Upload LlamaForCausalLM

config.json

@@ -4,19 +4,23 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
   "head_dim": 64,
   "hidden_act": "silu",
   "hidden_size": 2048,
   "initializer_range": 0.02,
-  "intermediate_size": 5632,
-  "max_position_embeddings": 2048,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
   "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,
-  "num_hidden_layers": 22,
-  "num_key_value_heads": 4,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
   "pretraining_tp": 1,
   "quantization_config": {
     "_load_in_4bit": true,
@@ -34,11 +38,17 @@
     "quant_method": "bitsandbytes"
   },
   "rms_norm_eps": 1e-05,
-  "rope_scaling": null,
-  "rope_theta": 10000.0,
-  "tie_word_embeddings": false,
+  "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": "4.55.4",
   "use_cache": false,
-  "vocab_size": 32000
+  "vocab_size": 128256
 }

generation_config.json

@@ -1,7 +1,12 @@
 {
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "max_length": 2048,
-  "pad_token_id": 0,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
   "transformers_version": "4.55.4"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13a533b861ea20a24ee661f53b709274c7f4c85e447650cf81d0bb6b6da65359
-size 813150315
+oid sha256:917abdded5a61fccbaae44f2ccb35b04ccc5aa2ebb68748413b6386a4019b4e7
+size 1072936873