Upload LlamaForCausalLM

config.json

@@ -1,7 +1,7 @@
 {
-  "_name_or_path": "sn6-finetuning/test3_51",
+  "_name_or_path": "/notebooks/sn6-finetuning/test_3",
   "architectures": [
-    "StableLmForCausalLM"
+    "LlamaForCausalLM"
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 100289,
@@ -13,17 +13,19 @@
   "intermediate_size": 5632,
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 4096,
-  "model_type": "stablelm",
+  "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 24,
   "num_key_value_heads": 32,
   "partial_rotary_factor": 0.25,
+  "pretraining_tp": 1,
   "qk_layernorm": false,
+  "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 10000,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.40.0",
+  "transformers_version": "4.33.0",
   "use_cache": false,
   "use_parallel_residual": false,
   "use_qkv_bias": true,

generation_config.json

@@ -2,6 +2,6 @@
   "_from_model_config": true,
   "bos_token_id": 100289,
   "eos_token_id": 100290,
-  "transformers_version": "4.40.0",
+  "transformers_version": "4.33.0",
   "use_cache": false
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ca6a816a7cddd089e359af03666e542db3d1e775801331913c63c5bd40e30bf
-size 3289069520
+oid sha256:1b67eebe63ec8c3803d32e401d0492e164e0d529b0974a29e218ef4e4567ef4d
+size 3288560400