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
+Rombos-LLM-V2.6-Qwen-14b-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Rombos-LLM-V2.6-Qwen-14b-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Rombos-LLM-V2.6-Qwen-14b-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Rombos-LLM-V2.6-Qwen-14b-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Rombos-LLM-V2.6-Qwen-14b-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Rombos-LLM-V2.6-Qwen-14b-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Rombos-LLM-V2.6-Qwen-14b-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Rombos-LLM-V2.6-Qwen-14b-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Rombos-LLM-V2.6-Qwen-14b-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Rombos-LLM-V2.6-Qwen-14b-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Rombos-LLM-V2.6-Qwen-14b-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Rombos-LLM-V2.6-Qwen-14b-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,176 @@
+---
+license: apache-2.0
+library_name: transformers
+base_model: rombodawg/Rombos-LLM-V2.6-Qwen-14b
+tags:
+- TensorBlock
+- GGUF
+model-index:
+- name: Rombos-LLM-V2.6-Qwen-14b
+  results:
+  - 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: 52.14
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Rombos-LLM-V2.6-Qwen-14b
+      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: 49.22
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Rombos-LLM-V2.6-Qwen-14b
+      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: 28.85
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Rombos-LLM-V2.6-Qwen-14b
+      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: 17.0
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Rombos-LLM-V2.6-Qwen-14b
+      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: 19.26
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Rombos-LLM-V2.6-Qwen-14b
+      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: 48.85
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Rombos-LLM-V2.6-Qwen-14b
+      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>
+
+## rombodawg/Rombos-LLM-V2.6-Qwen-14b - GGUF
+
+This repo contains GGUF format model files for [rombodawg/Rombos-LLM-V2.6-Qwen-14b](https://huggingface.co/rombodawg/Rombos-LLM-V2.6-Qwen-14b).
+
+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
+
+```
+<|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 |
+| -------- | ---------- | --------- | ----------- |
+| [Rombos-LLM-V2.6-Qwen-14b-Q2_K.gguf](https://huggingface.co/tensorblock/Rombos-LLM-V2.6-Qwen-14b-GGUF/blob/main/Rombos-LLM-V2.6-Qwen-14b-Q2_K.gguf) | Q2_K | 5.374 GB | smallest, significant quality loss - not recommended for most purposes |
+| [Rombos-LLM-V2.6-Qwen-14b-Q3_K_S.gguf](https://huggingface.co/tensorblock/Rombos-LLM-V2.6-Qwen-14b-GGUF/blob/main/Rombos-LLM-V2.6-Qwen-14b-Q3_K_S.gguf) | Q3_K_S | 6.202 GB | very small, high quality loss |
+| [Rombos-LLM-V2.6-Qwen-14b-Q3_K_M.gguf](https://huggingface.co/tensorblock/Rombos-LLM-V2.6-Qwen-14b-GGUF/blob/main/Rombos-LLM-V2.6-Qwen-14b-Q3_K_M.gguf) | Q3_K_M | 6.835 GB | very small, high quality loss |
+| [Rombos-LLM-V2.6-Qwen-14b-Q3_K_L.gguf](https://huggingface.co/tensorblock/Rombos-LLM-V2.6-Qwen-14b-GGUF/blob/main/Rombos-LLM-V2.6-Qwen-14b-Q3_K_L.gguf) | Q3_K_L | 7.381 GB | small, substantial quality loss |
+| [Rombos-LLM-V2.6-Qwen-14b-Q4_0.gguf](https://huggingface.co/tensorblock/Rombos-LLM-V2.6-Qwen-14b-GGUF/blob/main/Rombos-LLM-V2.6-Qwen-14b-Q4_0.gguf) | Q4_0 | 7.933 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Rombos-LLM-V2.6-Qwen-14b-Q4_K_S.gguf](https://huggingface.co/tensorblock/Rombos-LLM-V2.6-Qwen-14b-GGUF/blob/main/Rombos-LLM-V2.6-Qwen-14b-Q4_K_S.gguf) | Q4_K_S | 7.985 GB | small, greater quality loss |
+| [Rombos-LLM-V2.6-Qwen-14b-Q4_K_M.gguf](https://huggingface.co/tensorblock/Rombos-LLM-V2.6-Qwen-14b-GGUF/blob/main/Rombos-LLM-V2.6-Qwen-14b-Q4_K_M.gguf) | Q4_K_M | 8.371 GB | medium, balanced quality - recommended |
+| [Rombos-LLM-V2.6-Qwen-14b-Q5_0.gguf](https://huggingface.co/tensorblock/Rombos-LLM-V2.6-Qwen-14b-GGUF/blob/main/Rombos-LLM-V2.6-Qwen-14b-Q5_0.gguf) | Q5_0 | 9.561 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Rombos-LLM-V2.6-Qwen-14b-Q5_K_S.gguf](https://huggingface.co/tensorblock/Rombos-LLM-V2.6-Qwen-14b-GGUF/blob/main/Rombos-LLM-V2.6-Qwen-14b-Q5_K_S.gguf) | Q5_K_S | 9.561 GB | large, low quality loss - recommended |
+| [Rombos-LLM-V2.6-Qwen-14b-Q5_K_M.gguf](https://huggingface.co/tensorblock/Rombos-LLM-V2.6-Qwen-14b-GGUF/blob/main/Rombos-LLM-V2.6-Qwen-14b-Q5_K_M.gguf) | Q5_K_M | 9.787 GB | large, very low quality loss - recommended |
+| [Rombos-LLM-V2.6-Qwen-14b-Q6_K.gguf](https://huggingface.co/tensorblock/Rombos-LLM-V2.6-Qwen-14b-GGUF/blob/main/Rombos-LLM-V2.6-Qwen-14b-Q6_K.gguf) | Q6_K | 11.292 GB | very large, extremely low quality loss |
+| [Rombos-LLM-V2.6-Qwen-14b-Q8_0.gguf](https://huggingface.co/tensorblock/Rombos-LLM-V2.6-Qwen-14b-GGUF/blob/main/Rombos-LLM-V2.6-Qwen-14b-Q8_0.gguf) | Q8_0 | 14.623 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/Rombos-LLM-V2.6-Qwen-14b-GGUF --include "Rombos-LLM-V2.6-Qwen-14b-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/Rombos-LLM-V2.6-Qwen-14b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

Rombos-LLM-V2.6-Qwen-14b-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d986616320106ca9e2398c33409f744e8d2dfa924dbc44e82ffad45a1c577508
+size 5770497664

Rombos-LLM-V2.6-Qwen-14b-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad20cc544d63d783cd43e8690f24a93bf56f55502d772415ef6fbfc2262c5293
+size 7924768384

Rombos-LLM-V2.6-Qwen-14b-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4808e2ec743b20ccb68cad1ba358d93248bb1f8b5eb8ebd0eef7f1e4668025f
+size 7339204224

Rombos-LLM-V2.6-Qwen-14b-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d43abf7e2b9b4fee7d4385e83603d99bae3141099444d5e8affe26d1aeeb5a2c
+size 6659595904

Rombos-LLM-V2.6-Qwen-14b-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b1dbb03623fd2c281ad57e860a158d7613a128b926f83e1cc23847b1266267f
+size 8517725824

Rombos-LLM-V2.6-Qwen-14b-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c103369f2b45068e561234d908991761a9690ed7557dc4f303866518a0d282ab
+size 8988110464

Rombos-LLM-V2.6-Qwen-14b-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ed0f37d9cf7c5de2eabaa8ed5d43a1e14062b61c625c9244aca770a9ad314db
+size 8573431424

Rombos-LLM-V2.6-Qwen-14b-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:288afc6f04bb603cedc3801f973da900362249fcbcec38d77a4024bcdc48d3a2
+size 10266553984

Rombos-LLM-V2.6-Qwen-14b-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b76f0130d04ede0b3d374815e655e04071c3b3fa2433cb66f92fbe96c850d5c8
+size 10508873344

Rombos-LLM-V2.6-Qwen-14b-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a21ea3f97f343ce9c9061264059ef0279b6ffbc47ca99111b70bfccc88d8d73f
+size 10266553984

Rombos-LLM-V2.6-Qwen-14b-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cbe2b900d13f457114dce3bc1f3efa88bc909b8d9ee77b0e3399f2f94dfd612
+size 12124683904

Rombos-LLM-V2.6-Qwen-14b-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abcf2d0236616cb68387f07f2001f48b0825cfae1eb60e6be7714cec37a40318
+size 15701597824