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
+Puma-3B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Puma-3B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Puma-3B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Puma-3B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Puma-3B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Puma-3B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Puma-3B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Puma-3B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Puma-3B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Puma-3B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Puma-3B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Puma-3B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

Puma-3B-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3ca34f364ed4358992eefe5d32e806c99af94c607cea0f1c7c340ce3e398f13
+size 1979924640

Puma-3B-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcf908a861f554c56448790ffa819ade78617ca7f188c7a8b63715654dafa3b4
+size 2214548640

Puma-3B-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c5ed56a84d96b1104f27035cf6607813dbbdbf05c9f8529e66a1a40aa2258f9
+size 2139348640

Puma-3B-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca31248976aec8fe16da8dbb4faae783da941b3c5790d17211f1f2554d7dede4
+size 1979924640

Puma-3B-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:848a83c377f79afa62c88e84a5f83e1302b07fabed220ad4020c6847499fb1b7
+size 1979924640

Puma-3B-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2de757b968f9769f579d225004d08dcc2cda1a6f7466b61be0bc9cd5f371f89
+size 2580116640

Puma-3B-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6adff33921f4745b76cd78995ded836a4dfee79681f67b69b0b8cdc3d462cb7d
+size 2403156640

Puma-3B-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ade36505c0c886d470d53fe507a5169a0476958ba24a539d332383c3c9fec2bc
+size 2395412640

Puma-3B-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07ad949f98cad9ef8b418c3ba54aae0819ed923a676b47b8af4212c6c693c8e2
+size 2757076640

Puma-3B-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88a54c7dd6e93731bc214641eb27c6c8eaee33e1c1117b097210047c21a471fa
+size 2603156640

Puma-3B-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7fcd9d40336c84cb1ba06b38c1bbc118d3414417e096702de9a36ba16f8b5a8
+size 3641876640

Puma-3B-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6198b1828b298e8ccf4a61129e1ddf69763f33e89240ced72a5efa57a3cbfbf4
+size 3641876640

README.md

@@ -0,0 +1,185 @@
+---
+language:
+- en
+license: apache-2.0
+library_name: transformers
+datasets:
+- totally-not-an-llm/sharegpt-hyperfiltered-3k
+pipeline_tag: text-generation
+base_model: acrastt/Puma-3B
+tags:
+- TensorBlock
+- GGUF
+model-index:
+- name: Puma-3B
+  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: 41.3
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Puma-3B
+      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: 71.85
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Puma-3B
+      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: 27.51
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Puma-3B
+      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: 38.34
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Puma-3B
+      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: 66.38
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Puma-3B
+      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: 0.76
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Puma-3B
+      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>
+
+## acrastt/Puma-3B - GGUF
+
+This repo contains GGUF format model files for [acrastt/Puma-3B](https://huggingface.co/acrastt/Puma-3B).
+
+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).
+
+<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 |
+| -------- | ---------- | --------- | ----------- |
+| [Puma-3B-Q2_K.gguf](https://huggingface.co/tensorblock/Puma-3B-GGUF/blob/main/Puma-3B-Q2_K.gguf) | Q2_K | 1.844 GB | smallest, significant quality loss - not recommended for most purposes |
+| [Puma-3B-Q3_K_S.gguf](https://huggingface.co/tensorblock/Puma-3B-GGUF/blob/main/Puma-3B-Q3_K_S.gguf) | Q3_K_S | 1.844 GB | very small, high quality loss |
+| [Puma-3B-Q3_K_M.gguf](https://huggingface.co/tensorblock/Puma-3B-GGUF/blob/main/Puma-3B-Q3_K_M.gguf) | Q3_K_M | 1.992 GB | very small, high quality loss |
+| [Puma-3B-Q3_K_L.gguf](https://huggingface.co/tensorblock/Puma-3B-GGUF/blob/main/Puma-3B-Q3_K_L.gguf) | Q3_K_L | 2.062 GB | small, substantial quality loss |
+| [Puma-3B-Q4_0.gguf](https://huggingface.co/tensorblock/Puma-3B-GGUF/blob/main/Puma-3B-Q4_0.gguf) | Q4_0 | 1.844 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Puma-3B-Q4_K_S.gguf](https://huggingface.co/tensorblock/Puma-3B-GGUF/blob/main/Puma-3B-Q4_K_S.gguf) | Q4_K_S | 2.238 GB | small, greater quality loss |
+| [Puma-3B-Q4_K_M.gguf](https://huggingface.co/tensorblock/Puma-3B-GGUF/blob/main/Puma-3B-Q4_K_M.gguf) | Q4_K_M | 2.403 GB | medium, balanced quality - recommended |
+| [Puma-3B-Q5_0.gguf](https://huggingface.co/tensorblock/Puma-3B-GGUF/blob/main/Puma-3B-Q5_0.gguf) | Q5_0 | 2.231 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Puma-3B-Q5_K_S.gguf](https://huggingface.co/tensorblock/Puma-3B-GGUF/blob/main/Puma-3B-Q5_K_S.gguf) | Q5_K_S | 2.424 GB | large, low quality loss - recommended |
+| [Puma-3B-Q5_K_M.gguf](https://huggingface.co/tensorblock/Puma-3B-GGUF/blob/main/Puma-3B-Q5_K_M.gguf) | Q5_K_M | 2.568 GB | large, very low quality loss - recommended |
+| [Puma-3B-Q6_K.gguf](https://huggingface.co/tensorblock/Puma-3B-GGUF/blob/main/Puma-3B-Q6_K.gguf) | Q6_K | 3.392 GB | very large, extremely low quality loss |
+| [Puma-3B-Q8_0.gguf](https://huggingface.co/tensorblock/Puma-3B-GGUF/blob/main/Puma-3B-Q8_0.gguf) | Q8_0 | 3.392 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/Puma-3B-GGUF --include "Puma-3B-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/Puma-3B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```