End of training

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
-license: llama3.1
-base_model: meta-llama/Meta-Llama-3.1-8B
+license: llama3.2
+base_model: meta-llama/Llama-3.2-1B
 tags:
 - generated_from_trainer
 model-index:
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Bitnet-LLaMa3
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on an unknown dataset.
 
 ## Model description
 

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "meta-llama/Meta-Llama-3.1-8B",
+  "_name_or_path": "meta-llama/Llama-3.2-1B",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -7,7 +7,7 @@
   "attention_dropout": 0.0,
   "bos_token_id": 128000,
   "eos_token_id": 128001,
-  "head_dim": 128,
+  "head_dim": 64,
   "hidden_act": "silu",
   "hidden_size": 768,
   "initializer_range": 0.02,
@@ -21,14 +21,14 @@
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": {
-    "factor": 8.0,
+    "factor": 32.0,
     "high_freq_factor": 4.0,
     "low_freq_factor": 1.0,
     "original_max_position_embeddings": 8192,
     "rope_type": "llama3"
   },
   "rope_theta": 500000.0,
-  "tie_word_embeddings": false,
+  "tie_word_embeddings": true,
   "torch_dtype": "float32",
   "transformers_version": "4.48.0",
   "use_cache": true,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e07ee156a5542b2a801163336121660ff09613e5d417f5357d68bb994a6b2617
-size 901278240
+oid sha256:3857f0b46aab17080c94a583b6c2510dd892eb840e09ffd66fb47d24ed855d50
+size 478964168

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30eb476622bcaed6a89610692f38493b3ec189fbb52596a83ae1353826546d87
+oid sha256:b5f77d9153ad0ea3bcf7e1eccda042c5fd6bcf1b8b0b9d9ca47822f597aa93a1
 size 5368