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
+Yi-34B-200K-AEZAKMI-v2-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Yi-34B-200K-AEZAKMI-v2-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Yi-34B-200K-AEZAKMI-v2-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Yi-34B-200K-AEZAKMI-v2-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Yi-34B-200K-AEZAKMI-v2-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Yi-34B-200K-AEZAKMI-v2-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Yi-34B-200K-AEZAKMI-v2-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Yi-34B-200K-AEZAKMI-v2-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Yi-34B-200K-AEZAKMI-v2-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Yi-34B-200K-AEZAKMI-v2-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Yi-34B-200K-AEZAKMI-v2-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Yi-34B-200K-AEZAKMI-v2-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,282 @@
+---
+license: apache-2.0
+tags:
+- llm
+- fine-tune
+- yi
+- TensorBlock
+- GGUF
+datasets:
+- adamo1139/AEZAKMI_v2
+license_name: yi-license
+license_link: LICENSE
+base_model: adamo1139/Yi-34B-200K-AEZAKMI-v2
+model-index:
+- name: Yi-34B-200K-AEZAKMI-v2
+  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: 67.92
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=adamo1139/Yi-34B-200K-AEZAKMI-v2
+      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: 85.61
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=adamo1139/Yi-34B-200K-AEZAKMI-v2
+      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: 75.22
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=adamo1139/Yi-34B-200K-AEZAKMI-v2
+      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: 56.74
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=adamo1139/Yi-34B-200K-AEZAKMI-v2
+      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: 81.61
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=adamo1139/Yi-34B-200K-AEZAKMI-v2
+      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: 58.91
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=adamo1139/Yi-34B-200K-AEZAKMI-v2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 45.55
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=adamo1139/Yi-34B-200K-AEZAKMI-v2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 35.28
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=adamo1139/Yi-34B-200K-AEZAKMI-v2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 4.83
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=adamo1139/Yi-34B-200K-AEZAKMI-v2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 10.96
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=adamo1139/Yi-34B-200K-AEZAKMI-v2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 6.48
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=adamo1139/Yi-34B-200K-AEZAKMI-v2
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 39.03
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=adamo1139/Yi-34B-200K-AEZAKMI-v2
+      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>
+
+## adamo1139/Yi-34B-200K-AEZAKMI-v2 - GGUF
+
+This repo contains GGUF format model files for [adamo1139/Yi-34B-200K-AEZAKMI-v2](https://huggingface.co/adamo1139/Yi-34B-200K-AEZAKMI-v2).
+
+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
+
+```
+<|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 |
+| -------- | ---------- | --------- | ----------- |
+| [Yi-34B-200K-AEZAKMI-v2-Q2_K.gguf](https://huggingface.co/tensorblock/Yi-34B-200K-AEZAKMI-v2-GGUF/blob/main/Yi-34B-200K-AEZAKMI-v2-Q2_K.gguf) | Q2_K | 12.825 GB | smallest, significant quality loss - not recommended for most purposes |
+| [Yi-34B-200K-AEZAKMI-v2-Q3_K_S.gguf](https://huggingface.co/tensorblock/Yi-34B-200K-AEZAKMI-v2-GGUF/blob/main/Yi-34B-200K-AEZAKMI-v2-Q3_K_S.gguf) | Q3_K_S | 14.960 GB | very small, high quality loss |
+| [Yi-34B-200K-AEZAKMI-v2-Q3_K_M.gguf](https://huggingface.co/tensorblock/Yi-34B-200K-AEZAKMI-v2-GGUF/blob/main/Yi-34B-200K-AEZAKMI-v2-Q3_K_M.gguf) | Q3_K_M | 16.655 GB | very small, high quality loss |
+| [Yi-34B-200K-AEZAKMI-v2-Q3_K_L.gguf](https://huggingface.co/tensorblock/Yi-34B-200K-AEZAKMI-v2-GGUF/blob/main/Yi-34B-200K-AEZAKMI-v2-Q3_K_L.gguf) | Q3_K_L | 18.139 GB | small, substantial quality loss |
+| [Yi-34B-200K-AEZAKMI-v2-Q4_0.gguf](https://huggingface.co/tensorblock/Yi-34B-200K-AEZAKMI-v2-GGUF/blob/main/Yi-34B-200K-AEZAKMI-v2-Q4_0.gguf) | Q4_0 | 19.467 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Yi-34B-200K-AEZAKMI-v2-Q4_K_S.gguf](https://huggingface.co/tensorblock/Yi-34B-200K-AEZAKMI-v2-GGUF/blob/main/Yi-34B-200K-AEZAKMI-v2-Q4_K_S.gguf) | Q4_K_S | 19.599 GB | small, greater quality loss |
+| [Yi-34B-200K-AEZAKMI-v2-Q4_K_M.gguf](https://huggingface.co/tensorblock/Yi-34B-200K-AEZAKMI-v2-GGUF/blob/main/Yi-34B-200K-AEZAKMI-v2-Q4_K_M.gguf) | Q4_K_M | 20.659 GB | medium, balanced quality - recommended |
+| [Yi-34B-200K-AEZAKMI-v2-Q5_0.gguf](https://huggingface.co/tensorblock/Yi-34B-200K-AEZAKMI-v2-GGUF/blob/main/Yi-34B-200K-AEZAKMI-v2-Q5_0.gguf) | Q5_0 | 23.708 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Yi-34B-200K-AEZAKMI-v2-Q5_K_S.gguf](https://huggingface.co/tensorblock/Yi-34B-200K-AEZAKMI-v2-GGUF/blob/main/Yi-34B-200K-AEZAKMI-v2-Q5_K_S.gguf) | Q5_K_S | 23.708 GB | large, low quality loss - recommended |
+| [Yi-34B-200K-AEZAKMI-v2-Q5_K_M.gguf](https://huggingface.co/tensorblock/Yi-34B-200K-AEZAKMI-v2-GGUF/blob/main/Yi-34B-200K-AEZAKMI-v2-Q5_K_M.gguf) | Q5_K_M | 24.322 GB | large, very low quality loss - recommended |
+| [Yi-34B-200K-AEZAKMI-v2-Q6_K.gguf](https://huggingface.co/tensorblock/Yi-34B-200K-AEZAKMI-v2-GGUF/blob/main/Yi-34B-200K-AEZAKMI-v2-Q6_K.gguf) | Q6_K | 28.214 GB | very large, extremely low quality loss |
+| [Yi-34B-200K-AEZAKMI-v2-Q8_0.gguf](https://huggingface.co/tensorblock/Yi-34B-200K-AEZAKMI-v2-GGUF/blob/main/Yi-34B-200K-AEZAKMI-v2-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/Yi-34B-200K-AEZAKMI-v2-GGUF --include "Yi-34B-200K-AEZAKMI-v2-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/Yi-34B-200K-AEZAKMI-v2-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

Yi-34B-200K-AEZAKMI-v2-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:809068996e1541e3ce6a4c6063845687297e2758a0c0f9454ce927aab636272e
+size 12825234560

Yi-34B-200K-AEZAKMI-v2-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81eae9bf0a9a186f270de8292e80c686efbf6e62b3695090ca53d5c21a3ff5e5
+size 18139446400

Yi-34B-200K-AEZAKMI-v2-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ee41b410aa377c689edc37cf2a1b71dc467fc887c99f42a1355e791dc19eb69
+size 16654924928

Yi-34B-200K-AEZAKMI-v2-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87b7ee9c01cc8fce901cf7efe3d85ddd921f2deaddaa1b992eae842887cd44a1
+size 14960295040

Yi-34B-200K-AEZAKMI-v2-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:269772f2473dd0dca0e16dae3c8e9714cb4939f6df02b1231e4d1ed17974b554
+size 19466529920

Yi-34B-200K-AEZAKMI-v2-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3866751b65d28ec6ea2b5db0d8aba2b4f91324f058ab2b12bf8b581f807b9f6
+size 20658711680

Yi-34B-200K-AEZAKMI-v2-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6fcc39fdcf917aed5854caa5a6ed1e68fca1f697c543b4491cb4350ecea3235
+size 19598650496

Yi-34B-200K-AEZAKMI-v2-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4d4c43eef94bca68b6e9530f36145982aae5bb950b77db4521a12fcf850c690
+size 23707692160

Yi-34B-200K-AEZAKMI-v2-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a73d46531effa6ec9d6bdf01ac05651c24eaa5097205646931da2142aa3cd6b
+size 24321846400

Yi-34B-200K-AEZAKMI-v2-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db73140de60be1f4e48f5e27408551d5d4d8b545b0780cd877f3810ca17d44bb
+size 23707692160

Yi-34B-200K-AEZAKMI-v2-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:916429d4580c3e9cdc0e7d8b11a93f0c5c0bb4588e4edf8c67266dbb4eaa802b
+size 28213927040

Yi-34B-200K-AEZAKMI-v2-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:479bafa8d7d52fec14397d8e800da134e19de04d3a4b059db3064597be3484d9
+size 36542282880