Upload StableLmForCausalLM

config.json

@@ -1,12 +1,11 @@
 {
-  "_name_or_path": "neurons/model-best-0.998969982887929",
+  "_name_or_path": "neurons/model-best-0.9981573857838595",
   "architectures": [
     "StableLmForCausalLM"
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 100289,
-  "eos_token_id": 100257,
-  "eos_token_id_was": 100290,
+  "eos_token_id": 100290,
   "hidden_act": "silu",
   "hidden_dropout": 0.0,
   "hidden_size": 2048,
@@ -19,12 +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",
-  "use_cache": true,
+  "use_cache": false,
+  "use_parallel_residual": false,
   "use_qkv_bias": true,
   "vocab_size": 100352
 }

generation_config.json

@@ -2,5 +2,6 @@
   "_from_model_config": true,
   "bos_token_id": 100289,
   "eos_token_id": 100290,
-  "transformers_version": "4.38.2"
+  "transformers_version": "4.38.2",
+  "use_cache": false
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94663385dd39d10b5472733bcfdafedf902714f26331c2aa569e46e543fb4570
+oid sha256:2ea9240cffa647abfd74910dff61c198273a4b5b95c7e33066dd9aa26815dd31
 size 3289069520