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

README.md

@@ -0,0 +1,173 @@
+---
+license: apache-2.0
+tags:
+- TensorBlock
+- GGUF
+base_model: kevin009/llamaRAGdrama
+model-index:
+- name: llamaRAGdrama
+  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: 72.01
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kevin009/llamaRAGdrama
+      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: 88.83
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kevin009/llamaRAGdrama
+      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: 64.5
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kevin009/llamaRAGdrama
+      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: 70.24
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kevin009/llamaRAGdrama
+      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: 86.66
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kevin009/llamaRAGdrama
+      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: 65.66
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kevin009/llamaRAGdrama
+      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>
+
+## kevin009/llamaRAGdrama - GGUF
+
+This repo contains GGUF format model files for [kevin009/llamaRAGdrama](https://huggingface.co/kevin009/llamaRAGdrama).
+
+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 |
+| -------- | ---------- | --------- | ----------- |
+| [llamaRAGdrama-Q2_K.gguf](https://huggingface.co/tensorblock/llamaRAGdrama-GGUF/tree/main/llamaRAGdrama-Q2_K.gguf) | Q2_K | 2.532 GB | smallest, significant quality loss - not recommended for most purposes |
+| [llamaRAGdrama-Q3_K_S.gguf](https://huggingface.co/tensorblock/llamaRAGdrama-GGUF/tree/main/llamaRAGdrama-Q3_K_S.gguf) | Q3_K_S | 2.947 GB | very small, high quality loss |
+| [llamaRAGdrama-Q3_K_M.gguf](https://huggingface.co/tensorblock/llamaRAGdrama-GGUF/tree/main/llamaRAGdrama-Q3_K_M.gguf) | Q3_K_M | 3.277 GB | very small, high quality loss |
+| [llamaRAGdrama-Q3_K_L.gguf](https://huggingface.co/tensorblock/llamaRAGdrama-GGUF/tree/main/llamaRAGdrama-Q3_K_L.gguf) | Q3_K_L | 3.560 GB | small, substantial quality loss |
+| [llamaRAGdrama-Q4_0.gguf](https://huggingface.co/tensorblock/llamaRAGdrama-GGUF/tree/main/llamaRAGdrama-Q4_0.gguf) | Q4_0 | 3.827 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [llamaRAGdrama-Q4_K_S.gguf](https://huggingface.co/tensorblock/llamaRAGdrama-GGUF/tree/main/llamaRAGdrama-Q4_K_S.gguf) | Q4_K_S | 3.856 GB | small, greater quality loss |
+| [llamaRAGdrama-Q4_K_M.gguf](https://huggingface.co/tensorblock/llamaRAGdrama-GGUF/tree/main/llamaRAGdrama-Q4_K_M.gguf) | Q4_K_M | 4.068 GB | medium, balanced quality - recommended |
+| [llamaRAGdrama-Q5_0.gguf](https://huggingface.co/tensorblock/llamaRAGdrama-GGUF/tree/main/llamaRAGdrama-Q5_0.gguf) | Q5_0 | 4.654 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [llamaRAGdrama-Q5_K_S.gguf](https://huggingface.co/tensorblock/llamaRAGdrama-GGUF/tree/main/llamaRAGdrama-Q5_K_S.gguf) | Q5_K_S | 4.654 GB | large, low quality loss - recommended |
+| [llamaRAGdrama-Q5_K_M.gguf](https://huggingface.co/tensorblock/llamaRAGdrama-GGUF/tree/main/llamaRAGdrama-Q5_K_M.gguf) | Q5_K_M | 4.779 GB | large, very low quality loss - recommended |
+| [llamaRAGdrama-Q6_K.gguf](https://huggingface.co/tensorblock/llamaRAGdrama-GGUF/tree/main/llamaRAGdrama-Q6_K.gguf) | Q6_K | 5.534 GB | very large, extremely low quality loss |
+| [llamaRAGdrama-Q8_0.gguf](https://huggingface.co/tensorblock/llamaRAGdrama-GGUF/tree/main/llamaRAGdrama-Q8_0.gguf) | Q8_0 | 7.167 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/llamaRAGdrama-GGUF --include "llamaRAGdrama-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/llamaRAGdrama-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

llamaRAGdrama-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:589d649e570c30ef68274933b519a9b5be79ebefc4cb2132ffefcd8030a50870
+size 2719242144

llamaRAGdrama-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2c9ac0def8b7b6c378f9d306a0fc20716004bf07b0ebb87c56179c325fa9159
+size 3822024608

llamaRAGdrama-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29b6f2421316d15c8c6224087b5842290ac79c5b9a29f975987baeb79da9e8ff
+size 3518986144

llamaRAGdrama-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ef25b29d08c3a00253e042de04349f2e6c59cb9252456f362d59063eae17157
+size 3164567456

llamaRAGdrama-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21e68a3964f8182cd8d5ff12e67ffc337a3f10ba15a3d335dd2e54bf35282872
+size 4108916640

llamaRAGdrama-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f32a381a6cd2e013a0a7428b161d228b85b383200f009f76a521b99daaf9fee
+size 4368439200

llamaRAGdrama-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fc13ce6f9aab3a09655ad7939f00a8093005fa35824ff15c1c2a3796ebb22e4
+size 4140373920

llamaRAGdrama-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51bd8ed16d403e4f005c5e693d21a74246297486a30478239fdd066e861f03be
+size 4997715872

llamaRAGdrama-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b9110d92062a493857a4fc16790f68341cf32822b1f1db569b164882b6b3c86
+size 5131409312

llamaRAGdrama-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:826fd78804e97eb15c6de832faabf57ff7ec9894d03ed727d744607dc19e09a6
+size 4997715872

llamaRAGdrama-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fa915fe253af186c0a601921a193eb98b91fffe6fce02e13bf718f3f11c7f79
+size 5942065056

llamaRAGdrama-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6002e234855b36053d7dbf99a151ee134a42f2a63b14a5ad812176d86e0396c
+size 7695857568