Update README.md

README.md

@@ -268,4 +268,156 @@ Traceback (most recent call last):
   File "/teamspace/studios/this_studio/mergekit/mergekit/io/tasks.py", line 86, in execute
     raise RuntimeError(
 RuntimeError: Tensor lm_head.weight required but not present in model meta-llama/Llama-3.2-1B
+```
+
+which seems odd given the following output layers from llama-3-1b:
+
+```
+model.embed_tokens.weight
+model.layers.0.self_attn.q_proj.weight
+model.layers.0.self_attn.k_proj.weight
+model.layers.0.self_attn.v_proj.weight
+model.layers.0.self_attn.o_proj.weight
+model.layers.0.mlp.gate_proj.weight
+model.layers.0.mlp.up_proj.weight
+model.layers.0.mlp.down_proj.weight
+model.layers.0.input_layernorm.weight
+model.layers.0.post_attention_layernorm.weight
+model.layers.1.self_attn.q_proj.weight
+model.layers.1.self_attn.k_proj.weight
+model.layers.1.self_attn.v_proj.weight
+model.layers.1.self_attn.o_proj.weight
+model.layers.1.mlp.gate_proj.weight
+model.layers.1.mlp.up_proj.weight
+model.layers.1.mlp.down_proj.weight
+model.layers.1.input_layernorm.weight
+model.layers.1.post_attention_layernorm.weight
+model.layers.2.self_attn.q_proj.weight
+model.layers.2.self_attn.k_proj.weight
+model.layers.2.self_attn.v_proj.weight
+model.layers.2.self_attn.o_proj.weight
+model.layers.2.mlp.gate_proj.weight
+model.layers.2.mlp.up_proj.weight
+model.layers.2.mlp.down_proj.weight
+model.layers.2.input_layernorm.weight
+model.layers.2.post_attention_layernorm.weight
+model.layers.3.self_attn.q_proj.weight
+model.layers.3.self_attn.k_proj.weight
+model.layers.3.self_attn.v_proj.weight
+model.layers.3.self_attn.o_proj.weight
+model.layers.3.mlp.gate_proj.weight
+model.layers.3.mlp.up_proj.weight
+model.layers.3.mlp.down_proj.weight
+model.layers.3.input_layernorm.weight
+model.layers.3.post_attention_layernorm.weight
+model.layers.4.self_attn.q_proj.weight
+model.layers.4.self_attn.k_proj.weight
+model.layers.4.self_attn.v_proj.weight
+model.layers.4.self_attn.o_proj.weight
+model.layers.4.mlp.gate_proj.weight
+model.layers.4.mlp.up_proj.weight
+model.layers.4.mlp.down_proj.weight
+model.layers.4.input_layernorm.weight
+model.layers.4.post_attention_layernorm.weight
+model.layers.5.self_attn.q_proj.weight
+model.layers.5.self_attn.k_proj.weight
+model.layers.5.self_attn.v_proj.weight
+model.layers.5.self_attn.o_proj.weight
+model.layers.5.mlp.gate_proj.weight
+model.layers.5.mlp.up_proj.weight
+model.layers.5.mlp.down_proj.weight
+model.layers.5.input_layernorm.weight
+model.layers.5.post_attention_layernorm.weight
+model.layers.6.self_attn.q_proj.weight
+model.layers.6.self_attn.k_proj.weight
+model.layers.6.self_attn.v_proj.weight
+model.layers.6.self_attn.o_proj.weight
+model.layers.6.mlp.gate_proj.weight
+model.layers.6.mlp.up_proj.weight
+model.layers.6.mlp.down_proj.weight
+model.layers.6.input_layernorm.weight
+model.layers.6.post_attention_layernorm.weight
+model.layers.7.self_attn.q_proj.weight
+model.layers.7.self_attn.k_proj.weight
+model.layers.7.self_attn.v_proj.weight
+model.layers.7.self_attn.o_proj.weight
+model.layers.7.mlp.gate_proj.weight
+model.layers.7.mlp.up_proj.weight
+model.layers.7.mlp.down_proj.weight
+model.layers.7.input_layernorm.weight
+model.layers.7.post_attention_layernorm.weight
+model.layers.8.self_attn.q_proj.weight
+model.layers.8.self_attn.k_proj.weight
+model.layers.8.self_attn.v_proj.weight
+model.layers.8.self_attn.o_proj.weight
+model.layers.8.mlp.gate_proj.weight
+model.layers.8.mlp.up_proj.weight
+model.layers.8.mlp.down_proj.weight
+model.layers.8.input_layernorm.weight
+model.layers.8.post_attention_layernorm.weight
+model.layers.9.self_attn.q_proj.weight
+model.layers.9.self_attn.k_proj.weight
+model.layers.9.self_attn.v_proj.weight
+model.layers.9.self_attn.o_proj.weight
+model.layers.9.mlp.gate_proj.weight
+model.layers.9.mlp.up_proj.weight
+model.layers.9.mlp.down_proj.weight
+model.layers.9.input_layernorm.weight
+model.layers.9.post_attention_layernorm.weight
+model.layers.10.self_attn.q_proj.weight
+model.layers.10.self_attn.k_proj.weight
+model.layers.10.self_attn.v_proj.weight
+model.layers.10.self_attn.o_proj.weight
+model.layers.10.mlp.gate_proj.weight
+model.layers.10.mlp.up_proj.weight
+model.layers.10.mlp.down_proj.weight
+model.layers.10.input_layernorm.weight
+model.layers.10.post_attention_layernorm.weight
+model.layers.11.self_attn.q_proj.weight
+model.layers.11.self_attn.k_proj.weight
+model.layers.11.self_attn.v_proj.weight
+model.layers.11.self_attn.o_proj.weight
+model.layers.11.mlp.gate_proj.weight
+model.layers.11.mlp.up_proj.weight
+model.layers.11.mlp.down_proj.weight
+model.layers.11.input_layernorm.weight
+model.layers.11.post_attention_layernorm.weight
+model.layers.12.self_attn.q_proj.weight
+model.layers.12.self_attn.k_proj.weight
+model.layers.12.self_attn.v_proj.weight
+model.layers.12.self_attn.o_proj.weight
+model.layers.12.mlp.gate_proj.weight
+model.layers.12.mlp.up_proj.weight
+model.layers.12.mlp.down_proj.weight
+model.layers.12.input_layernorm.weight
+model.layers.12.post_attention_layernorm.weight
+model.layers.13.self_attn.q_proj.weight
+model.layers.13.self_attn.k_proj.weight
+model.layers.13.self_attn.v_proj.weight
+model.layers.13.self_attn.o_proj.weight
+model.layers.13.mlp.gate_proj.weight
+model.layers.13.mlp.up_proj.weight
+model.layers.13.mlp.down_proj.weight
+model.layers.13.input_layernorm.weight
+model.layers.13.post_attention_layernorm.weight
+model.layers.14.self_attn.q_proj.weight
+model.layers.14.self_attn.k_proj.weight
+model.layers.14.self_attn.v_proj.weight
+model.layers.14.self_attn.o_proj.weight
+model.layers.14.mlp.gate_proj.weight
+model.layers.14.mlp.up_proj.weight
+model.layers.14.mlp.down_proj.weight
+model.layers.14.input_layernorm.weight
+model.layers.14.post_attention_layernorm.weight
+model.layers.15.self_attn.q_proj.weight
+model.layers.15.self_attn.k_proj.weight
+model.layers.15.self_attn.v_proj.weight
+model.layers.15.self_attn.o_proj.weight
+model.layers.15.mlp.gate_proj.weight
+model.layers.15.mlp.up_proj.weight
+model.layers.15.mlp.down_proj.weight
+model.layers.15.input_layernorm.weight
+model.layers.15.post_attention_layernorm.weight
+model.norm.weight
+lm_head.weight
 ```