Add FP8 dynamically quantized Qwen3-0.6B-Base model using llm-compressor

config.json

@@ -65,7 +65,7 @@
   "sliding_window": null,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.52.3",
+  "transformers_version": "4.52.4",
   "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151936

generation_config.json

@@ -2,5 +2,5 @@
   "bos_token_id": 151643,
   "eos_token_id": 151643,
   "max_new_tokens": 2048,
-  "transformers_version": "4.52.3"
+  "transformers_version": "4.52.4"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93b9e00ceea769d885151d1c6a331fe8fffa4d0f3d8bfb7a3d9cafd93fd2a889
+oid sha256:9df3b1dc1785115e8b679849372d1a5d5abc85573495458f96d060d926f23cfb
 size 1069802016