初始化项目，由ModelHub XC社区提供模型

Model: dormantx/Qwen2.5-1.5B-Instruct-NLA-L18-av Source: Original Platform
2026-07-20 06:28:09 +08:00
commit d61644c5d3
11 changed files with 663 additions and 0 deletions
--- a/nla_meta.yaml
+++ b/nla_meta.yaml
@@ -0,0 +1,40 @@
+kind: nla_model
+schema_version: 2
+d_model: 1536
+tokens:
+  injection_char: <|image_pad|>
+  injection_token_id: 151655
+  injection_left_neighbor_id: 220
+  injection_right_neighbor_id: 151645
+  critic_suffix_ids: null
+prompt_templates:
+  av: '<|im_start|>system
+
+    You interpret neural-network activations. Given one activation vector, name in a single sentence the
+    concept, entity, topic, or syntactic role it encodes. Be concrete; do not hedge or add preamble.<|im_end|>
+
+    <|im_start|>user
+
+    Activation: {injection_char}<|im_end|>
+
+    <|im_start|>assistant
+
+    '
+  ar: '{explanation}'
+created_by: nla (dormantx/NLA_Qwen2.5_1.5B pipeline)
+role_aliases:
+  verbalizer: actor
+  recon: critic
+layer: 18
+extraction_layer_index: 18
+base_model: Qwen/Qwen2.5-1.5B-Instruct
+role: av
+stage: sl
+extraction:
+  injection_scale: 1.01256
+  mse_scale: 1.0
+training:
+  lr: 1.0e-05
+  loss_type: sft_next_token
+  global_batch_size: 16
+  num_layers: 28