From 4c85393a1d2c9d4cca05f2c640da73113fc532ae Mon Sep 17 00:00:00 2001 From: takatost Date: Wed, 24 Jul 2024 00:41:58 +0800 Subject: [PATCH] feat: add GroqCloud llama3.1 series models support (#6596) --- .../model_providers/groq/llm/_position.yaml | 7 ++++++ .../groq/llm/llama-3.1-405b-reasoning.yaml | 25 +++++++++++++++++++ .../groq/llm/llama-3.1-70b-versatile.yaml | 25 +++++++++++++++++++ .../groq/llm/llama-3.1-8b-instant.yaml | 25 +++++++++++++++++++ 4 files changed, 82 insertions(+) create mode 100644 api/core/model_runtime/model_providers/groq/llm/_position.yaml create mode 100644 api/core/model_runtime/model_providers/groq/llm/llama-3.1-405b-reasoning.yaml create mode 100644 api/core/model_runtime/model_providers/groq/llm/llama-3.1-70b-versatile.yaml create mode 100644 api/core/model_runtime/model_providers/groq/llm/llama-3.1-8b-instant.yaml diff --git a/api/core/model_runtime/model_providers/groq/llm/_position.yaml b/api/core/model_runtime/model_providers/groq/llm/_position.yaml new file mode 100644 index 0000000000..be115ca920 --- /dev/null +++ b/api/core/model_runtime/model_providers/groq/llm/_position.yaml @@ -0,0 +1,7 @@ +- llama-3.1-405b-reasoning +- llama-3.1-70b-versatile +- llama-3.1-8b-instant +- llama3-70b-8192 +- llama3-8b-8192 +- mixtral-8x7b-32768 +- llama2-70b-4096 diff --git a/api/core/model_runtime/model_providers/groq/llm/llama-3.1-405b-reasoning.yaml b/api/core/model_runtime/model_providers/groq/llm/llama-3.1-405b-reasoning.yaml new file mode 100644 index 0000000000..217785cea2 --- /dev/null +++ b/api/core/model_runtime/model_providers/groq/llm/llama-3.1-405b-reasoning.yaml @@ -0,0 +1,25 @@ +model: llama-3.1-405b-reasoning +label: + zh_Hans: Llama-3.1-405b-reasoning + en_US: Llama-3.1-405b-reasoning +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: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 8192 +pricing: + input: '0.05' + output: '0.1' + unit: '0.000001' + currency: USD diff --git a/api/core/model_runtime/model_providers/groq/llm/llama-3.1-70b-versatile.yaml b/api/core/model_runtime/model_providers/groq/llm/llama-3.1-70b-versatile.yaml new file mode 100644 index 0000000000..ab5f6ab05e --- /dev/null +++ b/api/core/model_runtime/model_providers/groq/llm/llama-3.1-70b-versatile.yaml @@ -0,0 +1,25 @@ +model: llama-3.1-70b-versatile +label: + zh_Hans: Llama-3.1-70b-versatile + en_US: Llama-3.1-70b-versatile +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: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 8192 +pricing: + input: '0.05' + output: '0.1' + unit: '0.000001' + currency: USD diff --git a/api/core/model_runtime/model_providers/groq/llm/llama-3.1-8b-instant.yaml b/api/core/model_runtime/model_providers/groq/llm/llama-3.1-8b-instant.yaml new file mode 100644 index 0000000000..a82e64532e --- /dev/null +++ b/api/core/model_runtime/model_providers/groq/llm/llama-3.1-8b-instant.yaml @@ -0,0 +1,25 @@ +model: llama-3.1-8b-instant +label: + zh_Hans: Llama-3.1-8b-instant + en_US: Llama-3.1-8b-instant +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: max_tokens + use_template: max_tokens + default: 512 + min: 1 + max: 8192 +pricing: + input: '0.05' + output: '0.1' + unit: '0.000001' + currency: USD