Lugha-Llama
/

Lugha-Llama-8B-wura_edu

Text Generation

text-generation-inference

Model card Files Files and versions

Happyb commited on Dec 19, 2024

Commit

5b729a5

·

verified ·

1 Parent(s): bfc3ee6

Upload config.json

Files changed (1) hide show

config.json +3 -4

config.json CHANGED Viewed

@@ -1,13 +1,12 @@
 {
-  "_name_or_path": "/scratch/gpfs/awettig/wura/checkpoints/lcft_Llama-3.1-8B_datasets_wura_unimax_0.6+edu_bsz512_steps2400_lr1e-5_warmup0.1",
   "architectures": [
-    "LlamaForSequenceClassification"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 128000,
   "eos_token_id": 128001,
-  "head_dim": 128,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
@@ -31,7 +30,7 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.47.0",
   "use_cache": true,
   "vocab_size": 128256
 }

 {
+  "_name_or_path": "/home/awettig/pli/models/meta-llama/Llama-3.1-8B",
   "architectures": [
+    "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 128000,
   "eos_token_id": 128001,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
   "use_cache": true,
   "vocab_size": 128256
 }