jungiebeen
/

pretrain4

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

jungiebeen commited on Feb 9

Commit

11573a3

•

1 Parent(s): ecc5af6

Upload LlamaForCausalLM

Files changed (2) hide show

config.json +13 -11
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -1,23 +1,25 @@
 {
-  "_name_or_path": "/workspace/pretraining/local-models/training/2024-02-05_16-59-29",
   "architectures": [
-    "MistralForCausalLM"
   ],
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
-  "hidden_size": 864,
   "initializer_range": 0.02,
-  "intermediate_size": 2382,
   "max_position_embeddings": 1024,
-  "model_type": "mistral",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 18,
-  "num_key_value_heads": 2,
-  "rms_norm_eps": 1e-06,
   "rope_theta": 10000.0,
-  "sliding_window": 4096,
-  "tie_word_embeddings": true,
   "torch_dtype": "float32",
   "transformers_version": "4.34.1",
   "use_cache": true,

 {
+  "_name_or_path": "/workspace/pretraining/local-models/training/2024-02-09_14-58-48",
   "architectures": [
+    "LlamaForCausalLM"
   ],
+  "attention_bias": false,
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
+  "hidden_size": 768,
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "max_position_embeddings": 1024,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
   "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.34.1",
   "use_cache": true,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7976b28faa4444b669d6d9200e9097df57300e3187a7cb2423a7fbc83500f8b
-size 743784040

 version https://git-lfs.github.com/spec/v1
+oid sha256:7947260eb0d46c9e2395dc870e2d808bc06f1677acd59ab561ad04a877de5bf2
+size 733541408