Upload StableLmForCausalLM

config.json

@@ -1,11 +1,11 @@
 {
-  "_name_or_path": "/home/lunarsylph/_code_/neuralpantheon/finetuning-subnet/local-models/training/now",
+  "_name_or_path": "/home/lunarsylph/_code_/neuralpantheon/output-model-directory",
   "architectures": [
     "StableLmForCausalLM"
   ],
   "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": 2048,
@@ -18,12 +18,14 @@
   "num_hidden_layers": 24,
   "num_key_value_heads": 32,
   "partial_rotary_factor": 0.25,
+  "qk_layernorm": false,
   "rope_scaling": null,
   "rope_theta": 10000,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.40.0",
   "use_cache": false,
+  "use_parallel_residual": false,
   "use_qkv_bias": true,
   "vocab_size": 100352
 }

generation_config.json

@@ -1,7 +1,7 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 100257,
-  "do_sample": true,
-  "eos_token_id": 100257,
-  "transformers_version": "4.38.2"
+  "bos_token_id": 100289,
+  "eos_token_id": 100290,
+  "transformers_version": "4.40.0",
+  "use_cache": false
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5617bc6dde25af47cd54f7f2c5ceb711ebf4155dc033ff445bc4852df5ad9db2
+oid sha256:849f1a1cea1d8871987956e4f4e1fd37e871b4663074e23fd04e5649822aa841
 size 3289069520