Trained with Unsloth

README.md

@@ -7,6 +7,8 @@ base_model:
 pipeline_tag: text-classification
 tags:
 - unsloth
+- trl
+- sft
 ---
 ---
 base_model: unsloth/Meta-Llama-3.1-8B-bnb-4bit

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "unsloth/Meta-Llama-3.1-8B-bnb-4bit",
+  "_name_or_path": "unsloth/llama-3.2-1b-bnb-4bit",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -7,30 +7,30 @@
   "attention_dropout": 0.0,
   "bos_token_id": 128000,
   "eos_token_id": 128001,
-  "head_dim": 128,
+  "head_dim": 64,
   "hidden_act": "silu",
-  "hidden_size": 4096,
+  "hidden_size": 2048,
   "initializer_range": 0.02,
-  "intermediate_size": 14336,
+  "intermediate_size": 8192,
   "max_position_embeddings": 131072,
   "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,
-  "num_hidden_layers": 32,
+  "num_hidden_layers": 16,
   "num_key_value_heads": 8,
   "pad_token_id": 128004,
   "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,
-  "torch_dtype": "bfloat16",
+  "tie_word_embeddings": true,
+  "torch_dtype": "float16",
   "transformers_version": "4.47.1",
   "unsloth_version": "2025.1.5",
   "use_cache": true,

generation_config.json

@@ -1,11 +1,8 @@
 {
   "_from_model_config": true,
   "bos_token_id": 128000,
-  "do_sample": true,
   "eos_token_id": 128001,
   "max_length": 131072,
   "pad_token_id": 128004,
-  "temperature": 0.6,
-  "top_p": 0.9,
   "transformers_version": "4.47.1"
 }

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72f96868259abaefd21dcfee7731d74b1f9376da9ce599e844911634b93eceba
+size 2471678098