Upload Qwen2ForCausalLM

README.md

@@ -1,4 +1,3 @@
-
 ---
 language: en
 tags:
@@ -14,16 +13,16 @@ datasets:
 model-index:
 - name: Qwen-0.5B-MUSR
   results:
-  - task: 
+  - task:
       type: question-answering
       name: Multi-Source Reasoning (MUSR)
-    dataset: 
+    dataset:
       name: QASC
       type: allenai/qasc
     metrics:
-      - name: Accuracy
-        type: accuracy
-        value: 0.87
+    - type: accuracy
+      value: 0.87
+      name: Accuracy
 ---
 
 # Qwen-0.5B-MUSR

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Mxode/NanoLM-0.3B-Instruct-v1.1",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "down_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 sha256:5077027c58bec87df83d6272d6ecb37a8e9b743b84cea212c3882aa8e767c67d
+size 17618400

generation_config.json

@@ -1,6 +1,10 @@
 {
-  "bos_token_id": 151643,
-  "eos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": 151645,
   "max_new_tokens": 2048,
-  "transformers_version": "4.46.1"
+  "pad_token_id": 151643,
+  "temperature": 0.3,
+  "top_k": 20,
+  "top_p": 0.7,
+  "transformers_version": "4.46.2"
 }