Upload StableLmForCausalLM

config.json

@@ -3,30 +3,27 @@
   "architectures": [
     "StableLmForCausalLM"
   ],
-  "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 100257,
-  "eos_token_id": 100257,
+  "bos_token_id": 100289,
+  "eos_token_id": 100290,
   "hidden_act": "silu",
   "hidden_dropout": 0.0,
-  "hidden_size": 4096,
+  "hidden_size": 2048,
   "initializer_range": 0.02,
-  "intermediate_size": 14336,
+  "intermediate_size": 5632,
   "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 8192,
+  "max_position_embeddings": 4096,
   "model_type": "stablelm",
   "num_attention_heads": 32,
-  "num_hidden_layers": 32,
-  "num_key_value_heads": 8,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 32,
   "partial_rotary_factor": 0.25,
-  "pretraining_tp": 1,
-  "rms_norm_eps": 1e-05,
   "rope_scaling": null,
-  "rope_theta": 500000.0,
+  "rope_theta": 10000,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.38.2",
   "use_cache": false,
-  "use_qkv_bias": false,
-  "vocab_size": 128256
+  "use_qkv_bias": true,
+  "vocab_size": 100352
 }

generation_config.json

@@ -1,7 +1,7 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 128000,
-  "eos_token_id": 128001,
+  "bos_token_id": 100289,
+  "eos_token_id": 100290,
   "transformers_version": "4.38.2",
   "use_cache": false
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f946b9fb3813c70e0785bd5b6f40ee87786e23ecf864d116d11a108e20cab648
+oid sha256:dda3b2c847eca15873040a8a6f159609a4724bb28c9f949279be24a2bbc5f34c
 size 3289069520