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-6B-Infinity-Chat-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Yi-6B-Infinity-Chat-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Yi-6B-Infinity-Chat-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Yi-6B-Infinity-Chat-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Yi-6B-Infinity-Chat-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Yi-6B-Infinity-Chat-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Yi-6B-Infinity-Chat-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Yi-6B-Infinity-Chat-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Yi-6B-Infinity-Chat-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Yi-6B-Infinity-Chat-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Yi-6B-Infinity-Chat-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Yi-6B-Infinity-Chat-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,178 @@
+---
+license: cc
+base_model: Walmart-the-bag/Yi-6B-Infinity-Chat
+inference: false
+tags:
+- TensorBlock
+- GGUF
+model-index:
+- name: Yi-6B-Infinity-Chat
+  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: 56.57
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Walmart-the-bag/Yi-6B-Infinity-Chat
+      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: 77.66
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Walmart-the-bag/Yi-6B-Infinity-Chat
+      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: 64.05
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Walmart-the-bag/Yi-6B-Infinity-Chat
+      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: 50.75
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Walmart-the-bag/Yi-6B-Infinity-Chat
+      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: 73.95
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Walmart-the-bag/Yi-6B-Infinity-Chat
+      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: 36.01
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Walmart-the-bag/Yi-6B-Infinity-Chat
+      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>
+
+## Walmart-the-bag/Yi-6B-Infinity-Chat - GGUF
+
+This repo contains GGUF format model files for [Walmart-the-bag/Yi-6B-Infinity-Chat](https://huggingface.co/Walmart-the-bag/Yi-6B-Infinity-Chat).
+
+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
+
+```
+<|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-6B-Infinity-Chat-Q2_K.gguf](https://huggingface.co/tensorblock/Yi-6B-Infinity-Chat-GGUF/tree/main/Yi-6B-Infinity-Chat-Q2_K.gguf) | Q2_K | 2.177 GB | smallest, significant quality loss - not recommended for most purposes |
+| [Yi-6B-Infinity-Chat-Q3_K_S.gguf](https://huggingface.co/tensorblock/Yi-6B-Infinity-Chat-GGUF/tree/main/Yi-6B-Infinity-Chat-Q3_K_S.gguf) | Q3_K_S | 2.523 GB | very small, high quality loss |
+| [Yi-6B-Infinity-Chat-Q3_K_M.gguf](https://huggingface.co/tensorblock/Yi-6B-Infinity-Chat-GGUF/tree/main/Yi-6B-Infinity-Chat-Q3_K_M.gguf) | Q3_K_M | 2.788 GB | very small, high quality loss |
+| [Yi-6B-Infinity-Chat-Q3_K_L.gguf](https://huggingface.co/tensorblock/Yi-6B-Infinity-Chat-GGUF/tree/main/Yi-6B-Infinity-Chat-Q3_K_L.gguf) | Q3_K_L | 3.015 GB | small, substantial quality loss |
+| [Yi-6B-Infinity-Chat-Q4_0.gguf](https://huggingface.co/tensorblock/Yi-6B-Infinity-Chat-GGUF/tree/main/Yi-6B-Infinity-Chat-Q4_0.gguf) | Q4_0 | 3.241 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Yi-6B-Infinity-Chat-Q4_K_S.gguf](https://huggingface.co/tensorblock/Yi-6B-Infinity-Chat-GGUF/tree/main/Yi-6B-Infinity-Chat-Q4_K_S.gguf) | Q4_K_S | 3.263 GB | small, greater quality loss |
+| [Yi-6B-Infinity-Chat-Q4_K_M.gguf](https://huggingface.co/tensorblock/Yi-6B-Infinity-Chat-GGUF/tree/main/Yi-6B-Infinity-Chat-Q4_K_M.gguf) | Q4_K_M | 3.422 GB | medium, balanced quality - recommended |
+| [Yi-6B-Infinity-Chat-Q5_0.gguf](https://huggingface.co/tensorblock/Yi-6B-Infinity-Chat-GGUF/tree/main/Yi-6B-Infinity-Chat-Q5_0.gguf) | Q5_0 | 3.916 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Yi-6B-Infinity-Chat-Q5_K_S.gguf](https://huggingface.co/tensorblock/Yi-6B-Infinity-Chat-GGUF/tree/main/Yi-6B-Infinity-Chat-Q5_K_S.gguf) | Q5_K_S | 3.916 GB | large, low quality loss - recommended |
+| [Yi-6B-Infinity-Chat-Q5_K_M.gguf](https://huggingface.co/tensorblock/Yi-6B-Infinity-Chat-GGUF/tree/main/Yi-6B-Infinity-Chat-Q5_K_M.gguf) | Q5_K_M | 4.009 GB | large, very low quality loss - recommended |
+| [Yi-6B-Infinity-Chat-Q6_K.gguf](https://huggingface.co/tensorblock/Yi-6B-Infinity-Chat-GGUF/tree/main/Yi-6B-Infinity-Chat-Q6_K.gguf) | Q6_K | 4.633 GB | very large, extremely low quality loss |
+| [Yi-6B-Infinity-Chat-Q8_0.gguf](https://huggingface.co/tensorblock/Yi-6B-Infinity-Chat-GGUF/tree/main/Yi-6B-Infinity-Chat-Q8_0.gguf) | Q8_0 | 6.000 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-6B-Infinity-Chat-GGUF --include "Yi-6B-Infinity-Chat-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-6B-Infinity-Chat-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

Yi-6B-Infinity-Chat-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d071f14141a4a649027f802a2571e4b3ef527d078148bbe7f631d0a204d8352
+size 2337369920

Yi-6B-Infinity-Chat-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2183edaddeb070cdbbc6e550e11fe0b612ccc21bbf10517fa6c85dd29e89f6b
+size 3237222208

Yi-6B-Infinity-Chat-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51fe5fae2a93d4c98044464393bb68233b1afb8f0b71a4eb48b12c0f90eb2fa8
+size 2993166144

Yi-6B-Infinity-Chat-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f795f5991476507eba08afe92c0cd4551913c006c7955f6bd63983fe4385fd9
+size 2709526336

Yi-6B-Infinity-Chat-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8850aba291b9259de10379b77969ab8b6efcad0037097ba7df173d6d90b5c35
+size 3479691072

Yi-6B-Infinity-Chat-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6921f633511fc03d935d1004d08026cb5488e2a863fa26259e214e4d1a359af
+size 3674332992

Yi-6B-Infinity-Chat-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea024c24396b46940e59e4337d4b6f60f23d0ffec4cbae354718b4ae0948d778
+size 3503284032

Yi-6B-Infinity-Chat-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c40944dd50b48158b55745f970ab8e08112e847e3ff5f4645eef4fc62b6dbff1
+size 4204552000

Yi-6B-Infinity-Chat-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16ec2c6b50cbdff754c5d07f15b539abc0cf0d0818dc8d560fb385394b5e780a
+size 4304822080

Yi-6B-Infinity-Chat-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cde286fde8acd4ae81afde0b386b8e09e4592274840d3876de0d9c3c5241959d
+size 4204552000

Yi-6B-Infinity-Chat-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f347f5dc451646eb842fe807e9c36f22f5bf8589e874b56645b52604a7546311
+size 4974716736

Yi-6B-Infinity-Chat-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cf6a121be32868dbfd30bcb5d6377417d21fe0a1a49ddb000b8b81999561062
+size 6442686272