Upload HGRN2ForCausalLM

README.md

@@ -8,4 +8,4 @@ license: mit
 datasets:
 - cerebras/SlimPajama-627B
 library_name: fla
----
+---

config.json

@@ -3,13 +3,16 @@
   "architectures": [
     "HGRN2ForCausalLM"
   ],
+  "attn": null,
   "attn_mode": "chunk",
   "bos_token_id": 1,
   "clamp_min": null,
   "conv_size": 4,
+  "elementwise_affine": true,
   "eos_token_id": 2,
   "expand_ratio": 128,
   "fuse_cross_entropy": true,
+  "fuse_norm": true,
   "hidden_act": "swish",
   "hidden_ratio": 4,
   "hidden_size": 2560,
@@ -17,13 +20,14 @@
   "intermediate_size": null,
   "max_position_embeddings": 2048,
   "model_type": "hgrn2",
+  "norm_eps": 1e-06,
   "num_heads": null,
   "num_hidden_layers": 32,
   "rms_norm_eps": 1e-06,
   "share_conv_kernel": true,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.40.0",
+  "transformers_version": "4.48.2",
   "use_cache": true,
   "use_lower_bound": true,
   "use_short_conv": false,

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.40.0"
+  "transformers_version": "4.48.2"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95cae9caf9d48a6cec02380ef75c0f5464c482a1c3a039658918f20eecf5efc1
-size 4974853272
+oid sha256:a8008edb10834e196bbe9c78f896a21d4f089395061529d74e1fbf5bd33d1426
+size 4974856616

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3956beea2164c9ef7d3b8dee6d573a3efa280838b3f214a5fb85a5d82300982
-size 428627344
+oid sha256:fb674a97de711b6364529b121c268d0961e29d109cd9e6d791a2c81c1b85f122
+size 428627568

model.safetensors.index.json

@@ -13,6 +13,7 @@
     "model.layers.0.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.attn.f_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.attn.g_norm.weight": "model-00001-of-00002.safetensors",
@@ -22,6 +23,7 @@
     "model.layers.1.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.attn.f_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.attn.g_norm.weight": "model-00001-of-00002.safetensors",
@@ -31,6 +33,7 @@
     "model.layers.10.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.attn.f_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.attn.g_norm.weight": "model-00001-of-00002.safetensors",
@@ -40,6 +43,7 @@
     "model.layers.11.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.attn.f_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.attn.g_norm.weight": "model-00001-of-00002.safetensors",
@@ -49,6 +53,7 @@
     "model.layers.12.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.attn.f_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.attn.g_norm.weight": "model-00001-of-00002.safetensors",
@@ -58,6 +63,7 @@
     "model.layers.13.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.attn.f_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.attn.g_norm.weight": "model-00001-of-00002.safetensors",
@@ -67,6 +73,7 @@
     "model.layers.14.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.attn.f_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.attn.g_norm.weight": "model-00001-of-00002.safetensors",
@@ -76,6 +83,7 @@
     "model.layers.15.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.attn.f_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.attn.g_norm.weight": "model-00001-of-00002.safetensors",
@@ -85,6 +93,7 @@
     "model.layers.16.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.attn.f_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.attn.g_norm.weight": "model-00001-of-00002.safetensors",
@@ -94,6 +103,7 @@
     "model.layers.17.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.attn.f_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.attn.g_norm.weight": "model-00001-of-00002.safetensors",
@@ -103,6 +113,7 @@
     "model.layers.18.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.attn.f_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.attn.g_norm.weight": "model-00001-of-00002.safetensors",
@@ -112,6 +123,7 @@
     "model.layers.19.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.attn.f_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.attn.g_norm.weight": "model-00001-of-00002.safetensors",
@@ -121,6 +133,7 @@
     "model.layers.2.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.attn.f_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.attn.g_norm.weight": "model-00001-of-00002.safetensors",
@@ -130,6 +143,7 @@
     "model.layers.20.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.attn.f_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.attn.g_norm.weight": "model-00001-of-00002.safetensors",
@@ -139,6 +153,7 @@
     "model.layers.21.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.attn.f_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.attn.g_norm.weight": "model-00001-of-00002.safetensors",
@@ -148,6 +163,7 @@
     "model.layers.22.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.23.attn.f_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.23.attn.g_norm.weight": "model-00001-of-00002.safetensors",
@@ -157,6 +173,7 @@
     "model.layers.23.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.23.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.attn.f_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.attn.g_norm.weight": "model-00001-of-00002.safetensors",
@@ -166,6 +183,7 @@
     "model.layers.24.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.25.attn.f_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.25.attn.g_norm.weight": "model-00001-of-00002.safetensors",
@@ -175,6 +193,7 @@
     "model.layers.25.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.25.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.26.attn.f_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.26.attn.g_norm.weight": "model-00001-of-00002.safetensors",
@@ -184,6 +203,7 @@
     "model.layers.26.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.26.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.27.attn.f_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.27.attn.g_norm.weight": "model-00001-of-00002.safetensors",
@@ -193,6 +213,7 @@
     "model.layers.27.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.28.attn.f_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.28.attn.g_norm.weight": "model-00001-of-00002.safetensors",
@@ -202,6 +223,7 @@
     "model.layers.28.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.28.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.29.attn.f_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.29.attn.g_norm.weight": "model-00001-of-00002.safetensors",
@@ -211,6 +233,7 @@
     "model.layers.29.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.29.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.attn.f_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.attn.g_norm.weight": "model-00001-of-00002.safetensors",
@@ -220,6 +243,7 @@
     "model.layers.3.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.30.attn.f_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.30.attn.g_norm.weight": "model-00001-of-00002.safetensors",
@@ -229,6 +253,7 @@
     "model.layers.30.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.31.attn.f_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.attn.g_norm.weight": "model-00002-of-00002.safetensors",
@@ -238,6 +263,7 @@
     "model.layers.31.attn_norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.mlp_norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.4.attn.f_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.attn.g_norm.weight": "model-00001-of-00002.safetensors",
@@ -247,6 +273,7 @@
     "model.layers.4.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.attn.f_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.attn.g_norm.weight": "model-00001-of-00002.safetensors",
@@ -256,6 +283,7 @@
     "model.layers.5.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.attn.f_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.attn.g_norm.weight": "model-00001-of-00002.safetensors",
@@ -265,6 +293,7 @@
     "model.layers.6.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.attn.f_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.attn.g_norm.weight": "model-00001-of-00002.safetensors",
@@ -274,6 +303,7 @@
     "model.layers.7.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.attn.f_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.attn.g_norm.weight": "model-00001-of-00002.safetensors",
@@ -283,6 +313,7 @@
     "model.layers.8.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.attn.f_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.attn.g_norm.weight": "model-00001-of-00002.safetensors",
@@ -292,6 +323,7 @@
     "model.layers.9.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.lower_bounds": "model-00001-of-00002.safetensors",
     "model.norm.weight": "model-00002-of-00002.safetensors"