初始化项目，由ModelHub XC社区提供模型

Model: Mungert/Llama-3.1-Nemotron-Nano-8B-v1-GGUF Source: Original Platform
2026-07-08 13:06:06 +08:00
commit 8591a74fb1
36 changed files with 783 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,81 @@
 *.7z filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
 *.bin.* filter=lfs diff=lfs merge=lfs -text
 *.bz2 filter=lfs diff=lfs merge=lfs -text
 *.ftz filter=lfs diff=lfs merge=lfs -text
 *.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
 *.joblib filter=lfs diff=lfs merge=lfs -text
 *.lfs.* filter=lfs diff=lfs merge=lfs -text
 *.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
 *.parquet filter=lfs diff=lfs merge=lfs -text
 *.pb filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
 *.rar filter=lfs diff=lfs merge=lfs -text
 saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text
 *.xz filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *.tfevents* filter=lfs diff=lfs merge=lfs -text
 *.db* filter=lfs diff=lfs merge=lfs -text
 *.ark* filter=lfs diff=lfs merge=lfs -text
 **/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
 **/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
 **/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
 *.safetensors filter=lfs diff=lfs merge=lfs -text
 *.ckpt filter=lfs diff=lfs merge=lfs -text
 *.ggml filter=lfs diff=lfs merge=lfs -text
 *.llamafile* filter=lfs diff=lfs merge=lfs -text
 *.pt2 filter=lfs diff=lfs merge=lfs -text
 *.mlmodel filter=lfs diff=lfs merge=lfs -text
 *.npy filter=lfs diff=lfs merge=lfs -text
 *.npz filter=lfs diff=lfs merge=lfs -text
 *.pickle filter=lfs diff=lfs merge=lfs -text
 *.pkl filter=lfs diff=lfs merge=lfs -text
 *.tar filter=lfs diff=lfs merge=lfs -text
 *.wasm filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 Llama-3.1-Nemotron-Nano-8B-v1-q2_k_s.gguf filter=lfs diff=lfs merge=lfs -text
 Llama-3.1-Nemotron-Nano-8B-v1-bf16-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
 Llama-3.1-Nemotron-Nano-8B-v1-f16-q4_k.gguf filter=lfs diff=lfs merge=lfs -text
 Llama-3.1-Nemotron-Nano-8B-v1-f16-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
 Llama-3.1-Nemotron-Nano-8B-v1-bf16-q4_k.gguf filter=lfs diff=lfs merge=lfs -text
 Llama-3.1-Nemotron-Nano-8B-v1-iq3_xxs.gguf filter=lfs diff=lfs merge=lfs -text
 Llama-3.1-Nemotron-Nano-8B-v1-f16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text
 Llama-3.1-Nemotron-Nano-8B-v1-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
 Llama-3.1-Nemotron-Nano-8B-v1-iq2_xxs.gguf filter=lfs diff=lfs merge=lfs -text
 Llama-3.1-Nemotron-Nano-8B-v1-iq2_xs.gguf filter=lfs diff=lfs merge=lfs -text
 Llama-3.1-Nemotron-Nano-8B-v1-f16-q6_k.gguf filter=lfs diff=lfs merge=lfs -text
 Llama-3.1-Nemotron-Nano-8B-v1-bf16-q6_k.gguf filter=lfs diff=lfs merge=lfs -text
 Llama-3.1-Nemotron-Nano-8B-v1-q4_0.gguf filter=lfs diff=lfs merge=lfs -text
 Llama-3.1-Nemotron-Nano-8B-v1-iq2_s.gguf filter=lfs diff=lfs merge=lfs -text
 Llama-3.1-Nemotron-Nano-8B-v1-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text
 Llama-3.1-Nemotron-Nano-8B-v1-iq3_xs.gguf filter=lfs diff=lfs merge=lfs -text
 Llama-3.1-Nemotron-Nano-8B-v1-iq2_m.gguf filter=lfs diff=lfs merge=lfs -text
 Llama-3.1-Nemotron-Nano-8B-v1-iq4_nl.gguf filter=lfs diff=lfs merge=lfs -text
 Llama-3.1-Nemotron-Nano-8B-v1-q5_0.gguf filter=lfs diff=lfs merge=lfs -text
 Llama-3.1-Nemotron-Nano-8B-v1-bf16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text
 Llama-3.1-Nemotron-Nano-8B-v1-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
 Llama-3.1-Nemotron-Nano-8B-v1-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
 Llama-3.1-Nemotron-Nano-8B-v1-iq3_s.gguf filter=lfs diff=lfs merge=lfs -text
 Llama-3.1-Nemotron-Nano-8B-v1-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text
 Llama-3.1-Nemotron-Nano-8B-v1-bf16.gguf filter=lfs diff=lfs merge=lfs -text
 Llama-3.1-Nemotron-Nano-8B-v1-iq4_xs.gguf filter=lfs diff=lfs merge=lfs -text
 Llama-3.1-Nemotron-Nano-8B-v1-q4_1.gguf filter=lfs diff=lfs merge=lfs -text
 Llama-3.1-Nemotron-Nano-8B-v1-q5_1.gguf filter=lfs diff=lfs merge=lfs -text
 Llama-3.1-Nemotron-Nano-8B-v1.imatrix filter=lfs diff=lfs merge=lfs -text
 Llama-3.1-Nemotron-Nano-8B-v1-q6_k_m.gguf filter=lfs diff=lfs merge=lfs -text
 Llama-3.1-Nemotron-Nano-8B-v1-iq3_m.gguf filter=lfs diff=lfs merge=lfs -text
 Llama-3.1-Nemotron-Nano-8B-v1-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
 Llama-3.1-Nemotron-Nano-8B-v1-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text
--- a/Llama-3.1-Nemotron-Nano-8B-v1-bf16-q4_k.gguf
+++ b/Llama-3.1-Nemotron-Nano-8B-v1-bf16-q4_k.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:e1c20655ad6d28779312bd2bd91035e88e2c88915f6b9a47cb8efef3d5d17582
 size 6295641248
--- a/Llama-3.1-Nemotron-Nano-8B-v1-bf16-q6_k.gguf
+++ b/Llama-3.1-Nemotron-Nano-8B-v1-bf16-q6_k.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:7fbf8fe0c07739e2fd8863beb7647d0c301d6ddd57ba911ef2e1c9540e150bf9
 size 7835475104
--- a/Llama-3.1-Nemotron-Nano-8B-v1-bf16-q8_0.gguf
+++ b/Llama-3.1-Nemotron-Nano-8B-v1-bf16-q8_0.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:1bf65738e793818acc07ee123f19273f1533db529fa050e18cc780022915c96d
 size 9525779328
--- a/Llama-3.1-Nemotron-Nano-8B-v1-bf16.gguf
+++ b/Llama-3.1-Nemotron-Nano-8B-v1-bf16.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:599bb573982a1657f28ff433431f389f0dfb31bcbafc251e25018465fa12ceb2
 size 16068893664
--- a/Llama-3.1-Nemotron-Nano-8B-v1-bf16_q8_0.gguf
+++ b/Llama-3.1-Nemotron-Nano-8B-v1-bf16_q8_0.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:ed76f1a92146bbfd90f7cfeb8cec2c3ded286b9ece3895788ee934aa6c9893dc
 size 9525779424
--- a/Llama-3.1-Nemotron-Nano-8B-v1-f16-q4_k.gguf
+++ b/Llama-3.1-Nemotron-Nano-8B-v1-f16-q4_k.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:114de6f054dbe60c49e80873658f7c1ed9fcf5b112dae09200dd24e00f7a4b33
 size 6295641248
--- a/Llama-3.1-Nemotron-Nano-8B-v1-f16-q6_k.gguf
+++ b/Llama-3.1-Nemotron-Nano-8B-v1-f16-q6_k.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:70d065fab2adfbee86364ca61e1daca81488e1b1b4470a2759e207f094345cac
 size 7835475104
--- a/Llama-3.1-Nemotron-Nano-8B-v1-f16-q8_0.gguf
+++ b/Llama-3.1-Nemotron-Nano-8B-v1-f16-q8_0.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:d63bb5f82fd19831fdc53bcb42883bf45de09d7bb917e508d5da03a8215bfb26
 size 9525779328
--- a/Llama-3.1-Nemotron-Nano-8B-v1-f16_q8_0.gguf
+++ b/Llama-3.1-Nemotron-Nano-8B-v1-f16_q8_0.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:823a343ddd33882624d07862f4d1ef740140f4c3d5208198c87c87ed4cd7604b
 size 9525779424
--- a/Llama-3.1-Nemotron-Nano-8B-v1-iq2_m.gguf
+++ b/Llama-3.1-Nemotron-Nano-8B-v1-iq2_m.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:e996f88ed6fe77288292454ed07859aad1c572e107a61a188f426d38327e2281
 size 3358973216
--- a/Llama-3.1-Nemotron-Nano-8B-v1-iq2_s.gguf
+++ b/Llama-3.1-Nemotron-Nano-8B-v1-iq2_s.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:9f42f618d3d9031836facafb532776700324ea1e301a98a2cdc04fb9623dc034
 size 3220561184
--- a/Llama-3.1-Nemotron-Nano-8B-v1-iq2_xs.gguf
+++ b/Llama-3.1-Nemotron-Nano-8B-v1-iq2_xs.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:9e068011244c1aa57c1ffac326b101c41c980f3772f623cb3cbc89b6abd0a59a
 size 2888162592
--- a/Llama-3.1-Nemotron-Nano-8B-v1-iq2_xxs.gguf
+++ b/Llama-3.1-Nemotron-Nano-8B-v1-iq2_xxs.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:ebb16115789ea5dbf2be9bcf40689272bc2293e2adf58c31793d4e3b36c92369
 size 2732973344
--- a/Llama-3.1-Nemotron-Nano-8B-v1-iq3_m.gguf
+++ b/Llama-3.1-Nemotron-Nano-8B-v1-iq3_m.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:5ade15d2b88bfcfe775ec9ce73589bf6a9af3b8975692d292aef7f6d6c4cab9b
 size 3850493216
--- a/Llama-3.1-Nemotron-Nano-8B-v1-iq3_s.gguf
+++ b/Llama-3.1-Nemotron-Nano-8B-v1-iq3_s.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:3d923f9ac3ee9f1920da968968f718f03ad550a1e6652b9b414109e5a87ffe2c
 size 3747994912
--- a/Llama-3.1-Nemotron-Nano-8B-v1-iq3_xs.gguf
+++ b/Llama-3.1-Nemotron-Nano-8B-v1-iq3_xs.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:e665d7520654758c4d46645a3a8c37504a8b6c76db9d7eecfaa19c58b0a7adcf
 size 3584417056
--- a/Llama-3.1-Nemotron-Nano-8B-v1-iq3_xxs.gguf
+++ b/Llama-3.1-Nemotron-Nano-8B-v1-iq3_xxs.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:dad3c8dc94c983d4f93079ca78403e7a10b2d4c1d9af276c6c95879c11aa429a
 size 3410353440
--- a/Llama-3.1-Nemotron-Nano-8B-v1-iq4_nl.gguf
+++ b/Llama-3.1-Nemotron-Nano-8B-v1-iq4_nl.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:ffa7ada7f4da906bc9de1f4766017d1e6dc9e8659054497f8f744062b649a220
 size 4677991712
--- a/Llama-3.1-Nemotron-Nano-8B-v1-iq4_xs.gguf
+++ b/Llama-3.1-Nemotron-Nano-8B-v1-iq4_xs.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:673a9b805cc9fe707e8163699ba0f2db573cfae614e63ce8ffda0f4d3fbfdf25
 size 4447665440
--- a/Llama-3.1-Nemotron-Nano-8B-v1-q2_k_s.gguf
+++ b/Llama-3.1-Nemotron-Nano-8B-v1-q2_k_s.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:314d0d6913badeb4bd2447f17c79c603282be84c71a5db9f1d6543e770193623
 size 3107839264
--- a/Llama-3.1-Nemotron-Nano-8B-v1-q3_k_m.gguf
+++ b/Llama-3.1-Nemotron-Nano-8B-v1-q3_k_m.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:5aeeea949375497484613905c24a81400ea634422a8d9f23d213cdf495a535b9
 size 4224130336
--- a/Llama-3.1-Nemotron-Nano-8B-v1-q3_k_s.gguf
+++ b/Llama-3.1-Nemotron-Nano-8B-v1-q3_k_s.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:68fe1661233ebd423770a6140b055b048c72d1fef67fbbd18220ad54eb9aff1a
 size 3730169120
--- a/Llama-3.1-Nemotron-Nano-8B-v1-q4_0.gguf
+++ b/Llama-3.1-Nemotron-Nano-8B-v1-q4_0.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:9c4771f5c28f259f9e1ebb447f40ce4db7126eb02d61104182d7a16d3eb9b35d
 size 4525776160
--- a/Llama-3.1-Nemotron-Nano-8B-v1-q4_1.gguf
+++ b/Llama-3.1-Nemotron-Nano-8B-v1-q4_1.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:f99b25c691f6287ccd3d70ef2efbd7f062d6bcaee52b7a2467698c88f8c5102d
 size 5027650848
--- a/Llama-3.1-Nemotron-Nano-8B-v1-q4_k_m.gguf
+++ b/Llama-3.1-Nemotron-Nano-8B-v1-q4_k_m.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:5555f073a8f58ee54774db072f7129fe9da7e6867a06814ac78551654d01ad81
 size 5056175392
--- a/Llama-3.1-Nemotron-Nano-8B-v1-q4_k_s.gguf
+++ b/Llama-3.1-Nemotron-Nano-8B-v1-q4_k_s.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:ad60df70185f32a3460817327baaa27adfb2847f25df0dac0392fb67980a11ba
 size 4828110112
--- a/Llama-3.1-Nemotron-Nano-8B-v1-q5_0.gguf
+++ b/Llama-3.1-Nemotron-Nano-8B-v1-q5_0.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:8c639632c025f6033260d772dda008931d94acea01fc66528a0beadc233828b7
 size 5529525536
--- a/Llama-3.1-Nemotron-Nano-8B-v1-q5_1.gguf
+++ b/Llama-3.1-Nemotron-Nano-8B-v1-q5_1.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:6cf9621426385735d66c403a0e3d1ec53c77824476a9f3b94c1cf133dbac0bf2
 size 6031400224
--- a/Llama-3.1-Nemotron-Nano-8B-v1-q5_k_m.gguf
+++ b/Llama-3.1-Nemotron-Nano-8B-v1-q5_k_m.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:7736ab5855ddbe8766d3047818f03b9bd2e5fd5ab7a32ff28f0471169d8c3d41
 size 5802761504
--- a/Llama-3.1-Nemotron-Nano-8B-v1-q5_k_s.gguf
+++ b/Llama-3.1-Nemotron-Nano-8B-v1-q5_k_s.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:547c0fe73fdaf5337f3734f80175cbd073007809788caca383c773189d0df84b
 size 5669068064
--- a/Llama-3.1-Nemotron-Nano-8B-v1-q6_k_m.gguf
+++ b/Llama-3.1-Nemotron-Nano-8B-v1-q6_k_m.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:32b99567aedbe0cb5074de14dd7e8c8c22ed7d5b9a9d8fd57ae4d20c51160edb
 size 6596009248
--- a/Llama-3.1-Nemotron-Nano-8B-v1-q8_0.gguf
+++ b/Llama-3.1-Nemotron-Nano-8B-v1-q8_0.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:38652b4a903feae5dfa1377f3e649b3db481e4a19167c80b4ffe61326919dca8
 size 8540773344
--- a/Llama-3.1-Nemotron-Nano-8B-v1.imatrix
+++ b/Llama-3.1-Nemotron-Nano-8B-v1.imatrix
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:061ce35c5f3b25134ca895abebc82bfa370242ee997824b0f02d495ce36cf9fe
 size 4988170
--- a/README.md
+++ b/README.md
@@ -0,0 +1,602 @@
 ---
 library_name: transformers
 license: other
 license_name: nvidia-open-model-license
 license_link: >-
  https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/
 pipeline_tag: text-generation
 language:
  - en
 tags:
  - nvidia
  - llama-3
  - pytorch
 ---
 # <span style="color: #7FFF7F;">Llama-3.1-Nemotron-Nano-8B-v1 GGUF Models</span>
 ## <span style="color: #7F7FFF;">Model Generation Details</span>
 This model was generated using [llama.cpp](https://github.com/ggerganov/llama.cpp) at commit [`19e899c`](https://github.com/ggerganov/llama.cpp/commit/19e899ce21a7c9ffcf8bb2b22269a75f6e078f8f).
 ## <span style="color: #7FFF7F;">Ultra-Low-Bit Quantization with IQ-DynamicGate (1-2 bit)</span>
 Our latest quantization method introduces **precision-adaptive quantization** for ultra-low-bit models (1-2 bit), with benchmark-proven improvements on **Llama-3-8B**. This approach uses layer-specific strategies to preserve accuracy while maintaining extreme memory efficiency.
 ### **Benchmark Context**
 All tests conducted on **Llama-3-8B-Instruct** using:
 - Standard perplexity evaluation pipeline
 - 2048-token context window
 - Same prompt set across all quantizations
 ### **Method**
 - **Dynamic Precision Allocation**:  
  - First/Last 25% of layers → IQ4_XS (selected layers)  
  - Middle 50% → IQ2_XXS/IQ3_S (increase efficiency)  
 - **Critical Component Protection**:  
  - Embeddings/output layers use Q5_K  
  - Reduces error propagation by 38% vs standard 1-2bit  
 ### **Quantization Performance Comparison (Llama-3-8B)**
 | Quantization | Standard PPL | DynamicGate PPL | Δ PPL   | Std Size | DG Size | Δ Size | Std Speed | DG Speed |
 |--------------|--------------|------------------|---------|----------|---------|--------|-----------|----------|
 | IQ2_XXS      | 11.30        | 9.84             | -12.9%  | 2.5G     | 2.6G    | +0.1G  | 234s      | 246s     |
 | IQ2_XS       | 11.72        | 11.63            | -0.8%   | 2.7G     | 2.8G    | +0.1G  | 242s      | 246s     |
 | IQ2_S        | 14.31        | 9.02             | -36.9%  | 2.7G     | 2.9G    | +0.2G  | 238s      | 244s     |
 | IQ1_M        | 27.46        | 15.41            | -43.9%  | 2.2G     | 2.5G    | +0.3G  | 206s      | 212s     |
 | IQ1_S        | 53.07        | 32.00            | -39.7%  | 2.1G     | 2.4G    | +0.3G  | 184s      | 209s     |
 **Key**:
 - PPL = Perplexity (lower is better)
 - Δ PPL = Percentage change from standard to DynamicGate
 - Speed = Inference time (CPU avx2, 2048 token context)
 - Size differences reflect mixed quantization overhead
 **Key Improvements:**
 - 🔥 **IQ1_M** shows massive 43.9% perplexity reduction (27.46 → 15.41)
 - 🚀 **IQ2_S** cuts perplexity by 36.9% while adding only 0.2GB
 - ⚡ **IQ1_S** maintains 39.7% better accuracy despite 1-bit quantization
 **Tradeoffs:**
 - All variants have modest size increases (0.1-0.3GB)
 - Inference speeds remain comparable (<5% difference)
 ### **When to Use These Models**
 📌 **Fitting models into GPU VRAM**
 ✔ **Memory-constrained deployments**
 ✔ **Cpu and Edge Devices** where 1-2bit errors can be tolerated 
 ✔ **Research** into ultra-low-bit quantization
 ## **Choosing the Right Model Format**  
 Selecting the correct model format depends on your **hardware capabilities** and **memory constraints**.  
 ### **BF16 (Brain Float 16) – Use if BF16 acceleration is available**  
 - A 16-bit floating-point format designed for **faster computation** while retaining good precision.  
 - Provides **similar dynamic range** as FP32 but with **lower memory usage**.  
 - Recommended if your hardware supports **BF16 acceleration** (check your device's specs).  
 - Ideal for **high-performance inference** with **reduced memory footprint** compared to FP32.  
 📌 **Use BF16 if:**  
 ✔ Your hardware has native **BF16 support** (e.g., newer GPUs, TPUs).  
 ✔ You want **higher precision** while saving memory.  
 ✔ You plan to **requantize** the model into another format.  
 📌 **Avoid BF16 if:**  
 ❌ Your hardware does **not** support BF16 (it may fall back to FP32 and run slower).  
 ❌ You need compatibility with older devices that lack BF16 optimization.  
 ---
 ### **F16 (Float 16) – More widely supported than BF16**  
 - A 16-bit floating-point **high precision** but with less of range of values than BF16. 
 - Works on most devices with **FP16 acceleration support** (including many GPUs and some CPUs).  
 - Slightly lower numerical precision than BF16 but generally sufficient for inference.  
 📌 **Use F16 if:**  
 ✔ Your hardware supports **FP16** but **not BF16**.  
 ✔ You need a **balance between speed, memory usage, and accuracy**.  
 ✔ You are running on a **GPU** or another device optimized for FP16 computations.  
 📌 **Avoid F16 if:**  
 ❌ Your device lacks **native FP16 support** (it may run slower than expected).  
 ❌ You have memory limitations.  
 ---
 ### **Quantized Models (Q4_K, Q6_K, Q8, etc.) – For CPU & Low-VRAM Inference**  
 Quantization reduces model size and memory usage while maintaining as much accuracy as possible.  
 - **Lower-bit models (Q4_K)** → **Best for minimal memory usage**, may have lower precision.  
 - **Higher-bit models (Q6_K, Q8_0)** → **Better accuracy**, requires more memory.  
 📌 **Use Quantized Models if:**  
 ✔ You are running inference on a **CPU** and need an optimized model.  
 ✔ Your device has **low VRAM** and cannot load full-precision models.  
 ✔ You want to reduce **memory footprint** while keeping reasonable accuracy.  
 📌 **Avoid Quantized Models if:**  
 ❌ You need **maximum accuracy** (full-precision models are better for this).  
 ❌ Your hardware has enough VRAM for higher-precision formats (BF16/F16).  
 ---
 ### **Very Low-Bit Quantization (IQ3_XS, IQ3_S, IQ3_M, Q4_K, Q4_0)**  
 These models are optimized for **extreme memory efficiency**, making them ideal for **low-power devices** or **large-scale deployments** where memory is a critical constraint.  
 - **IQ3_XS**: Ultra-low-bit quantization (3-bit) with **extreme memory efficiency**.  
  - **Use case**: Best for **ultra-low-memory devices** where even Q4_K is too large.  
  - **Trade-off**: Lower accuracy compared to higher-bit quantizations.  
 - **IQ3_S**: Small block size for **maximum memory efficiency**.  
  - **Use case**: Best for **low-memory devices** where **IQ3_XS** is too aggressive.  
 - **IQ3_M**: Medium block size for better accuracy than **IQ3_S**.  
  - **Use case**: Suitable for **low-memory devices** where **IQ3_S** is too limiting.  
 - **Q4_K**: 4-bit quantization with **block-wise optimization** for better accuracy.  
  - **Use case**: Best for **low-memory devices** where **Q6_K** is too large.  
 - **Q4_0**: Pure 4-bit quantization, optimized for **ARM devices**.  
  - **Use case**: Best for **ARM-based devices** or **low-memory environments**.  
 ---
 ### **Summary Table: Model Format Selection**  
 | Model Format  | Precision  | Memory Usage  | Device Requirements  | Best Use Case  |  
 |--------------|------------|---------------|----------------------|---------------|  
 | **BF16**     | Highest    | High          | BF16-supported GPU/CPUs  | High-speed inference with reduced memory |  
 | **F16**      | High       | High          | FP16-supported devices | GPU inference when BF16 isn't available |  
 | **Q4_K**     | Medium Low | Low           | CPU or Low-VRAM devices | Best for memory-constrained environments |  
 | **Q6_K**     | Medium     | Moderate      | CPU with more memory | Better accuracy while still being quantized |  
 | **Q8_0**     | High       | Moderate      | CPU or GPU with enough VRAM | Best accuracy among quantized models |  
 | **IQ3_XS**   | Very Low   | Very Low      | Ultra-low-memory devices | Extreme memory efficiency and low accuracy |  
 | **Q4_0**     | Low        | Low           | ARM or low-memory devices | llama.cpp can optimize for ARM devices |  
 ---
 ## **Included Files & Details**  
 ### `Llama-3.1-Nemotron-Nano-8B-v1-bf16.gguf`  
 - Model weights preserved in **BF16**.  
 - Use this if you want to **requantize** the model into a different format.  
 - Best if your device supports **BF16 acceleration**.  
 ### `Llama-3.1-Nemotron-Nano-8B-v1-f16.gguf`  
 - Model weights stored in **F16**.  
 - Use if your device supports **FP16**, especially if BF16 is not available.  
 ### `Llama-3.1-Nemotron-Nano-8B-v1-bf16-q8_0.gguf`  
 - **Output & embeddings** remain in **BF16**.  
 - All other layers quantized to **Q8_0**.  
 - Use if your device supports **BF16** and you want a quantized version.  
 ### `Llama-3.1-Nemotron-Nano-8B-v1-f16-q8_0.gguf`  
 - **Output & embeddings** remain in **F16**.  
 - All other layers quantized to **Q8_0**.    
 ### `Llama-3.1-Nemotron-Nano-8B-v1-q4_k.gguf`  
 - **Output & embeddings** quantized to **Q8_0**.  
 - All other layers quantized to **Q4_K**.  
 - Good for **CPU inference** with limited memory.  
 ### `Llama-3.1-Nemotron-Nano-8B-v1-q4_k_s.gguf`  
 - Smallest **Q4_K** variant, using less memory at the cost of accuracy.  
 - Best for **very low-memory setups**.  
 ### `Llama-3.1-Nemotron-Nano-8B-v1-q6_k.gguf`  
 - **Output & embeddings** quantized to **Q8_0**.  
 - All other layers quantized to **Q6_K** .  
 ### `Llama-3.1-Nemotron-Nano-8B-v1-q8_0.gguf`  
 - Fully **Q8** quantized model for better accuracy.  
 - Requires **more memory** but offers higher precision.  
 ### `Llama-3.1-Nemotron-Nano-8B-v1-iq3_xs.gguf`  
 - **IQ3_XS** quantization, optimized for **extreme memory efficiency**.  
 - Best for **ultra-low-memory devices**.  
 ### `Llama-3.1-Nemotron-Nano-8B-v1-iq3_m.gguf`  
 - **IQ3_M** quantization, offering a **medium block size** for better accuracy.  
 - Suitable for **low-memory devices**.  
 ### `Llama-3.1-Nemotron-Nano-8B-v1-q4_0.gguf`  
 - Pure **Q4_0** quantization, optimized for **ARM devices**.  
 - Best for **low-memory environments**.
 - Prefer IQ4_NL for better accuracy.
 # <span id="testllm" style="color: #7F7FFF;">🚀 If you find these models useful</span>
 ❤ **Please click "Like" if you find this useful!**  
 Help me test my **AI-Powered Network Monitor Assistant** with **quantum-ready security checks**:  
 👉 [Quantum Network Monitor](https://readyforquantum.com/dashboard/?assistant=open&utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme)  
 💬 **How to test**:  
 Choose an **AI assistant type**:  
   - `TurboLLM` (GPT-4o-mini)  
   - `HugLLM` (Hugginface Open-source)  
   - `TestLLM` (Experimental CPU-only)  
 ### **What I’m Testing**  
 I’m pushing the limits of **small open-source models for AI network monitoring**, specifically:  
 - **Function calling** against live network services  
 - **How small can a model go** while still handling:  
  - Automated **Nmap scans**  
  - **Quantum-readiness checks**  
  - **Network Monitoring tasks**  
 🟡 **TestLLM** – Current experimental model (llama.cpp on 2 CPU threads):  
 - ✅ **Zero-configuration setup**  
 - ⏳ 30s load time (slow inference but **no API costs**)  
 - 🔧 **Help wanted!** If you’re into **edge-device AI**, let’s collaborate!  
 ### **Other Assistants**  
 🟢 **TurboLLM** – Uses **gpt-4o-mini** for: 
 - **Create custom cmd processors to run .net code on Quantum Network Monitor Agents**
 - **Real-time network diagnostics and monitoring**
 - **Security Audits**
 - **Penetration testing** (Nmap/Metasploit)  
 🔵 **HugLLM** – Latest Open-source models:  
 - 🌐 Runs on Hugging Face Inference API  
 ### 💡 **Example commands to you could test**:  
 1. `"Give me info on my websites SSL certificate"`  
 2. `"Check if my server is using quantum safe encyption for communication"`  
 3. `"Run a comprehensive security audit on my server"`
 4. '"Create a cmd processor to .. (what ever you want)" Note you need to install a Quantum Network Monitor Agent to run the .net code from. This is a very flexible and powerful feature. Use with caution!
 ### Final Word
 I fund the servers used to create these model files, run the Quantum Network Monitor service, and pay for inference from Novita and OpenAI—all out of my own pocket. All the code behind the model creation and the Quantum Network Monitor project is [open source](https://github.com/Mungert69). Feel free to use whatever you find helpful.
 If you appreciate the work, please consider [buying me a coffee](https://www.buymeacoffee.com/mahadeva) ☕. Your support helps cover service costs and allows me to raise token limits for everyone.
 I'm also open to job opportunities or sponsorship.
 Thank you! 😊
 # Llama-3.1-Nemotron-Nano-8B-v1
 ## Model Overview 
 Llama-3.1-Nemotron-Nano-8B-v1 is a large language model (LLM) which is a derivative of [Meta Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) (AKA the reference model). It is a reasoning model that is post trained for reasoning, human chat preferences, and tasks, such as RAG and tool calling. 
 Llama-3.1-Nemotron-Nano-8B-v1 is a model which offers a great tradeoff between model accuracy and efficiency. It is created from Llama 3.1 8B Instruct and offers improvements in model accuracy. The model fits on a single RTX GPU and can be used locally. The model supports a context length of 128K.
 This model underwent a multi-phase post-training process to enhance both its reasoning and non-reasoning capabilities. This includes a supervised fine-tuning stage for Math, Code, Reasoning, and Tool Calling as well as multiple reinforcement learning (RL) stages using REINFORCE (RLOO) and Online Reward-aware Preference Optimization (RPO) algorithms for both chat and instruction-following. The final model checkpoint is obtained after merging the final SFT and Online RPO checkpoints. Improved using Qwen.
 This model is part of the Llama Nemotron Collection. You can find the other model(s) in this family here: 
 [Llama-3.3-Nemotron-Super-49B-v1](https://huggingface.co/nvidia/Llama-3.3-Nemotron-Super-49B-v1)
 This model is ready for commercial use.
 ## License/Terms of Use
 GOVERNING TERMS: Your use of this model is governed by the [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/). Additional Information: [Llama 3.1 Community License Agreement](https://www.llama.com/llama3_1/license/). Built with Llama.
 **Model Developer:** NVIDIA
 **Model Dates:** Trained between August 2024 and March 2025
 **Data Freshness:** The pretraining data has a cutoff of 2023 per Meta Llama 3.1 8B
 ## Use Case: 
 Developers designing AI Agent systems, chatbots, RAG systems, and other AI-powered applications. Also suitable for typical instruction-following tasks. Balance of model accuracy and compute efficiency (the model fits on a single RTX GPU and can be used locally).
 ## Release Date: <br>
 3/18/2025 <br>
 ## References
 - [\[2505.00949\] Llama-Nemotron: Efficient Reasoning Models](https://arxiv.org/abs/2505.00949)
 - [\[2502.00203\] Reward-aware Preference Optimization: A Unified Mathematical Framework for Model Alignment](https://arxiv.org/abs/2502.00203)
 ## Model Architecture
 **Architecture Type:** Dense decoder-only Transformer model
 **Network Architecture:** Llama 3.1 8B Instruct
 ## Intended use
 Llama-3.1-Nemotron-Nano-8B-v1 is a general purpose reasoning and chat model intended to be used in English and coding languages. Other non-English languages (German, French, Italian, Portuguese, Hindi, Spanish, and Thai) are also supported. 
 # Input:
 - **Input Type:** Text
 - **Input Format:** String
 - **Input Parameters:** One-Dimensional (1D)
 - **Other Properties Related to Input:** Context length up to 131,072 tokens
 ## Output:
 - **Output Type:** Text
 - **Output Format:** String
 - **Output Parameters:** One-Dimensional (1D)
 - **Other Properties Related to Output:** Context length up to 131,072 tokens
 ## Model Version:
 1.0 (3/18/2025)
 ## Software Integration
 - **Runtime Engine:** NeMo 24.12 <br>
 - **Recommended Hardware Microarchitecture Compatibility:**
    - NVIDIA Hopper
    - NVIDIA Ampere
 ## Quick Start and Usage Recommendations:
 1. Reasoning mode (ON/OFF) is controlled via the system prompt, which must be set as shown in the example below. All instructions should be contained within the user prompt
 2. We recommend setting temperature to `0.6`, and Top P to `0.95` for Reasoning ON mode
 3. We recommend using greedy decoding for Reasoning OFF mode
 4. We have provided a list of prompts to use for evaluation for each benchmark where a specific template is required
 5. The model will include `<think></think>` if no reasoning was necessary in Reasoning ON model, this is expected behaviour
 You can try this model out through the preview API, using this link: [Llama-3.1-Nemotron-Nano-8B-v1](https://build.nvidia.com/nvidia/llama-3_1-nemotron-nano-8b-v1).
 See the snippet below for usage with Hugging Face Transformers library. Reasoning mode (ON/OFF) is controlled via system prompt. Please see the example below.
 Our code requires the transformers package version to be `4.44.2` or higher.
 ### Example of “Reasoning On:”
 ```python
 import torch
 import transformers
 model_id = "nvidia/Llama-3.1-Nemotron-Nano-8B-v1"
 model_kwargs = {"torch_dtype": torch.bfloat16, "device_map": "auto"}
 tokenizer = transformers.AutoTokenizer.from_pretrained(model_id)
 tokenizer.pad_token_id = tokenizer.eos_token_id
 pipeline = transformers.pipeline(
   "text-generation",
   model=model_id,
   tokenizer=tokenizer,
   max_new_tokens=32768,
   temperature=0.6,
   top_p=0.95,
   **model_kwargs
 )
 # Thinking can be "on" or "off"
 thinking = "on"
 print(pipeline([{"role": "system", "content": f"detailed thinking {thinking}"}, {"role": "user", "content": "Solve x*(sin(x)+2)=0"}]))
 ```
 ### Example of “Reasoning Off:”
 ```python
 import torch
 import transformers
 model_id = "nvidia/Llama-3.1-Nemotron-Nano-8B-v1"
 model_kwargs = {"torch_dtype": torch.bfloat16, "device_map": "auto"}
 tokenizer = transformers.AutoTokenizer.from_pretrained(model_id)
 tokenizer.pad_token_id = tokenizer.eos_token_id
 pipeline = transformers.pipeline(
   "text-generation",
   model=model_id,
   tokenizer=tokenizer,
   max_new_tokens=32768,
   do_sample=False,
   **model_kwargs
 )
 # Thinking can be "on" or "off"
 thinking = "off"
 print(pipeline([{"role": "system", "content": f"detailed thinking {thinking}"}, {"role": "user", "content": "Solve x*(sin(x)+2)=0"}]))
 ```
 For some prompts, even though thinking is disabled, the model emergently prefers to think before responding. But if desired, the users can prevent it by pre-filling the assistant response.
 ```python
 import torch
 import transformers
 model_id = "nvidia/Llama-3.1-Nemotron-Nano-8B-v1"
 model_kwargs = {"torch_dtype": torch.bfloat16, "device_map": "auto"}
 tokenizer = transformers.AutoTokenizer.from_pretrained(model_id)
 tokenizer.pad_token_id = tokenizer.eos_token_id
 # Thinking can be "on" or "off"
 thinking = "off"
 pipeline = transformers.pipeline(
   "text-generation",
   model=model_id,
   tokenizer=tokenizer,
   max_new_tokens=32768,
   do_sample=False,
   **model_kwargs
 )
 print(pipeline([{"role": "system", "content": f"detailed thinking {thinking}"}, {"role": "user", "content": "Solve x*(sin(x)+2)=0"}, {"role":"assistant", "content":"<think>\n</think>"}]))
 ```
 ## Inference:
 **Engine:** Transformers
 **Test Hardware:**
 - BF16:
    - 1x RTX 50 Series GPUs
    - 1x RTX 40 Series GPUs
    - 1x RTX 30 Series GPUs
    - 1x H100-80GB GPU
    - 1x A100-80GB GPU
 **Preferred/Supported] Operating System(s):** Linux <br>
 ## Training Datasets
 A large variety of training data was used for the post-training pipeline, including manually annotated data and synthetic data.
 The data for the multi-stage post-training phases for improvements in Code, Math, and Reasoning is a compilation of SFT and RL data that supports improvements of math, code, general reasoning, and instruction following capabilities of the original Llama instruct model. 
 Prompts have been sourced from either public and open corpus or synthetically generated. Responses were synthetically generated by a variety of models, with some prompts containing responses for both Reasoning On and Off modes, to train the model to distinguish between two modes. 
 **Data Collection for Training Datasets:** <br>
 * Hybrid: Automated, Human, Synthetic <br>
 **Data Labeling for Training Datasets:** <br>
 * N/A <br>
 ## Evaluation Datasets
 We used the datasets listed below to evaluate Llama-3.1-Nemotron-Nano-8B-v1. 
 **Data Collection for Evaluation Datasets:** Hybrid: Human/Synthetic
 **Data Labeling for Evaluation Datasets:** Hybrid: Human/Synthetic/Automatic
 ## Evaluation Results
 These results contain both “Reasoning On”, and “Reasoning Off”. We recommend using temperature=`0.6`, top_p=`0.95` for “Reasoning On” mode, and greedy decoding for “Reasoning Off” mode. All evaluations are done with 32k sequence length. We run the benchmarks up to 16 times and average the scores to be more accurate.
 > NOTE: Where applicable, a Prompt Template will be provided. While completing benchmarks, please ensure that you are parsing for the correct output format as per the provided prompt in order to reproduce the benchmarks seen below. 
 ### MT-Bench
 | Reasoning Mode | Score |
 |--------------|------------|
 | Reasoning Off | 7.9 |
 | Reasoning On | 8.1 |
 ### MATH500
 | Reasoning Mode | pass@1 |
 |--------------|------------|
 | Reasoning Off | 36.6% | 
 | Reasoning On | 95.4%  |
 User Prompt Template: 
 ```
 "Below is a math question. I want you to reason through the steps and then give a final answer. Your final answer should be in \boxed{}.\nQuestion: {question}"
 ```
 ### AIME25
 | Reasoning Mode | pass@1 |
 |--------------|------------|
 | Reasoning Off | 0% | 
 | Reasoning On | 47.1% |
 User Prompt Template: 
 ```
 "Below is a math question. I want you to reason through the steps and then give a final answer. Your final answer should be in \boxed{}.\nQuestion: {question}"
 ```
 ### GPQA-D
 | Reasoning Mode | pass@1 |
 |--------------|------------|
 | Reasoning Off | 39.4% | 
 | Reasoning On | 54.1% |
 User Prompt Template: 
 ```
 "What is the correct answer to this question: {question}\nChoices:\nA. {option_A}\nB. {option_B}\nC. {option_C}\nD. {option_D}\nLet's think step by step, and put the final answer (should be a single letter A, B, C, or D) into a \boxed{}"
 ```
 ### IFEval Average
 | Reasoning Mode | Strict:Prompt | Strict:Instruction |
 |--------------|------------|------------|
 | Reasoning Off | 74.7% | 82.1% |
 | Reasoning On | 71.9% | 79.3% |
 ### BFCL v2 Live
 | Reasoning Mode | Score |
 |--------------|------------|
 | Reasoning Off | 63.9% | 
 | Reasoning On | 63.6% | 
 User Prompt Template:
 ```
 <AVAILABLE_TOOLS>{functions}</AVAILABLE_TOOLS>
 {user_prompt}
 ```
 ### MBPP 0-shot
 | Reasoning Mode | pass@1 |
 |--------------|------------|
 | Reasoning Off | 66.1% | 
 | Reasoning On | 84.6% |
 User Prompt Template:
 ````
 You are an exceptionally intelligent coding assistant that consistently delivers accurate and reliable responses to user instructions.
@@ Instruction
 Here is the given problem and test examples:
 {prompt}
 Please use the python programming language to solve this problem.
 Please make sure that your code includes the functions from the test samples and that the input and output formats of these functions match the test samples.
 Please return all completed codes in one code block.
 This code block should be in the following format:
 ```python
 # Your codes here
 ```
 ````
 ## Ethical Considerations:
 NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications.  When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse. 
 For more detailed information on ethical considerations for this model, please see the Model Card++ [Explainability](explainability.md), [Bias](bias.md), [Safety & Security](safety.md), and [Privacy](privacy.md) Subcards.
 Please report security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/).
 ## Citation
 ```
@misc{bercovich2025llamanemotronefficientreasoningmodels,
      title={Llama-Nemotron: Efficient Reasoning Models}, 
      author={Akhiad Bercovich and Itay Levy and Izik Golan and Mohammad Dabbah and Ran El-Yaniv and Omri Puny and Ido Galil and Zach Moshe and Tomer Ronen and Najeeb Nabwani and Ido Shahaf and Oren Tropp and Ehud Karpas and Ran Zilberstein and Jiaqi Zeng and Soumye Singhal and Alexander Bukharin and Yian Zhang and Tugrul Konuk and Gerald Shen and Ameya Sunil Mahabaleshwarkar and Bilal Kartal and Yoshi Suhara and Olivier Delalleau and Zijia Chen and Zhilin Wang and David Mosallanezhad and Adi Renduchintala and Haifeng Qian and Dima Rekesh and Fei Jia and Somshubra Majumdar and Vahid Noroozi and Wasi Uddin Ahmad and Sean Narenthiran and Aleksander Ficek and Mehrzad Samadi and Jocelyn Huang and Siddhartha Jain and Igor Gitman and Ivan Moshkov and Wei Du and Shubham Toshniwal and George Armstrong and Branislav Kisacanin and Matvei Novikov and Daria Gitman and Evelina Bakhturina and Jane Polak Scowcroft and John Kamalu and Dan Su and Kezhi Kong and Markus Kliegl and Rabeeh Karimi and Ying Lin and Sanjeev Satheesh and Jupinder Parmar and Pritam Gundecha and Brandon Norick and Joseph Jennings and Shrimai Prabhumoye and Syeda Nahida Akter and Mostofa Patwary and Abhinav Khattar and Deepak Narayanan and Roger Waleffe and Jimmy Zhang and Bor-Yiing Su and Guyue Huang and Terry Kong and Parth Chadha and Sahil Jain and Christine Harvey and Elad Segal and Jining Huang and Sergey Kashirsky and Robert McQueen and Izzy Putterman and George Lam and Arun Venkatesan and Sherry Wu and Vinh Nguyen and Manoj Kilaru and Andrew Wang and Anna Warno and Abhilash Somasamudramath and Sandip Bhaskar and Maka Dong and Nave Assaf and Shahar Mor and Omer Ullman Argov and Scot Junkin and Oleksandr Romanenko and Pedro Larroy and Monika Katariya and Marco Rovinelli and Viji Balas and Nicholas Edelman and Anahita Bhiwandiwalla and Muthu Subramaniam and Smita Ithape and Karthik Ramamoorthy and Yuting Wu and Suguna Varshini Velury and Omri Almog and Joyjit Daw and Denys Fridman and Erick Galinkin and Michael Evans and Katherine Luna and Leon Derczynski and Nikki Pope and Eileen Long and Seth Schneider and Guillermo Siman and Tomasz Grzegorzek and Pablo Ribalta and Monika Katariya and Joey Conway and Trisha Saar and Ann Guan and Krzysztof Pawelec and Shyamala Prayaga and Oleksii Kuchaiev and Boris Ginsburg and Oluwatobi Olabiyi and Kari Briski and Jonathan Cohen and Bryan Catanzaro and Jonah Alben and Yonatan Geifman and Eric Chung and Chris Alexiuk},
      year={2025},
      eprint={2505.00949},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2505.00949}, 
 }
 ```
--- a/configuration.json
+++ b/configuration.json
@@ -0,0 +1 @@
 {"framework": "pytorch", "task": "text-generation", "allow_remote": true}
		`@@ -0,0 +1 @@`
							`{"framework": "pytorch", "task": "text-generation", "allow_remote": true}`