Update model_config.yaml

model_config.yaml

@@ -33,7 +33,6 @@ model:
     attention_bias: false
     attention_dropout: 0.0
     mlp_bias: false
-    
   tokenizer:
     type: "sentencepiece"
     model_max_length: 131072
@@ -42,15 +41,6 @@ model:
     chat_template: "{% for message in messages %}{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>\n' }}{% endfor %}{{ '<|im_start|>assistant\n' }}"
 
   training:
-    base_model: "meta-llama/Meta-Llama-3.1-70B"
-    training_data:
-      - "scientific_papers"
-      - "code_repositories"
-      - "mathematical_proofs"
-      - "conversational_data"
-      - "multilingual_corpus"
-      - "technical_documentation"
-    total_tokens: "2.5T"
     training_steps: 150000
     warmup_steps: 2000
     learning_rate: 2.0e-5
@@ -70,14 +60,10 @@ model:
     
   quantization:
     bits: 16
+    precision: "float16"
     supported_formats:
       - "fp16"
-      - "bf16"
-      - "int8"
-      - "int4"
-      - "awq"
-      - "gptq"
-      - "gguf"
+    note: "Model is provided in full FP16 precision without quantization"
 
 inference:
   default_parameters: