jtatman
/

pythia-delphi-small

Text Generation

text-generation-inference

Model card Files Files and versions

jtatman commited on Jun 29, 2024

Commit

213a817

·

verified ·

1 Parent(s): bfb027b

Upload GPTNeoXForCausalLM

Files changed (2) hide show

config.json +7 -7
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "jtatman/pythia-delphi-small",
   "architectures": [
     "GPTNeoXForCausalLM"
   ],
@@ -10,18 +10,18 @@
   "eos_token_id": 0,
   "hidden_act": "gelu",
   "hidden_dropout": 0.0,
-  "hidden_size": 2048,
   "initializer_range": 0.02,
-  "intermediate_size": 7168,
   "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 2048,
   "model_type": "gpt_neox",
-  "num_attention_heads": 8,
-  "num_hidden_layers": 8,
   "pad_token_id": 0,
   "rope_scaling": null,
   "rotary_emb_base": 10000,
-  "rotary_pct": 0.75,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.41.1",

 {
+  "_name_or_path": "jtatman/pythia-delphi-micromachine-funnel",
   "architectures": [
     "GPTNeoXForCausalLM"
   ],
   "eos_token_id": 0,
   "hidden_act": "gelu",
   "hidden_dropout": 0.0,
+  "hidden_size": 4096,
   "initializer_range": 0.02,
+  "intermediate_size": 8192,
   "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 4096,
   "model_type": "gpt_neox",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 1,
   "pad_token_id": 0,
   "rope_scaling": null,
   "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.41.1",

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b72281a1163679f0ae631f9c9436bff7d160705baa8a91e5e421e7bbc760b7f
-size 2301570480

 version https://git-lfs.github.com/spec/v1
+oid sha256:cfe5830823739de375837a56bcd913fd55444b69129d94de0bf37df5b76c830e
+size 2185742136