Update README.md

README.md

@@ -1,15 +1,50 @@
 ---
-model_type: gpt2
+activation_function: gelu_new
 architectures:
   - GPT2LMHeadModel
-config:
+attn_pdrop: 0.1
+bos_token_id: 50256
+embd_pdrop: 0.1
+eos_token_id: 50256
+initializer_range: 0.02
+layer_norm_epsilon: 1e-05
+model_type: gpt2
+n_ctx: 2048
+n_embd: 2048
+n_head: 16
+n_layer: 24
+n_positions: 2048
+n_special: 0
+predict_special_tokens: true
+resid_pdrop: 0.1
+summary_activation: null
+summary_first_dropout: 0.1
+summary_proj_to_labels: true
+summary_type: cls_index
+summary_use_proj: true
+task_specific_params:
+  text-generation:
+    do_sample: true
+    max_length: 2048
+transformers_version: 4.34.0
+language:
+  - en
+tags:
+  - text-generation-inference
+metrics:
+  - accuracy
+pipeline_tag: text-generation
+library_name: transformers
+datasets:
+  - vicgalle/alpaca-gpt4
+license: apache-2.0
+custom_params:
   adaptation_rate: 0.05
   complexity_metric: null
   desired_improvement_rate: 0.02
   ecosystem_dynamics:
     environmental_volatility: 0.1
     resource_pool: 1
-  embedding_dim: 768
   growth_improvement_threshold: 0.01
   hidden_dim: 2048
   initial_neuron_count: 5000
@@ -18,49 +53,27 @@ config:
     complexity_metric: null
     initial_capacity: 250000
     input_size: 2048
-  input_dimension: 768
+  input_dimension: 2048
   low_stability_threshold: 0.01
-  max_complexity: 10000
+  max_complexity: 50000
   max_neurons: 250000
-  max_sequence_length: 200
+  max_sequence_length: 2048
   min_epochs_before_growth: 5
   model_filename: pytorch_model.bin
-  num_embeddings: 25000
+  num_embeddings: 100000
   pruning_improvement_threshold: 0.005
   some_adaptation_rate: 0.05
   stability_threshold: 0.02
   start_token_index: 2
-  transformers_version: 4.34.0
-  attn_pdrop: 0.1
-  bos_token_id: 50256
-  embd_pdrop: 0.1
-  eos_token_id: 50256
-  initializer_range: 0.02
-  layer_norm_epsilon: 0.00001
-  n_ctx: 2048
-  n_embd: 2048
-  n_head: 16
-  n_layer: 24
-  n_positions: 2048
-  n_special: 0
-  predict_special_tokens: true
-  resid_pdrop: 0.1
-  summary_activation: null
-  summary_first_dropout: 0.1
-  summary_proj_to_labels: true
-  summary_type: cls_index
-  summary_use_proj: true
-license: apache-2.0
-datasets:
-  - vicgalle/alpaca-gpt4
-language:
-  - en
-tags:
-  - text-generation-inference
-metrics:
-  - accuracy
-pipeline_tag: text-generation
-library_name: transformers
+max_input_length: 1024
+max_total_tokens: 1512
+max_concurrent_requests: 128
+max_best_of: 2
+max_stop_sequences: 4
+max_top_n_tokens: 5
+waiting_served_ratio: 1.2
+max_batch_prefill_tokens: 2048
+max_waiting_tokens: 20
 ---
 ---
 ## Phillnet Large 🚀