add deepseek-coder-v2 in siliconflow (#6149)

This commit is contained in:
SiliconFlow, Inc
2024-07-29 18:45:19 +08:00
committed by GitHub
parent 94d68b6a08
commit 3e18d32ce5
13 changed files with 165 additions and 24 deletions

View File

@@ -0,0 +1,30 @@
model: deepseek-ai/DeepSeek-Coder-V2-Instruct
label:
en_US: deepseek-ai/DeepSeek-Coder-V2-Instruct
model_type: llm
features:
- agent-thought
model_properties:
mode: chat
context_size: 32768
parameter_rules:
- name: temperature
use_template: temperature
- name: max_tokens
use_template: max_tokens
type: int
default: 512
min: 1
max: 4096
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: '1.33'
output: '1.33'
unit: '0.000001'
currency: RMB

View File

@@ -1,11 +1,9 @@
model: deepseek-ai/deepseek-v2-chat
label:
en_US: deepseek-ai/deepseek-v2-chat
en_US: deepseek-ai/DeepSeek-V2-Chat
model_type: llm
features:
- multi-tool-call
- agent-thought
- stream-tool-call
model_properties:
mode: chat
context_size: 32768

View File

@@ -1,11 +1,9 @@
model: zhipuai/glm4-9B-chat
label:
en_US: zhipuai/glm4-9B-chat
en_US: THUDM/glm-4-9b-chat
model_type: llm
features:
- multi-tool-call
- agent-thought
- stream-tool-call
model_properties:
mode: chat
context_size: 32768

View File

@@ -1,11 +1,9 @@
model: alibaba/Qwen2-57B-A14B-Instruct
label:
en_US: alibaba/Qwen2-57B-A14B-Instruct
en_US: Qwen/Qwen2-57B-A14B-Instruct
model_type: llm
features:
- multi-tool-call
- agent-thought
- stream-tool-call
model_properties:
mode: chat
context_size: 32768

View File

@@ -1,11 +1,9 @@
model: alibaba/Qwen2-72B-Instruct
label:
en_US: alibaba/Qwen2-72B-Instruct
en_US: Qwen/Qwen2-72B-Instruct
model_type: llm
features:
- multi-tool-call
- agent-thought
- stream-tool-call
model_properties:
mode: chat
context_size: 32768

View File

@@ -1,11 +1,9 @@
model: alibaba/Qwen2-7B-Instruct
label:
en_US: alibaba/Qwen2-7B-Instruct
en_US: Qwen/Qwen2-7B-Instruct
model_type: llm
features:
- multi-tool-call
- agent-thought
- stream-tool-call
model_properties:
mode: chat
context_size: 32768

View File

@@ -1,11 +1,9 @@
model: 01-ai/Yi-1.5-34B-Chat
label:
en_US: 01-ai/Yi-1.5-34B-Chat
en_US: 01-ai/Yi-1.5-34B-Chat-16K
model_type: llm
features:
- multi-tool-call
- agent-thought
- stream-tool-call
model_properties:
mode: chat
context_size: 16384

View File

@@ -3,9 +3,7 @@ label:
en_US: 01-ai/Yi-1.5-6B-Chat
model_type: llm
features:
- multi-tool-call
- agent-thought
- stream-tool-call
model_properties:
mode: chat
context_size: 4096

View File

@@ -1,11 +1,9 @@
model: 01-ai/Yi-1.5-9B-Chat
label:
en_US: 01-ai/Yi-1.5-9B-Chat
en_US: 01-ai/Yi-1.5-9B-Chat-16K
model_type: llm
features:
- multi-tool-call
- agent-thought
- stream-tool-call
model_properties:
mode: chat
context_size: 16384

View File

@@ -19,7 +19,7 @@ class SiliconflowProvider(ModelProvider):
model_instance = self.get_model_instance(ModelType.LLM)
model_instance.validate_credentials(
model='deepseek-ai/deepseek-v2-chat',
model='deepseek-ai/DeepSeek-V2-Chat',
credentials=credentials
)
except CredentialsValidateFailedError as ex: