Trained with Unsloth

README.md

@@ -6,6 +6,7 @@ tags:
 - unsloth
 - llama
 - trl
+- sft
 license: apache-2.0
 language:
 - en

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "scb10x/llama3.2-typhoon2-1b-instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128001,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "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": true,
+  "torch_dtype": "float16",
+  "transformers_version": "4.46.3",
+  "unsloth_version": "2024.12.8",
+  "use_cache": false,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,19 @@
+{
+  "alpha": 0.0,
+  "attn_implementation": "flash_attention_2",
+  "beta": 1.0,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "gamma": 1.0,
+  "kl_temperature": 1.0,
+  "max_length": 131072,
+  "pad_token_id": 128001,
+  "temperature": 0.4,
+  "top_p": 0.9,
+  "transformers_version": "4.46.3"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fd7b3f06beadda3f5146ce92d9a32bc25505fea8a7bf6d014500ab8e965199f
+size 2471678098