Upload LlamaForCausalLM

config.json

@@ -1,23 +1,22 @@
 {
-  "_name_or_path": "beomi/OPEN-SOLAR-KO-10.7B",
+  "_name_or_path": "MLP-KTLim/llama-3-Korean-Bllossom-8B",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
+  "bos_token_id": 144782,
+  "eos_token_id": 144783,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 14336,
-  "max_position_embeddings": 4096,
+  "max_position_embeddings": 8192,
   "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,
-  "num_hidden_layers": 48,
+  "num_hidden_layers": 32,
   "num_key_value_heads": 8,
-  "pad_token_id": 2,
   "pretraining_tp": 1,
   "quantization_config": {
     "_load_in_4bit": true,
@@ -36,10 +35,10 @@
   },
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
-  "rope_theta": 10000.0,
+  "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.42.0.dev0",
   "use_cache": true,
-  "vocab_size": 46592
+  "vocab_size": 145088
 }

generation_config.json

@@ -1,7 +1,12 @@
 {
-  "_from_model_config": true,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "pad_token_id": 2,
+  "bos_token_id": 144782,
+  "do_sample": true,
+  "eos_token_id": [
+    144783,
+    144791
+  ],
+  "max_length": 8192,
+  "temperature": 0.6,
+  "top_p": 0.9,
   "transformers_version": "4.42.0.dev0"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4c8a4783a248582a31a4603279226a785bd7cb1b4c5cd48ff2b72a238292bc2
-size 4980021348
+oid sha256:1aafbb763d7d0cd431cd2627304679b560bdb943057d7103fd8015e289eee67b
+size 4987647217

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa013eceba4c01da94e12da13167a64bebee30b772f3005de12715aeacb306f2
-size 1949600570
+oid sha256:1c1354ca568202717d207596d9d23186ba5eec2adb44048e9a34a2d935e3ace8
+size 3368533469