Upload LlamaForCausalLM

README.md

@@ -4,13 +4,13 @@ language:
 - ja
 license: other
 library_name: transformers
-base_model: meta-llama/Meta-Llama-3-8B-Instruct
 tags:
 - facebook
 - meta
 - pytorch
 - llama
 - llama-3
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
 datasets:
 - cl-nagoya/auto-wiki-qa
 - llm-jp/databricks-dolly-15k-ja

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "rinna/llama-3-youko-8b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61dd70c14a136f9b9329eec5fcc5136dd33cff54ae8b5a46aedfd2c9b908e116
+size 54543312

generation_config.json

@@ -1,9 +1,6 @@
 {
   "_from_model_config": true,
   "bos_token_id": 128000,
-  "eos_token_id": [
-    128001,
-    128009
-  ],
+  "eos_token_id": 128001,
   "transformers_version": "4.40.0"
 }