upload model

README.md

@@ -1,3 +1,6 @@
----
-license: llama3
----
+This is the PosS-2 model of the paper **PosS:Position Specialist Generates Better Draft for Speculative Decoding**
+
+If the code fails to auto-download the models, you may mannually download the following files.
+
+- `pytorch_model.bin`: Model weights
+- `config.json`: Model config

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_key_value_heads": 8,
+  "num_hidden_layers": 1,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-05,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "vocab_size": 128256,
+  "rope_theta": 500000.0,
+  "bias": true
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e39e5aa4d847647288f5fb4b2c4c0c881b4364e1d25bcb525a9dfc32f45ba601
+size 5725321327