From 824a0dd63ec30f94eacf64fddbbdd367ff5ad48e Mon Sep 17 00:00:00 2001
From: zhuhao <37029601+hwzhuhao@users.noreply.github.com>
Date: Tue, 1 Oct 2024 10:55:51 +0800
Subject: [PATCH] feat: add qwen2.5-72b and llama3.2 for openrouter (#8956)

---
 .../openrouter/llm/_position.yaml             |  5 +++
 .../llm/llama-3.2-11b-vision-instruct.yaml    | 45 +++++++++++++++++++
 .../openrouter/llm/llama-3.2-1b-instruct.yaml | 45 +++++++++++++++++++
 .../openrouter/llm/llama-3.2-3b-instruct.yaml | 45 +++++++++++++++++++
 .../llm/llama-3.2-90b-vision-instruct.yaml    | 45 +++++++++++++++++++
 .../openrouter/llm/qwen2.5-72b-instruct.yaml  | 30 +++++++++++++
 6 files changed, 215 insertions(+)
 create mode 100644 api/core/model_runtime/model_providers/openrouter/llm/llama-3.2-11b-vision-instruct.yaml
 create mode 100644 api/core/model_runtime/model_providers/openrouter/llm/llama-3.2-1b-instruct.yaml
 create mode 100644 api/core/model_runtime/model_providers/openrouter/llm/llama-3.2-3b-instruct.yaml
 create mode 100644 api/core/model_runtime/model_providers/openrouter/llm/llama-3.2-90b-vision-instruct.yaml
 create mode 100644 api/core/model_runtime/model_providers/openrouter/llm/qwen2.5-72b-instruct.yaml

diff --git a/api/core/model_runtime/model_providers/openrouter/llm/_position.yaml b/api/core/model_runtime/model_providers/openrouter/llm/_position.yaml
index d9497b76b8..5a25c84c34 100644
--- a/api/core/model_runtime/model_providers/openrouter/llm/_position.yaml
+++ b/api/core/model_runtime/model_providers/openrouter/llm/_position.yaml
@@ -14,6 +14,10 @@
 - google/gemini-pro
 - cohere/command-r-plus
 - cohere/command-r
+- meta-llama/llama-3.2-1b-instruct
+- meta-llama/llama-3.2-3b-instruct
+- meta-llama/llama-3.2-11b-vision-instruct
+- meta-llama/llama-3.2-90b-vision-instruct
 - meta-llama/llama-3.1-405b-instruct
 - meta-llama/llama-3.1-70b-instruct
 - meta-llama/llama-3.1-8b-instruct
@@ -22,6 +26,7 @@
 - mistralai/mixtral-8x22b-instruct
 - mistralai/mixtral-8x7b-instruct
 - mistralai/mistral-7b-instruct
+- qwen/qwen-2.5-72b-instruct
 - qwen/qwen-2-72b-instruct
 - deepseek/deepseek-chat
 - deepseek/deepseek-coder
diff --git a/api/core/model_runtime/model_providers/openrouter/llm/llama-3.2-11b-vision-instruct.yaml b/api/core/model_runtime/model_providers/openrouter/llm/llama-3.2-11b-vision-instruct.yaml
new file mode 100644
index 0000000000..235156997f
--- /dev/null
+++ b/api/core/model_runtime/model_providers/openrouter/llm/llama-3.2-11b-vision-instruct.yaml
@@ -0,0 +1,45 @@
+model: meta-llama/llama-3.2-11b-vision-instruct
+label:
+  zh_Hans: llama-3.2-11b-vision-instruct
+  en_US: llama-3.2-11b-vision-instruct
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 131072
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+  - name: max_tokens
+    use_template: max_tokens
+  - name: context_length_exceeded_behavior
+    default: None
+    label:
+      zh_Hans: 上下文长度超出行为
+      en_US: Context Length Exceeded Behavior
+    help:
+      zh_Hans: 上下文长度超出行为
+      en_US: Context Length Exceeded Behavior
+    type: string
+    options:
+      - None
+      - truncate
+      - error
+  - name: response_format
+    use_template: response_format
+pricing:
+  input: '0.055'
+  output: '0.055'
+  unit: '0.000001'
+  currency: USD
diff --git a/api/core/model_runtime/model_providers/openrouter/llm/llama-3.2-1b-instruct.yaml b/api/core/model_runtime/model_providers/openrouter/llm/llama-3.2-1b-instruct.yaml
new file mode 100644
index 0000000000..657ef16835
--- /dev/null
+++ b/api/core/model_runtime/model_providers/openrouter/llm/llama-3.2-1b-instruct.yaml
@@ -0,0 +1,45 @@
+model: meta-llama/llama-3.2-1b-instruct
+label:
+  zh_Hans: llama-3.2-1b-instruct
+  en_US: llama-3.2-1b-instruct
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 131072
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+  - name: max_tokens
+    use_template: max_tokens
+  - name: context_length_exceeded_behavior
+    default: None
+    label:
+      zh_Hans: 上下文长度超出行为
+      en_US: Context Length Exceeded Behavior
+    help:
+      zh_Hans: 上下文长度超出行为
+      en_US: Context Length Exceeded Behavior
+    type: string
+    options:
+      - None
+      - truncate
+      - error
+  - name: response_format
+    use_template: response_format
+pricing:
+  input: '0.01'
+  output: '0.02'
+  unit: '0.000001'
+  currency: USD
diff --git a/api/core/model_runtime/model_providers/openrouter/llm/llama-3.2-3b-instruct.yaml b/api/core/model_runtime/model_providers/openrouter/llm/llama-3.2-3b-instruct.yaml
new file mode 100644
index 0000000000..7f6e24e591
--- /dev/null
+++ b/api/core/model_runtime/model_providers/openrouter/llm/llama-3.2-3b-instruct.yaml
@@ -0,0 +1,45 @@
+model: meta-llama/llama-3.2-3b-instruct
+label:
+  zh_Hans: llama-3.2-3b-instruct
+  en_US: llama-3.2-3b-instruct
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 131072
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+  - name: max_tokens
+    use_template: max_tokens
+  - name: context_length_exceeded_behavior
+    default: None
+    label:
+      zh_Hans: 上下文长度超出行为
+      en_US: Context Length Exceeded Behavior
+    help:
+      zh_Hans: 上下文长度超出行为
+      en_US: Context Length Exceeded Behavior
+    type: string
+    options:
+      - None
+      - truncate
+      - error
+  - name: response_format
+    use_template: response_format
+pricing:
+  input: '0.03'
+  output: '0.05'
+  unit: '0.000001'
+  currency: USD
diff --git a/api/core/model_runtime/model_providers/openrouter/llm/llama-3.2-90b-vision-instruct.yaml b/api/core/model_runtime/model_providers/openrouter/llm/llama-3.2-90b-vision-instruct.yaml
new file mode 100644
index 0000000000..5d597f00a2
--- /dev/null
+++ b/api/core/model_runtime/model_providers/openrouter/llm/llama-3.2-90b-vision-instruct.yaml
@@ -0,0 +1,45 @@
+model: meta-llama/llama-3.2-90b-vision-instruct
+label:
+  zh_Hans: llama-3.2-90b-vision-instruct
+  en_US: llama-3.2-90b-vision-instruct
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 131072
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+  - name: max_tokens
+    use_template: max_tokens
+  - name: context_length_exceeded_behavior
+    default: None
+    label:
+      zh_Hans: 上下文长度超出行为
+      en_US: Context Length Exceeded Behavior
+    help:
+      zh_Hans: 上下文长度超出行为
+      en_US: Context Length Exceeded Behavior
+    type: string
+    options:
+      - None
+      - truncate
+      - error
+  - name: response_format
+    use_template: response_format
+pricing:
+  input: '0.35'
+  output: '0.4'
+  unit: '0.000001'
+  currency: USD
diff --git a/api/core/model_runtime/model_providers/openrouter/llm/qwen2.5-72b-instruct.yaml b/api/core/model_runtime/model_providers/openrouter/llm/qwen2.5-72b-instruct.yaml
new file mode 100644
index 0000000000..f141a40a00
--- /dev/null
+++ b/api/core/model_runtime/model_providers/openrouter/llm/qwen2.5-72b-instruct.yaml
@@ -0,0 +1,30 @@
+model: qwen/qwen-2.5-72b-instruct
+label:
+  en_US: qwen-2.5-72b-instruct
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 131072
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: max_tokens
+    use_template: max_tokens
+    type: int
+    default: 512
+    min: 1
+    max: 8192
+    help:
+      zh_Hans: 指定生成结果长度的上限。如果生成结果截断，可以调大该参数。
+      en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
+  - name: top_p
+    use_template: top_p
+  - name: frequency_penalty
+    use_template: frequency_penalty
+pricing:
+  input: "0.35"
+  output: "0.4"
+  unit: "0.000001"
+  currency: USD