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
+dolphin-2.2-yi-34b-200k-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+dolphin-2.2-yi-34b-200k-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+dolphin-2.2-yi-34b-200k-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+dolphin-2.2-yi-34b-200k-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+dolphin-2.2-yi-34b-200k-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+dolphin-2.2-yi-34b-200k-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+dolphin-2.2-yi-34b-200k-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+dolphin-2.2-yi-34b-200k-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+dolphin-2.2-yi-34b-200k-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+dolphin-2.2-yi-34b-200k-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+dolphin-2.2-yi-34b-200k-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+dolphin-2.2-yi-34b-200k-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,226 @@
+---
+language:
+- en
+datasets:
+- ehartford/dolphin
+- jondurbin/airoboros-2.2.1
+- ehartford/samantha-data
+- ehartford/WizardLM_evol_instruct_V2_196k_unfiltered_merged_split
+license: apache-2.0
+tags:
+- TensorBlock
+- GGUF
+base_model: cognitivecomputations/dolphin-2.2-yi-34b-200k
+model-index:
+- name: dolphin-2.2-yi-34b-200k
+  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: 42.15
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ehartford/dolphin-2.2-yi-34b-200k
+      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: 68.18
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ehartford/dolphin-2.2-yi-34b-200k
+      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: 55.47
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ehartford/dolphin-2.2-yi-34b-200k
+      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: 45.93
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ehartford/dolphin-2.2-yi-34b-200k
+      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: 64.56
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ehartford/dolphin-2.2-yi-34b-200k
+      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: 3.71
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ehartford/dolphin-2.2-yi-34b-200k
+      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>
+
+## cognitivecomputations/dolphin-2.2-yi-34b-200k - GGUF
+
+This repo contains GGUF format model files for [cognitivecomputations/dolphin-2.2-yi-34b-200k](https://huggingface.co/cognitivecomputations/dolphin-2.2-yi-34b-200k).
+
+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
+
+```
+<|im_start|>system
+{system_prompt}<|im_end|>
+<|im_start|>user
+{prompt}<|im_end|>
+<|im_start|>assistant
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [dolphin-2.2-yi-34b-200k-Q2_K.gguf](https://huggingface.co/tensorblock/cognitivecomputations_dolphin-2.2-yi-34b-200k-GGUF/blob/main/dolphin-2.2-yi-34b-200k-Q2_K.gguf) | Q2_K | 12.825 GB | smallest, significant quality loss - not recommended for most purposes |
+| [dolphin-2.2-yi-34b-200k-Q3_K_S.gguf](https://huggingface.co/tensorblock/cognitivecomputations_dolphin-2.2-yi-34b-200k-GGUF/blob/main/dolphin-2.2-yi-34b-200k-Q3_K_S.gguf) | Q3_K_S | 14.960 GB | very small, high quality loss |
+| [dolphin-2.2-yi-34b-200k-Q3_K_M.gguf](https://huggingface.co/tensorblock/cognitivecomputations_dolphin-2.2-yi-34b-200k-GGUF/blob/main/dolphin-2.2-yi-34b-200k-Q3_K_M.gguf) | Q3_K_M | 16.655 GB | very small, high quality loss |
+| [dolphin-2.2-yi-34b-200k-Q3_K_L.gguf](https://huggingface.co/tensorblock/cognitivecomputations_dolphin-2.2-yi-34b-200k-GGUF/blob/main/dolphin-2.2-yi-34b-200k-Q3_K_L.gguf) | Q3_K_L | 18.139 GB | small, substantial quality loss |
+| [dolphin-2.2-yi-34b-200k-Q4_0.gguf](https://huggingface.co/tensorblock/cognitivecomputations_dolphin-2.2-yi-34b-200k-GGUF/blob/main/dolphin-2.2-yi-34b-200k-Q4_0.gguf) | Q4_0 | 19.467 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [dolphin-2.2-yi-34b-200k-Q4_K_S.gguf](https://huggingface.co/tensorblock/cognitivecomputations_dolphin-2.2-yi-34b-200k-GGUF/blob/main/dolphin-2.2-yi-34b-200k-Q4_K_S.gguf) | Q4_K_S | 19.599 GB | small, greater quality loss |
+| [dolphin-2.2-yi-34b-200k-Q4_K_M.gguf](https://huggingface.co/tensorblock/cognitivecomputations_dolphin-2.2-yi-34b-200k-GGUF/blob/main/dolphin-2.2-yi-34b-200k-Q4_K_M.gguf) | Q4_K_M | 20.659 GB | medium, balanced quality - recommended |
+| [dolphin-2.2-yi-34b-200k-Q5_0.gguf](https://huggingface.co/tensorblock/cognitivecomputations_dolphin-2.2-yi-34b-200k-GGUF/blob/main/dolphin-2.2-yi-34b-200k-Q5_0.gguf) | Q5_0 | 23.708 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [dolphin-2.2-yi-34b-200k-Q5_K_S.gguf](https://huggingface.co/tensorblock/cognitivecomputations_dolphin-2.2-yi-34b-200k-GGUF/blob/main/dolphin-2.2-yi-34b-200k-Q5_K_S.gguf) | Q5_K_S | 23.708 GB | large, low quality loss - recommended |
+| [dolphin-2.2-yi-34b-200k-Q5_K_M.gguf](https://huggingface.co/tensorblock/cognitivecomputations_dolphin-2.2-yi-34b-200k-GGUF/blob/main/dolphin-2.2-yi-34b-200k-Q5_K_M.gguf) | Q5_K_M | 24.322 GB | large, very low quality loss - recommended |
+| [dolphin-2.2-yi-34b-200k-Q6_K.gguf](https://huggingface.co/tensorblock/cognitivecomputations_dolphin-2.2-yi-34b-200k-GGUF/blob/main/dolphin-2.2-yi-34b-200k-Q6_K.gguf) | Q6_K | 28.214 GB | very large, extremely low quality loss |
+| [dolphin-2.2-yi-34b-200k-Q8_0.gguf](https://huggingface.co/tensorblock/cognitivecomputations_dolphin-2.2-yi-34b-200k-GGUF/blob/main/dolphin-2.2-yi-34b-200k-Q8_0.gguf) | Q8_0 | 36.542 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/cognitivecomputations_dolphin-2.2-yi-34b-200k-GGUF --include "dolphin-2.2-yi-34b-200k-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/cognitivecomputations_dolphin-2.2-yi-34b-200k-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

dolphin-2.2-yi-34b-200k-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c71841686476cda771174653045923e3e536c114fc6c876701bb31eb7aee8a95
+size 12825235072

dolphin-2.2-yi-34b-200k-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e1073f8dee500d3c5bd2e2d3f23c68e295e32633c39fe44e77ef7a9a3f10738
+size 18139446912

dolphin-2.2-yi-34b-200k-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88caf988854400521a33c9ca1547ea30ba7339eb501fa652d75838898a74fa4f
+size 16654925440

dolphin-2.2-yi-34b-200k-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:459d880cdd880c59ba02cdb0cca2ff89fd1a1335501fd3b2975950cf399f9cb7
+size 14960295552

dolphin-2.2-yi-34b-200k-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:303fedb533e61dfe6d8b7641b0675e5784a455e04539d81d99320e7d363c8d9b
+size 19466530432

dolphin-2.2-yi-34b-200k-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccebaf34f781216f76edecac09302bdc50fdcd909523960864ff02f4a6ba5e50
+size 20658712192

dolphin-2.2-yi-34b-200k-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d95534ae3f18cbb83f4a20c90df09b8e1a26ba29e21b8888308367014e6685e
+size 19598651008

dolphin-2.2-yi-34b-200k-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7b89404f1fc5919cd60ca2bfd588fd405298a9c2ce289b5e55a2df79a16f92d
+size 23707692672

dolphin-2.2-yi-34b-200k-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9b8e03eeb9ee202933b3c293d34f4f60510c8737b54380478c441507fe84824
+size 24321846912

dolphin-2.2-yi-34b-200k-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaa8d01234664f6dc64676472bde5051a7e5b2af0cccb92f81df65678f8196f7
+size 23707692672

dolphin-2.2-yi-34b-200k-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d35b90ecd25ccb58aae7bf5b41bbec00ccddfc2927ff62efd8e65169f4b6bf2a
+size 28213927552

dolphin-2.2-yi-34b-200k-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62f3b937a0f4e25d2ba5a43cdf08e1d68e90f4adf2e2940ea2f1a30d0fa74370
+size 36542283392