Langlin Huang
commited on
Commit
·
f651a9a
1
Parent(s):
860d8e5
upload model
Browse files- README.md +6 -3
- config.json +24 -0
- pytorch_model.bin +3 -0
README.md
CHANGED
|
@@ -1,3 +1,6 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
This is the PosS-2 model of the paper **PosS:Position Specialist Generates Better Draft for Speculative Decoding**
|
| 2 |
+
|
| 3 |
+
If the code fails to auto-download the models, you may mannually download the following files.
|
| 4 |
+
|
| 5 |
+
- `pytorch_model.bin`: Model weights
|
| 6 |
+
- `config.json`: Model config
|
config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"bos_token_id": 1,
|
| 6 |
+
"eos_token_id": 2,
|
| 7 |
+
"hidden_act": "silu",
|
| 8 |
+
"hidden_size": 5120,
|
| 9 |
+
"initializer_range": 0.02,
|
| 10 |
+
"intermediate_size": 13824,
|
| 11 |
+
"max_position_embeddings": 4096,
|
| 12 |
+
"model_type": "llama",
|
| 13 |
+
"num_attention_heads": 40,
|
| 14 |
+
"num_hidden_layers": 1,
|
| 15 |
+
"num_key_value_heads": 40,
|
| 16 |
+
"pretraining_tp": 1,
|
| 17 |
+
"rms_norm_eps": 1e-05,
|
| 18 |
+
"rope_scaling": null,
|
| 19 |
+
"tie_word_embeddings": false,
|
| 20 |
+
"torch_dtype": "float16",
|
| 21 |
+
"transformers_version": "4.31.0.dev0",
|
| 22 |
+
"use_cache": true,
|
| 23 |
+
"vocab_size": 32000
|
| 24 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8d0d8ba2adca21a3515da70d733b30c385cfb6c9b4c7a4b80e74b0916530f6a
|
| 3 |
+
size 4671498999
|