Upload 4 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,51 @@
+{
+	"_name_or_path": "meta-llama/Llama-3.2-3B-Instruct",
+	"architectures": [
+		"LlamaForCausalLM"
+	],
+	"attention_bias": false,
+	"attention_dropout": 0.0,
+	"bos_token_id": 128000,
+	"eos_token_id": [
+		128001,
+		128008,
+		128009
+	],
+	"head_dim": 128,
+	"hidden_act": "silu",
+	"hidden_size": 3072,
+	"initializer_range": 0.02,
+	"intermediate_size": 8192,
+	"max_position_embeddings": 131072,
+	"mlp_bias": false,
+	"model_type": "llama",
+	"num_attention_heads": 24,
+	"num_hidden_layers": 28,
+	"num_key_value_heads": 8,
+	"pretraining_tp": 1,
+	"quantization_config": {
+		"bits": 8.0,
+		"calibration": {
+			"dataset": "(default)",
+			"length": 2048,
+			"rows": 115
+		},
+		"head_bits": 8,
+		"quant_method": "exl2",
+		"version": "0.2.7"
+	},
+	"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": "bfloat16",
+	"transformers_version": "4.46.1",
+	"use_cache": true,
+	"vocab_size": 193800
+}

output.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7aa2cfd1ebcc6bf93af2d23c69e023bc3c77edcf13b5fa34a56a683a2fbb0ea3
+size 4164834384

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95bf49f269d747b353adf1bcb53819f1fee8e0ecd657b38b37fef06d121b3568
+size 23569711