From 40dd63ecef93c478f4a7ffe58c9a077711e1c1d1 Mon Sep 17 00:00:00 2001 From: engchina <12236799+engchina@users.noreply.github.com> Date: Thu, 6 Feb 2025 13:24:27 +0800 Subject: [PATCH] Upgrade oracle models (#13174) Co-authored-by: engchina --- .../oci/llm/cohere.command-r-08-2024.yaml | 52 +++++++++++++++++++ .../oci/llm/cohere.command-r-16k.yaml | 1 + .../llm/cohere.command-r-plus-08-2024.yaml | 52 +++++++++++++++++++ .../oci/llm/cohere.command-r-plus.yaml | 1 + .../model_providers/oci/llm/llm.py | 8 +-- .../oci/llm/meta.llama-3-70b-instruct.yaml | 1 + .../oci/llm/meta.llama-3.1-70b-instruct.yaml | 51 ++++++++++++++++++ .../model_runtime/model_providers/oci/oci.py | 4 +- 8 files changed, 164 insertions(+), 6 deletions(-) create mode 100644 api/core/model_runtime/model_providers/oci/llm/cohere.command-r-08-2024.yaml create mode 100644 api/core/model_runtime/model_providers/oci/llm/cohere.command-r-plus-08-2024.yaml create mode 100644 api/core/model_runtime/model_providers/oci/llm/meta.llama-3.1-70b-instruct.yaml diff --git a/api/core/model_runtime/model_providers/oci/llm/cohere.command-r-08-2024.yaml b/api/core/model_runtime/model_providers/oci/llm/cohere.command-r-08-2024.yaml new file mode 100644 index 0000000000..adfd7543b2 --- /dev/null +++ b/api/core/model_runtime/model_providers/oci/llm/cohere.command-r-08-2024.yaml @@ -0,0 +1,52 @@ +model: cohere.command-r-08-2024 +label: + en_US: cohere.command-r-08-2024 v1.7 +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call +model_properties: + mode: chat + context_size: 128000 +parameter_rules: + - name: temperature + use_template: temperature + default: 1 + max: 1.0 + - name: topP + use_template: top_p + default: 0.75 + min: 0 + max: 1 + - name: topK + 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. + required: false + default: 0 + min: 0 + max: 500 + - name: presencePenalty + use_template: presence_penalty + min: 0 + max: 1 + default: 0 + - name: frequencyPenalty + use_template: frequency_penalty + min: 0 + max: 1 + default: 0 + - name: maxTokens + use_template: max_tokens + default: 600 + max: 4000 +pricing: + input: '0.0009' + output: '0.0009' + unit: '0.0001' + currency: USD diff --git a/api/core/model_runtime/model_providers/oci/llm/cohere.command-r-16k.yaml b/api/core/model_runtime/model_providers/oci/llm/cohere.command-r-16k.yaml index eb60cbcd90..152c09ce6c 100644 --- a/api/core/model_runtime/model_providers/oci/llm/cohere.command-r-16k.yaml +++ b/api/core/model_runtime/model_providers/oci/llm/cohere.command-r-16k.yaml @@ -50,3 +50,4 @@ pricing: output: '0.004' unit: '0.0001' currency: USD +deprecated: true diff --git a/api/core/model_runtime/model_providers/oci/llm/cohere.command-r-plus-08-2024.yaml b/api/core/model_runtime/model_providers/oci/llm/cohere.command-r-plus-08-2024.yaml new file mode 100644 index 0000000000..9db0a08496 --- /dev/null +++ b/api/core/model_runtime/model_providers/oci/llm/cohere.command-r-plus-08-2024.yaml @@ -0,0 +1,52 @@ +model: cohere.command-r-plus-08-2024 +label: + en_US: cohere.command-r-plus-08-2024 v1.6 +model_type: llm +features: + - multi-tool-call + - agent-thought + - stream-tool-call +model_properties: + mode: chat + context_size: 128000 +parameter_rules: + - name: temperature + use_template: temperature + default: 1 + max: 1.0 + - name: topP + use_template: top_p + default: 0.75 + min: 0 + max: 1 + - name: topK + 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. + required: false + default: 0 + min: 0 + max: 500 + - name: presencePenalty + use_template: presence_penalty + min: 0 + max: 1 + default: 0 + - name: frequencyPenalty + use_template: frequency_penalty + min: 0 + max: 1 + default: 0 + - name: maxTokens + use_template: max_tokens + default: 600 + max: 4000 +pricing: + input: '0.0156' + output: '0.0156' + unit: '0.0001' + currency: USD diff --git a/api/core/model_runtime/model_providers/oci/llm/cohere.command-r-plus.yaml b/api/core/model_runtime/model_providers/oci/llm/cohere.command-r-plus.yaml index df31b0d0df..e819fe05d4 100644 --- a/api/core/model_runtime/model_providers/oci/llm/cohere.command-r-plus.yaml +++ b/api/core/model_runtime/model_providers/oci/llm/cohere.command-r-plus.yaml @@ -50,3 +50,4 @@ pricing: output: '0.0219' unit: '0.0001' currency: USD +deprecated: true diff --git a/api/core/model_runtime/model_providers/oci/llm/llm.py b/api/core/model_runtime/model_providers/oci/llm/llm.py index 9f676573fc..ad40530222 100644 --- a/api/core/model_runtime/model_providers/oci/llm/llm.py +++ b/api/core/model_runtime/model_providers/oci/llm/llm.py @@ -33,7 +33,7 @@ logger = logging.getLogger(__name__) request_template = { "compartmentId": "", - "servingMode": {"modelId": "cohere.command-r-plus", "servingType": "ON_DEMAND"}, + "servingMode": {"modelId": "cohere.command-r-plus-08-2024", "servingType": "ON_DEMAND"}, "chatRequest": { "apiFormat": "COHERE", # "preambleOverride": "You are a helpful assistant.", @@ -60,19 +60,19 @@ oci_config_template = { class OCILargeLanguageModel(LargeLanguageModel): # https://docs.oracle.com/en-us/iaas/Content/generative-ai/pretrained-models.htm _supported_models = { - "meta.llama-3-70b-instruct": { + "meta.llama-3.1-70b-instruct": { "system": True, "multimodal": False, "tool_call": False, "stream_tool_call": False, }, - "cohere.command-r-16k": { + "cohere.command-r-08-2024": { "system": True, "multimodal": False, "tool_call": True, "stream_tool_call": False, }, - "cohere.command-r-plus": { + "cohere.command-r-plus-08-2024": { "system": True, "multimodal": False, "tool_call": True, diff --git a/api/core/model_runtime/model_providers/oci/llm/meta.llama-3-70b-instruct.yaml b/api/core/model_runtime/model_providers/oci/llm/meta.llama-3-70b-instruct.yaml index dd5be107c0..0917fe19a2 100644 --- a/api/core/model_runtime/model_providers/oci/llm/meta.llama-3-70b-instruct.yaml +++ b/api/core/model_runtime/model_providers/oci/llm/meta.llama-3-70b-instruct.yaml @@ -49,3 +49,4 @@ pricing: output: '0.015' unit: '0.0001' currency: USD +deprecated: true diff --git a/api/core/model_runtime/model_providers/oci/llm/meta.llama-3.1-70b-instruct.yaml b/api/core/model_runtime/model_providers/oci/llm/meta.llama-3.1-70b-instruct.yaml new file mode 100644 index 0000000000..2cf5666f89 --- /dev/null +++ b/api/core/model_runtime/model_providers/oci/llm/meta.llama-3.1-70b-instruct.yaml @@ -0,0 +1,51 @@ +model: meta.llama-3.1-70b-instruct +label: + zh_Hans: meta.llama-3.1-70b-instruct + en_US: meta.llama-3.1-70b-instruct +model_type: llm +features: + - agent-thought +model_properties: + mode: chat + context_size: 131072 +parameter_rules: + - name: temperature + use_template: temperature + default: 1 + max: 2.0 + - name: topP + use_template: top_p + default: 0.75 + min: 0 + max: 1 + - name: topK + 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. + required: false + default: 0 + min: 0 + max: 500 + - name: presencePenalty + use_template: presence_penalty + min: -2 + max: 2 + default: 0 + - name: frequencyPenalty + use_template: frequency_penalty + min: -2 + max: 2 + default: 0 + - name: maxTokens + use_template: max_tokens + default: 600 + max: 4000 +pricing: + input: '0.0075' + output: '0.0075' + unit: '0.0001' + currency: USD diff --git a/api/core/model_runtime/model_providers/oci/oci.py b/api/core/model_runtime/model_providers/oci/oci.py index e182d2d043..a3321cb9fd 100644 --- a/api/core/model_runtime/model_providers/oci/oci.py +++ b/api/core/model_runtime/model_providers/oci/oci.py @@ -19,8 +19,8 @@ class OCIGENAIProvider(ModelProvider): try: model_instance = self.get_model_instance(ModelType.LLM) - # Use `cohere.command-r-plus` model for validate, - model_instance.validate_credentials(model="cohere.command-r-plus", credentials=credentials) + # Use `cohere.command-r-plus-08-2024` model for validate, + model_instance.validate_credentials(model="cohere.command-r-plus-08-2024", credentials=credentials) except CredentialsValidateFailedError as ex: raise ex except Exception as ex: