vLLM compatible randon Medusa heads for llama-68m (only to test code)

.gitattributes

@@ -33,3 +33,4 @@ 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
+model.safetensors filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1 @@
+{"_name_or_path": "abhigoyal/vllm-medusa-llama-68m-random", "architectures": ["MedusaModel"], "hidden_size": 768, "model_type": "medusa", "num_heads": 5, "num_hidden_layers": 1, "transformers_version": "4.41.2", "truncated_vocab_size": null, "vocab_size": 32000}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77e25e430a4740d2a667770335d2703d2ea6c6adf91268193248b6e0df21a73c
+size 503317424