vLLM compatible version for FasterDecoding/medusa-vicuna-7b-v1.3

.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-vicuna-7b-v1.3", "architectures": ["MedusaModel"], "hidden_size": 4096, "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 sha256:1b1631aa671ced86c78c2f0e21ecb0e67970105962bc808d78173a0bf3e40545
+size 1478493144