TaylorAI
/

Flash-Llama-30M-10001

Text Generation

text-generation-inference

Model card Files Files and versions

andersonbcdefg commited on Sep 4, 2023

Commit

3f660f6

·

1 Parent(s): 2390371

Upload LlamaForCausalLM

Files changed (2) hide show

config.json +4 -4
pytorch_model.bin +2 -2

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "TaylorAI/Flash-Llama-220M",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -9,13 +9,13 @@
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
-  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 2048,
   "max_position_embeddings": 32768,
   "model_type": "llama",
   "num_attention_heads": 12,
-  "num_hidden_layers": 24,
   "num_key_value_heads": 12,
   "pad_token_id": 0,
   "pretraining_tp": 1,

 {
+  "_name_or_path": "TaylorAI/Flash-Llama-30M",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
+  "hidden_size": 384,
   "initializer_range": 0.02,
+  "intermediate_size": 1024,
   "max_position_embeddings": 32768,
   "model_type": "llama",
   "num_attention_heads": 12,
+  "num_hidden_layers": 4,
   "num_key_value_heads": 12,
   "pad_token_id": 0,
   "pretraining_tp": 1,

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e8f5ed5f1cecf9618554c29e8dc521010036a348af1b6f5fde2a25c189c31df
-size 876309369

 version https://git-lfs.github.com/spec/v1
+oid sha256:09492185918b3a42dd760c096e07c3d26368c4270ba9072b4e14332d890e1e7d
+size 126642150