Add files using upload-large-folder tool

Llama-3.1-Nemotron-Nano-8B-v1-Q4_K_M.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae3c9ebc13364bcda5c98f473bff77ddb37f3d20dbf10846788e386e21729c3e
-size 4920737376
+oid sha256:3fc180a9b0310146a86d1a0ac79e0fa7b932fbe5ad697b0aaf73f931f38eac3c
+size 4920737344

Llama-3.1-Nemotron-Nano-8B-v1-UD-IQ1_S.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f216e32cd529984bd80c89d7a3fb28ada2be4cbb0b64f947e93ffaf71970724
-size 2164670048
+oid sha256:d00bbcaae67af32a221a2a173402e9411f13dc098e11fbeca6ba554af984c58e
+size 2164670016

Llama-3.1-Nemotron-Nano-8B-v1-UD-Q2_K_XL.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fa878dc181382df70062bc464801d2352e0f7ae9258c39a26084af3215b9b56
-size 3388767840
+oid sha256:366adf3f9dddeb82256b730cc1fd8ec7558990d876b9e182296b822bf9cabcb6
+size 3388767808

Llama-3.1-Nemotron-Nano-8B-v1-UD-Q3_K_XL.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cd369a1a61de6add0497d2ef9c92b2a0a232c3d5497c382e1e6973b0f6091cb
-size 4199612000
+oid sha256:10ee118ebe4293541b546a93cb772d482be7c6cac94e27ec17aa295bc06d0b67
+size 4199611968

Llama-3.1-Nemotron-Nano-8B-v1-UD-Q4_K_XL.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fde406f1d51ea2272813f65f6698dde1d0993139da208c2e7aab510607d4914e
-size 4994203232
+oid sha256:c62e39d9170993d5eab0260b0935429f11af85100689f6dd40a4743bd5ac1476
+size 4994203200

Llama-3.1-Nemotron-Nano-8B-v1-UD-Q5_K_XL.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2fd3ec4485ddc07d7a526c14c095c39d7dfdbaca009d2131b74f0f9ec05a9f5
-size 5738135136
+oid sha256:bfcb0f81d1fa19274914c027ed9007881f81a5f1ec81217ab4f0c89bad3f709d
+size 5738135104

README.md

@@ -16,6 +16,23 @@ tags:
   - llama-3
   - pytorch
 ---
+<div>
+<p style="margin-top: 0;margin-bottom: 0;">
+    <em><a href="https://docs.unsloth.ai/basics/unsloth-dynamic-v2.0-gguf">Unsloth Dynamic 2.0</a> achieves superior accuracy & outperforms other leading quants.</em>
+  </p>
+  <div style="display: flex; gap: 5px; align-items: center; ">
+    <a href="https://github.com/unslothai/unsloth/">
+      <img src="https://github.com/unslothai/unsloth/raw/main/images/unsloth%20new%20logo.png" width="133">
+    </a>
+    <a href="https://discord.gg/unsloth">
+      <img src="https://github.com/unslothai/unsloth/raw/main/images/Discord%20button.png" width="173">
+    </a>
+    <a href="https://docs.unsloth.ai/basics/qwen3-how-to-run-and-fine-tune">
+      <img src="https://raw.githubusercontent.com/unslothai/unsloth/refs/heads/main/images/documentation%20green%20button.png" width="143">
+    </a>
+  </div>
+</div>
+
 
 # Llama-3.1-Nemotron-Nano-8B-v1
 

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "nvidia/Llama-3.1-Nemotron-Nano-8B-v1",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -22,6 +21,7 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
+  "pad_token_id": 128004,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": {
@@ -34,7 +34,8 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.47.1",
+  "transformers_version": "4.52.2",
+  "unsloth_fixed": true,
   "use_cache": true,
   "vocab_size": 128256
 }