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
+magnum-v4-9b-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+magnum-v4-9b-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+magnum-v4-9b-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+magnum-v4-9b-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+magnum-v4-9b-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+magnum-v4-9b-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+magnum-v4-9b-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+magnum-v4-9b-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+magnum-v4-9b-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+magnum-v4-9b-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+magnum-v4-9b-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+magnum-v4-9b-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,180 @@
+---
+language:
+- en
+license: gemma
+library_name: transformers
+tags:
+- chat
+- TensorBlock
+- GGUF
+pipeline_tag: text-generation
+base_model: anthracite-org/magnum-v4-9b
+model-index:
+- name: magnum-v4-9b
+  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: 35.03
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=anthracite-org/magnum-v4-9b
+      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: 33.27
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=anthracite-org/magnum-v4-9b
+      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: 11.63
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=anthracite-org/magnum-v4-9b
+      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: 12.98
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=anthracite-org/magnum-v4-9b
+      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: 15.65
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=anthracite-org/magnum-v4-9b
+      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: 32.81
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=anthracite-org/magnum-v4-9b
+      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>
+
+## anthracite-org/magnum-v4-9b - GGUF
+
+This repo contains GGUF format model files for [anthracite-org/magnum-v4-9b](https://huggingface.co/anthracite-org/magnum-v4-9b).
+
+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 |
+| -------- | ---------- | --------- | ----------- |
+| [magnum-v4-9b-Q2_K.gguf](https://huggingface.co/tensorblock/magnum-v4-9b-GGUF/blob/main/magnum-v4-9b-Q2_K.gguf) | Q2_K | 3.805 GB | smallest, significant quality loss - not recommended for most purposes |
+| [magnum-v4-9b-Q3_K_S.gguf](https://huggingface.co/tensorblock/magnum-v4-9b-GGUF/blob/main/magnum-v4-9b-Q3_K_S.gguf) | Q3_K_S | 4.338 GB | very small, high quality loss |
+| [magnum-v4-9b-Q3_K_M.gguf](https://huggingface.co/tensorblock/magnum-v4-9b-GGUF/blob/main/magnum-v4-9b-Q3_K_M.gguf) | Q3_K_M | 4.762 GB | very small, high quality loss |
+| [magnum-v4-9b-Q3_K_L.gguf](https://huggingface.co/tensorblock/magnum-v4-9b-GGUF/blob/main/magnum-v4-9b-Q3_K_L.gguf) | Q3_K_L | 5.132 GB | small, substantial quality loss |
+| [magnum-v4-9b-Q4_0.gguf](https://huggingface.co/tensorblock/magnum-v4-9b-GGUF/blob/main/magnum-v4-9b-Q4_0.gguf) | Q4_0 | 5.443 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [magnum-v4-9b-Q4_K_S.gguf](https://huggingface.co/tensorblock/magnum-v4-9b-GGUF/blob/main/magnum-v4-9b-Q4_K_S.gguf) | Q4_K_S | 5.479 GB | small, greater quality loss |
+| [magnum-v4-9b-Q4_K_M.gguf](https://huggingface.co/tensorblock/magnum-v4-9b-GGUF/blob/main/magnum-v4-9b-Q4_K_M.gguf) | Q4_K_M | 5.761 GB | medium, balanced quality - recommended |
+| [magnum-v4-9b-Q5_0.gguf](https://huggingface.co/tensorblock/magnum-v4-9b-GGUF/blob/main/magnum-v4-9b-Q5_0.gguf) | Q5_0 | 6.484 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [magnum-v4-9b-Q5_K_S.gguf](https://huggingface.co/tensorblock/magnum-v4-9b-GGUF/blob/main/magnum-v4-9b-Q5_K_S.gguf) | Q5_K_S | 6.484 GB | large, low quality loss - recommended |
+| [magnum-v4-9b-Q5_K_M.gguf](https://huggingface.co/tensorblock/magnum-v4-9b-GGUF/blob/main/magnum-v4-9b-Q5_K_M.gguf) | Q5_K_M | 6.647 GB | large, very low quality loss - recommended |
+| [magnum-v4-9b-Q6_K.gguf](https://huggingface.co/tensorblock/magnum-v4-9b-GGUF/blob/main/magnum-v4-9b-Q6_K.gguf) | Q6_K | 7.589 GB | very large, extremely low quality loss |
+| [magnum-v4-9b-Q8_0.gguf](https://huggingface.co/tensorblock/magnum-v4-9b-GGUF/blob/main/magnum-v4-9b-Q8_0.gguf) | Q8_0 | 9.827 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/magnum-v4-9b-GGUF --include "magnum-v4-9b-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/magnum-v4-9b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

magnum-v4-9b-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecd104923c2e1758133c9e5075ed75df2f09b244aab5764771c38e23e3aad59f
+size 3805397696

magnum-v4-9b-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76ed54861991527a81ac0471b6d6586c7a4b3a958538630f9645a1531817e78d
+size 5132452544

magnum-v4-9b-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9d93f0b9210095058daa69a956070964c551fa609c4f8536ce0c44e06cbb6e0
+size 4761780928

magnum-v4-9b-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72de43a78324a870d107675e92163b22491c13e2b005832b174599d4faab3052
+size 4337664704

magnum-v4-9b-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1302bb01e8cd202cb7419cd04ce38bf49c58395905cb2eb871a7dc42f32f8050
+size 5443142336

magnum-v4-9b-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f160c77a0a4dfe46425a03b7b5ead43ae95eaa1358c0dda76f90b83769cee5a
+size 5761057472

magnum-v4-9b-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:006f46e8f3041e049fd61630194aeb6a28f78aee809f4315456f08056f74787b
+size 5478924992

magnum-v4-9b-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9103bdb7e998b678e6b49560cb78a92f40cb802423c74c3645659b9e48af923f
+size 6483591872

magnum-v4-9b-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0be8f917d96e71a990f6f5a0cd76e040ae72341bcaf01aa91f66d78a69d3d1b8
+size 6647366336

magnum-v4-9b-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d6769ae726b765374ac3ae6676abb22e294fa2cf932bcb0012066418dea3d23
+size 6483591872

magnum-v4-9b-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c17fa17479ffad8e9a3bcbf14767ca46f7070f724e92684b4e4cafcca39d796
+size 7589069504

magnum-v4-9b-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acd3cd01ab1615d1aa05af6276bacfeca3dc8f11b63c578a86c4c152f0cfcdc1
+size 9827148480