ThisIsATest
/

dclm-id-410m

Text Generation

text-generation-inference

Model card Files Files and versions

ThisIsATest commited on Jan 30

Commit

a3b449c

·

verified ·

1 Parent(s): ffca336

Upload GPTNeoXForCausalLM

Files changed (2) hide show

config.json +5 -5
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "dclm_id_160m/0/final",
   "architectures": [
     "GPTNeoXForCausalLM"
   ],
@@ -10,14 +10,14 @@
   "eos_token_id": 0,
   "hidden_act": "gelu",
   "hidden_dropout": 0.0,
-  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 2048,
   "model_type": "gpt_neox",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
   "rope_scaling": null,
   "rotary_emb_base": 10000,
   "rotary_pct": 0.25,

 {
+  "_name_or_path": "dclm_id_410m/0/final",
   "architectures": [
     "GPTNeoXForCausalLM"
   ],
   "eos_token_id": 0,
   "hidden_act": "gelu",
   "hidden_dropout": 0.0,
+  "hidden_size": 1024,
   "initializer_range": 0.02,
+  "intermediate_size": 4096,
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 2048,
   "model_type": "gpt_neox",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
   "rope_scaling": null,
   "rotary_emb_base": 10000,
   "rotary_pct": 0.25,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14b27ef98298d20a7ddbebc03dc12cce838649ddde7410f55ef2c8b7ba0fcce3
-size 649308728

 version https://git-lfs.github.com/spec/v1
+oid sha256:526e0143e5f10d35f5d2a74833b8a5d47441202aaa92cd1892148c439b192799
+size 1621370224