Q3_K_S | 1.980 GB | very small, high quality loss |
+| [open_llama_3b_code_instruct_0.1-Q3_K_M.gguf](https://huggingface.co/tensorblock/mwitiderrick_open_llama_3b_code_instruct_0.1-GGUF/blob/main/open_llama_3b_code_instruct_0.1-Q3_K_M.gguf) | Q3_K_M | 2.139 GB | very small, high quality loss |
+| [open_llama_3b_code_instruct_0.1-Q3_K_L.gguf](https://huggingface.co/tensorblock/mwitiderrick_open_llama_3b_code_instruct_0.1-GGUF/blob/main/open_llama_3b_code_instruct_0.1-Q3_K_L.gguf) | Q3_K_L | 2.215 GB | small, substantial quality loss |
+| [open_llama_3b_code_instruct_0.1-Q4_0.gguf](https://huggingface.co/tensorblock/mwitiderrick_open_llama_3b_code_instruct_0.1-GGUF/blob/main/open_llama_3b_code_instruct_0.1-Q4_0.gguf) | Q4_0 | 1.980 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [open_llama_3b_code_instruct_0.1-Q4_K_S.gguf](https://huggingface.co/tensorblock/mwitiderrick_open_llama_3b_code_instruct_0.1-GGUF/blob/main/open_llama_3b_code_instruct_0.1-Q4_K_S.gguf) | Q4_K_S | 2.403 GB | small, greater quality loss |
+| [open_llama_3b_code_instruct_0.1-Q4_K_M.gguf](https://huggingface.co/tensorblock/mwitiderrick_open_llama_3b_code_instruct_0.1-GGUF/blob/main/open_llama_3b_code_instruct_0.1-Q4_K_M.gguf) | Q4_K_M | 2.580 GB | medium, balanced quality - recommended |
+| [open_llama_3b_code_instruct_0.1-Q5_0.gguf](https://huggingface.co/tensorblock/mwitiderrick_open_llama_3b_code_instruct_0.1-GGUF/blob/main/open_llama_3b_code_instruct_0.1-Q5_0.gguf) | Q5_0 | 2.395 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [open_llama_3b_code_instruct_0.1-Q5_K_S.gguf](https://huggingface.co/tensorblock/mwitiderrick_open_llama_3b_code_instruct_0.1-GGUF/blob/main/open_llama_3b_code_instruct_0.1-Q5_K_S.gguf) | Q5_K_S | 2.603 GB | large, low quality loss - recommended |
+| [open_llama_3b_code_instruct_0.1-Q5_K_M.gguf](https://huggingface.co/tensorblock/mwitiderrick_open_llama_3b_code_instruct_0.1-GGUF/blob/main/open_llama_3b_code_instruct_0.1-Q5_K_M.gguf) | Q5_K_M | 2.757 GB | large, very low quality loss - recommended |
+| [open_llama_3b_code_instruct_0.1-Q6_K.gguf](https://huggingface.co/tensorblock/mwitiderrick_open_llama_3b_code_instruct_0.1-GGUF/blob/main/open_llama_3b_code_instruct_0.1-Q6_K.gguf) | Q6_K | 3.642 GB | very large, extremely low quality loss |
+| [open_llama_3b_code_instruct_0.1-Q8_0.gguf](https://huggingface.co/tensorblock/mwitiderrick_open_llama_3b_code_instruct_0.1-GGUF/blob/main/open_llama_3b_code_instruct_0.1-Q8_0.gguf) | Q8_0 | 3.642 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/mwitiderrick_open_llama_3b_code_instruct_0.1-GGUF --include "open_llama_3b_code_instruct_0.1-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/mwitiderrick_open_llama_3b_code_instruct_0.1-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

open_llama_3b_code_instruct_0.1-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff6a79c253cd781b25a1e74543280e98fc4f26e91198673949a33c1e0efd44ea
+size 1979947840

open_llama_3b_code_instruct_0.1-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16721d37e85b015872c8843efaee4057e1dd87cda9bf31c9baa07cbda6f69041
+size 2214571840

open_llama_3b_code_instruct_0.1-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55bb922ba2087b7e60d4e08ff0a0b3a8e1a68b3943fbcf9fcf106d315515ea19
+size 2139371840

open_llama_3b_code_instruct_0.1-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d6c5bd21e86925a3367c8223c1710979d5058e9b674df4e7b60a6040b9517ba
+size 1979947840

open_llama_3b_code_instruct_0.1-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:807ec224587303687bcae04e5ebe43810b10c627e2069ed9068bb1eab9593986
+size 1979947840

open_llama_3b_code_instruct_0.1-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba21eb95c63fd0c96f5f0b7323f0f1a1655a71800daa0db6434a315054534fe3
+size 2580139840

open_llama_3b_code_instruct_0.1-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03ee51e32c75c609f6a33ef6016a78724e9a4b5304becf71800ebfb521951d16
+size 2403179840

open_llama_3b_code_instruct_0.1-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14c0c0199f3a06e4a75e8d7d8dc905cef74675ef9b429010f32cf68a83a4832c
+size 2395435840

open_llama_3b_code_instruct_0.1-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d17a1787dca12f1fd51cfe5b0c9ddc17caac6a9baab08a5007ab4c50e95bcf9b
+size 2757099840

open_llama_3b_code_instruct_0.1-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95ff34ed7ccaaa8116d9fc7bbffd970867c998b483650faaaef445bd9bc27f0d
+size 2603179840

open_llama_3b_code_instruct_0.1-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b1332f763ab6ccb1cc357742259eb84e39b5c03d66a25de5d96ddb4729d8359
+size 3641899840

open_llama_3b_code_instruct_0.1-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93a3fa17fda007eba5f8b5fddde039af6d455b4f3eebfe3169a51df463493514
+size 3641899840