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
+tamil-llama-13b-instruct-v0.1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+tamil-llama-13b-instruct-v0.1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+tamil-llama-13b-instruct-v0.1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+tamil-llama-13b-instruct-v0.1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+tamil-llama-13b-instruct-v0.1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+tamil-llama-13b-instruct-v0.1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+tamil-llama-13b-instruct-v0.1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+tamil-llama-13b-instruct-v0.1-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+tamil-llama-13b-instruct-v0.1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+tamil-llama-13b-instruct-v0.1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+tamil-llama-13b-instruct-v0.1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+tamil-llama-13b-instruct-v0.1-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,182 @@
+---
+language:
+- ta
+- en
+license: llama2
+tags:
+- TensorBlock
+- GGUF
+base_model: abhinand/tamil-llama-13b-instruct-v0.1
+model-index:
+- name: tamil-llama-13b-instruct-v0.1
+  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: 54.52
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhinand/tamil-llama-13b-instruct-v0.1
+      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: 79.35
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhinand/tamil-llama-13b-instruct-v0.1
+      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: 50.37
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhinand/tamil-llama-13b-instruct-v0.1
+      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: 41.22
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhinand/tamil-llama-13b-instruct-v0.1
+      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: 76.56
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhinand/tamil-llama-13b-instruct-v0.1
+      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: 7.51
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhinand/tamil-llama-13b-instruct-v0.1
+      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>
+
+## abhinand/tamil-llama-13b-instruct-v0.1 - GGUF
+
+This repo contains GGUF format model files for [abhinand/tamil-llama-13b-instruct-v0.1](https://huggingface.co/abhinand/tamil-llama-13b-instruct-v0.1).
+
+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
+
+```
+
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [tamil-llama-13b-instruct-v0.1-Q2_K.gguf](https://huggingface.co/tensorblock/tamil-llama-13b-instruct-v0.1-GGUF/blob/main/tamil-llama-13b-instruct-v0.1-Q2_K.gguf) | Q2_K | 4.949 GB | smallest, significant quality loss - not recommended for most purposes |
+| [tamil-llama-13b-instruct-v0.1-Q3_K_S.gguf](https://huggingface.co/tensorblock/tamil-llama-13b-instruct-v0.1-GGUF/blob/main/tamil-llama-13b-instruct-v0.1-Q3_K_S.gguf) | Q3_K_S | 5.762 GB | very small, high quality loss |
+| [tamil-llama-13b-instruct-v0.1-Q3_K_M.gguf](https://huggingface.co/tensorblock/tamil-llama-13b-instruct-v0.1-GGUF/blob/main/tamil-llama-13b-instruct-v0.1-Q3_K_M.gguf) | Q3_K_M | 6.441 GB | very small, high quality loss |
+| [tamil-llama-13b-instruct-v0.1-Q3_K_L.gguf](https://huggingface.co/tensorblock/tamil-llama-13b-instruct-v0.1-GGUF/blob/main/tamil-llama-13b-instruct-v0.1-Q3_K_L.gguf) | Q3_K_L | 7.032 GB | small, substantial quality loss |
+| [tamil-llama-13b-instruct-v0.1-Q4_0.gguf](https://huggingface.co/tensorblock/tamil-llama-13b-instruct-v0.1-GGUF/blob/main/tamil-llama-13b-instruct-v0.1-Q4_0.gguf) | Q4_0 | 7.479 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [tamil-llama-13b-instruct-v0.1-Q4_K_S.gguf](https://huggingface.co/tensorblock/tamil-llama-13b-instruct-v0.1-GGUF/blob/main/tamil-llama-13b-instruct-v0.1-Q4_K_S.gguf) | Q4_K_S | 7.537 GB | small, greater quality loss |
+| [tamil-llama-13b-instruct-v0.1-Q4_K_M.gguf](https://huggingface.co/tensorblock/tamil-llama-13b-instruct-v0.1-GGUF/blob/main/tamil-llama-13b-instruct-v0.1-Q4_K_M.gguf) | Q4_K_M | 7.980 GB | medium, balanced quality - recommended |
+| [tamil-llama-13b-instruct-v0.1-Q5_0.gguf](https://huggingface.co/tensorblock/tamil-llama-13b-instruct-v0.1-GGUF/blob/main/tamil-llama-13b-instruct-v0.1-Q5_0.gguf) | Q5_0 | 9.096 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [tamil-llama-13b-instruct-v0.1-Q5_K_S.gguf](https://huggingface.co/tensorblock/tamil-llama-13b-instruct-v0.1-GGUF/blob/main/tamil-llama-13b-instruct-v0.1-Q5_K_S.gguf) | Q5_K_S | 9.096 GB | large, low quality loss - recommended |
+| [tamil-llama-13b-instruct-v0.1-Q5_K_M.gguf](https://huggingface.co/tensorblock/tamil-llama-13b-instruct-v0.1-GGUF/blob/main/tamil-llama-13b-instruct-v0.1-Q5_K_M.gguf) | Q5_K_M | 9.354 GB | large, very low quality loss - recommended |
+| [tamil-llama-13b-instruct-v0.1-Q6_K.gguf](https://huggingface.co/tensorblock/tamil-llama-13b-instruct-v0.1-GGUF/blob/main/tamil-llama-13b-instruct-v0.1-Q6_K.gguf) | Q6_K | 10.814 GB | very large, extremely low quality loss |
+| [tamil-llama-13b-instruct-v0.1-Q8_0.gguf](https://huggingface.co/tensorblock/tamil-llama-13b-instruct-v0.1-GGUF/blob/main/tamil-llama-13b-instruct-v0.1-Q8_0.gguf) | Q8_0 | 14.006 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/tamil-llama-13b-instruct-v0.1-GGUF --include "tamil-llama-13b-instruct-v0.1-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/tamil-llama-13b-instruct-v0.1-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

tamil-llama-13b-instruct-v0.1-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e851547d939f8057002a200a1cd1efb30a4bdb54cdaa4fdeaf4577e1bffd234
+size 4948713792

tamil-llama-13b-instruct-v0.1-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13277b8f83eb1eab8ca91d2e3aac822120ff88ce6dcd680d0ac6be5e24618c69
+size 7032301024

tamil-llama-13b-instruct-v0.1-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bb2d275c8d0661077623f72a4eb14f39505b53f6aada613aa9e1e3023011ebf
+size 6440510944

tamil-llama-13b-instruct-v0.1-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10c65101f1917222bbc06e89b07d9bb47acaafa716e1a78e79803c981d0329f3
+size 5761721824

tamil-llama-13b-instruct-v0.1-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa36500c4e1e9d3ba60f2a3048a53e1a6ff794ec9dff8dacd8d5510e2361be18
+size 7479426976

tamil-llama-13b-instruct-v0.1-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7348ff31192cf4aba47d051dfb5dcf27f331f407f32bbd8e0ef16b0a97f7b52b
+size 7979548576

tamil-llama-13b-instruct-v0.1-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a84198303fdb859ea828fc3551f476801acb05f95dd02315b30f1590014e9e3c
+size 7536770976

tamil-llama-13b-instruct-v0.1-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31d953f769b1f9e33559048461d192ce90846beb0b2028100ae72fc7949adc68
+size 9096090656

tamil-llama-13b-instruct-v0.1-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2fc210bf89c4f7b53ec6f06daed295e65505e2e84910ace4172e30c88951422
+size 9353729056

tamil-llama-13b-instruct-v0.1-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4b2eba2496276fda6e31c70bd19fac33e617cbd98268feda84caccb6e41e42d
+size 9096090656

tamil-llama-13b-instruct-v0.1-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b0bbe73c3f0bc6d2f4cc83f9e6aad44deff3d0b5deab0f84cbf57b1c2ade0d1
+size 10813795840

tamil-llama-13b-instruct-v0.1-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a13e5fb582821f156502c2374d853ee5bd7c76c58d4fb6f88ade6ee3c1f5d9e7
+size 14005548352