Upload StableLmForCausalLM

config.json

@@ -1,28 +1,29 @@
 {
   "_name_or_path": "/finetuning-subnet/local-models/training/BestWeights",
   "architectures": [
-    "GemmaForCausalLM"
+    "StableLmForCausalLM"
   ],
-  "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 204,
-  "eos_token_id": 213,
-  "head_dim": 256,
-  "hidden_act": "gelu",
+  "bos_token_id": 100289,
+  "eos_token_id": 100290,
+  "hidden_act": "silu",
+  "hidden_dropout": 0.0,
   "hidden_size": 2048,
   "initializer_range": 0.02,
-  "intermediate_size": 16384,
-  "max_position_embeddings": 8192,
-  "model_type": "gemma",
-  "num_attention_heads": 8,
-  "num_hidden_layers": 18,
-  "num_key_value_heads": 1,
-  "pad_token_id": 0,
-  "rms_norm_eps": 1e-06,
+  "intermediate_size": 5632,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 4096,
+  "model_type": "stablelm",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 32,
+  "partial_rotary_factor": 0.25,
   "rope_scaling": null,
-  "rope_theta": 10000.0,
+  "rope_theta": 10000,
+  "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.38.2",
   "use_cache": false,
-  "vocab_size": 256000
+  "use_qkv_bias": true,
+  "vocab_size": 100352
 }

generation_config.json

@@ -1,8 +1,6 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 204,
-  "eos_token_id": 213,
-  "pad_token_id": 0,
-  "transformers_version": "4.38.2",
-  "use_cache": false
+  "bos_token_id": 100257,
+  "eos_token_id": 100257,
+  "transformers_version": "4.38.2"
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32aa2079a9b4d3c1e7c7288e0525f0f9e4a92e4fdd34295fa80459bcdf797059
+size 3289069520