Merge branch 'main' into cohere-lm-head

arcee-ai · Sep 16, 2024 · 1e829bd · 1e829bd
2 parents df7c08b + a5a597f
commit 1e829bd
Show file tree

Hide file tree

Showing 3 changed files with 173 additions and 0 deletions.
diff --git a/mergekit/_data/architectures/exaone.json b/mergekit/_data/architectures/exaone.json
@@ -0,0 +1,78 @@
+{
+    "model_type": "exaone",
+    "architectures": [
+        "ExaoneForCausalLM"
+    ],
+    "pre_weights": [
+        {
+            "name": "transformer.wte.weight",
+            "is_embed": true,
+            "output_space": "running_residual"
+        }
+    ],
+    "num_layers_config_key": "num_hidden_layers",
+    "layer_templates": {
+        "weights": [
+            {
+                "name": "transformer.h.${layer_index}.ln_1.weight",
+                "input_space": "running_residual"
+            },
+            {
+                "name": "transformer.h.${layer_index}.attn.attention.q_proj.weight",
+                "input_space": "running_residual",
+                "output_space": "attn_qk_${layer_index}",
+                "head_split": "output",
+                "is_kq": true
+            },
+            {
+                "name": "transformer.h.${layer_index}.attn.attention.k_proj.weight",
+                "input_space": "running_residual",
+                "output_space": "attn_qk_${layer_index}",
+                "head_split": "output",
+                "is_kq": true
+            },
+            {
+                "name": "transformer.h.${layer_index}.attn.attention.v_proj.weight",
+                "input_space": "running_residual",
+                "output_space": "attn_v_${layer_index}",
+                "head_split": "output"
+            },
+            {
+                "name": "transformer.h.${layer_index}.attn.attention.out_proj.weight",
+                "input_space": "attn_v_${layer_index}",
+                "output_space": "running_residual",
+                "head_split": "input"
+            },
+            {
+                "name": "transformer.h.${layer_index}.ln_2.weight",
+                "input_space": "running_residual"
+            },
+            {
+                "name": "transformer.h.${layer_index}.mlp.c_fc_0.weight",
+                "input_space": "running_residual",
+                "output_space": "up_${layer_index}"
+            },
+            {
+                "name": "transformer.h.${layer_index}.mlp.c_fc_1.weight",
+                "input_space": "running_residual",
+                "output_space": "up_${layer_index}"
+            },
+            {
+                "name": "transformer.h.${layer_index}.mlp.c_proj.weight",
+                "input_space": "up_${layer_index}",
+                "output_space": "running_residual"
+            }
+        ]
+    },
+    "post_weights": [
+        {
+            "name": "transformer.ln_f.weight",
+            "input_space": "running_residual"
+        },
+        {
+            "name": "lm_head.weight",
+            "input_space": "running_residual",
+            "is_embed": true
+        }
+    ]
+}
diff --git a/mergekit/_data/architectures/solar.json b/mergekit/_data/architectures/solar.json
@@ -0,0 +1,81 @@
+{
+  "model_type": "solar",
+  "architectures": [
+    "SolarForCausalLM"
+  ],
+  "pre_weights": [
+    {
+      "name": "model.embed_tokens.weight",
+      "is_embed": true,
+      "output_space": "running_residual"
+    }
+  ],
+  "num_layers_config_key": "num_hidden_layers",
+  "layer_templates": {
+    "weights": [
+      {
+        "name": "model.layers.${layer_index}.input_layernorm.weight",
+        "input_space": "running_residual"
+      },
+      {
+        "name": "model.layers.${layer_index}.self_attn.k_proj.weight",
+        "input_space": "running_residual",
+        "output_space": "attn_qk_${layer_index}",
+        "head_split": "output",
+        "is_kq": true
+      },
+      {
+        "name": "model.layers.${layer_index}.self_attn.q_proj.weight",
+        "input_space": "running_residual",
+        "output_space": "attn_qk_${layer_index}",
+        "head_split": "output",
+        "is_kq": true
+      },
+      {
+        "name": "model.layers.${layer_index}.self_attn.v_proj.weight",
+        "input_space": "running_residual",
+        "output_space": "attn_v_${layer_index}",
+        "head_split": "output"
+      },
+      {
+        "name": "model.layers.${layer_index}.self_attn.o_proj.weight",
+        "input_space": "attn_v_${layer_index}",
+        "output_space": "running_residual",
+        "head_split": "input"
+      },
+      {
+        "name": "model.layers.${layer_index}.post_attention_layernorm.weight",
+        "input_space": "running_residual"
+      },
+      {
+        "name": "model.layers.${layer_index}.mlp.gate_proj.weight",
+        "input_space": "running_residual",
+        "output_space": "up_${layer_index}"
+      },
+      {
+        "name": "model.layers.${layer_index}.mlp.up_proj.weight",
+        "input_space": "running_residual",
+        "output_space": "up_${layer_index}"
+      },
+      {
+        "name": "model.layers.${layer_index}.mlp.down_proj.weight",
+        "input_space": "up_${layer_index}",
+        "output_space": "running_residual"
+      }
+    ]
+  },
+  "post_weights": [
+    {
+      "name": "model.norm.weight",
+      "input_space": "running_residual"
+    },
+    {
+      "name": "lm_head.weight",
+      "input_space": "running_residual",
+      "is_embed": true,
+      "aliases": [
+        "model.lm_head.weight"
+      ]
+    }
+  ]
+}
diff --git a/mergekit/_data/chat_templates/exaone.jinja b/mergekit/_data/chat_templates/exaone.jinja
@@ -0,0 +1,14 @@
+{% for message in messages %}
+    {% if loop.first and message['role'] != 'system' %}
+        {{ '[|system|][|endofturn|]\n' }}
+    {% endif %}
+    {{ '[|' + message['role'] + '|]' + message['content'] }}
+    {% if message['role'] == 'user' %}
+        {{ '\n' }}
+    {% else %}
+        {{ '[|endofturn|]\n' }}
+    {% endif %}
+{% endfor %}
+{% if add_generation_prompt %}
+    {{ '[|assistant|]' }}
+{% endif %}