From 362b281e55d72104aff3fcfba742d6059f2a61a7 Mon Sep 17 00:00:00 2001
From: Hoter Young <hoteryoung@163.com>
Date: Fri, 14 Feb 2025 22:01:16 +0800
Subject: [PATCH] [Feature] Support 3 models (#34)

opencompass/configs/models/deepseek/lmdeploy_deepseek_r1_distill_llama_70b_instruct.py
opencompass/configs/models/deepseek/lmdeploy_deepseek_r1_distill_qwen_14b_instruct.py
opencompass/configs/models/hf_llama/llama3_3_70b_api_siliconflow.py
---
 ...oy_deepseek_r1_distill_llama_70b_instruct.py | 16 ++++++++++++++++
 ...loy_deepseek_r1_distill_qwen_14b_instruct.py | 15 +++++++++++++++
 .../hf_llama/llama3_3_70b_api_siliconflow.py    | 17 +++++++++++++++++
 3 files changed, 48 insertions(+)
 create mode 100644 opencompass/configs/models/deepseek/lmdeploy_deepseek_r1_distill_llama_70b_instruct.py
 create mode 100644 opencompass/configs/models/deepseek/lmdeploy_deepseek_r1_distill_qwen_14b_instruct.py
 create mode 100644 opencompass/configs/models/hf_llama/llama3_3_70b_api_siliconflow.py

diff --git a/opencompass/configs/models/deepseek/lmdeploy_deepseek_r1_distill_llama_70b_instruct.py b/opencompass/configs/models/deepseek/lmdeploy_deepseek_r1_distill_llama_70b_instruct.py
new file mode 100644
index 00000000..df154b09
--- /dev/null
+++ b/opencompass/configs/models/deepseek/lmdeploy_deepseek_r1_distill_llama_70b_instruct.py
@@ -0,0 +1,16 @@
+from opencompass.models import TurboMindModelwithChatTemplate
+
+models = [
+    dict(
+        type=TurboMindModelwithChatTemplate,
+        abbr='deepseek_r1_distill_llama_70b_turbomind',
+        path='deepseek-ai/DeepSeek-R1-Distill-Llama-70B',
+        engine_config=dict(max_batch_size=16, tp=4),
+        gen_config=dict(top_k=1, temperature=1e-6, top_p=0.9, max_new_tokens=8192),
+        max_seq_len=16384,
+        max_out_len=8192,
+        batch_size=16,
+        run_cfg=dict(num_gpus=4),
+        stop_words=['<|end_of_text|>', '<|eot_id|>', '<|eom_id|>'],
+    )
+]
diff --git a/opencompass/configs/models/deepseek/lmdeploy_deepseek_r1_distill_qwen_14b_instruct.py b/opencompass/configs/models/deepseek/lmdeploy_deepseek_r1_distill_qwen_14b_instruct.py
new file mode 100644
index 00000000..23555d0d
--- /dev/null
+++ b/opencompass/configs/models/deepseek/lmdeploy_deepseek_r1_distill_qwen_14b_instruct.py
@@ -0,0 +1,15 @@
+from opencompass.models import TurboMindModelwithChatTemplate
+
+models = [
+    dict(
+        type=TurboMindModelwithChatTemplate,
+        abbr='deepseek_r1_distill_qwen_14b_turbomind',
+        path='deepseek-ai/DeepSeek-R1-Distill-Qwen-14B',
+        engine_config=dict(session_len=16384, max_batch_size=16, tp=2),
+        gen_config=dict(top_k=1, temperature=1e-6, top_p=0.9, max_new_tokens=4096),
+        max_seq_len=16384,
+        max_out_len=4096,
+        batch_size=16,
+        run_cfg=dict(num_gpus=2),
+    )
+]
diff --git a/opencompass/configs/models/hf_llama/llama3_3_70b_api_siliconflow.py b/opencompass/configs/models/hf_llama/llama3_3_70b_api_siliconflow.py
new file mode 100644
index 00000000..c33c1a37
--- /dev/null
+++ b/opencompass/configs/models/hf_llama/llama3_3_70b_api_siliconflow.py
@@ -0,0 +1,17 @@
+from opencompass.models import OpenAISDK
+
+models = [
+    dict(
+        abbr='llama3_3_70b_api_siliconflow',
+        type=OpenAISDK,
+        path='meta-llama/Llama-3.3-70B-Instruct',
+        key='ENV_SILICONFLOW',
+        openai_api_base='https://api.siliconflow.cn/v1/',
+        query_per_second=1,
+        max_out_len=4096,
+        max_seq_len=4096,
+        batch_size=1,
+        retry=30,
+        verbose=True,
+    ),
+]