From 6478aa1c9d78f2f051baaf64323319cd72d56859 Mon Sep 17 00:00:00 2001 From: Alok Shrivastwa Date: Thu, 12 Dec 2024 11:41:30 +0530 Subject: [PATCH] Added new models and Removed the deleted ones for Groq #11455 (#11456) Co-authored-by: crazywoola <427733928@qq.com> Co-authored-by: Alok Shrivastwa --- .../model_providers/groq/llm/_position.yaml | 1 + .../model_providers/groq/llm/gemma-7b-it.yaml | 25 +++++++++++++++++++ .../groq/llm/gemma2-9b-it.yaml | 25 +++++++++++++++++++ .../groq/llm/llama-3.1-70b-versatile.yaml | 5 ++-- .../groq/llm/llama-3.2-11b-text-preview.yaml | 1 + .../groq/llm/llama-3.2-90b-text-preview.yaml | 1 + .../groq/llm/llama-3.3-70b-specdec\t.yaml" | 25 +++++++++++++++++++ ...llama3-groq-70b-8192-tool-use-preview.yaml | 25 +++++++++++++++++++ 8 files changed, 106 insertions(+), 2 deletions(-) create mode 100644 api/core/model_runtime/model_providers/groq/llm/gemma-7b-it.yaml create mode 100644 api/core/model_runtime/model_providers/groq/llm/gemma2-9b-it.yaml create mode 100644 "api/core/model_runtime/model_providers/groq/llm/llama-3.3-70b-specdec\t.yaml" create mode 100644 api/core/model_runtime/model_providers/groq/llm/llama3-groq-70b-8192-tool-use-preview.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 index 0613b19f87..279c1bcbe5 100644 --- a/api/core/model_runtime/model_providers/groq/llm/_position.yaml +++ b/api/core/model_runtime/model_providers/groq/llm/_position.yaml @@ -1,4 +1,5 @@ - llama-3.1-405b-reasoning +- llama-3.3-70b-versatile - llama-3.1-70b-versatile - llama-3.1-8b-instant - llama3-70b-8192 diff --git a/api/core/model_runtime/model_providers/groq/llm/gemma-7b-it.yaml b/api/core/model_runtime/model_providers/groq/llm/gemma-7b-it.yaml new file mode 100644 index 0000000000..02f84e95f6 --- /dev/null +++ b/api/core/model_runtime/model_providers/groq/llm/gemma-7b-it.yaml @@ -0,0 +1,25 @@ +model: gemma-7b-it +label: + zh_Hans: Gemma 7B Instruction Tuned + en_US: Gemma 7B Instruction Tuned +model_type: llm +features: + - agent-thought +model_properties: + mode: chat + context_size: 8192 +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/gemma2-9b-it.yaml b/api/core/model_runtime/model_providers/groq/llm/gemma2-9b-it.yaml new file mode 100644 index 0000000000..dad496f668 --- /dev/null +++ b/api/core/model_runtime/model_providers/groq/llm/gemma2-9b-it.yaml @@ -0,0 +1,25 @@ +model: gemma2-9b-it +label: + zh_Hans: Gemma 2 9B Instruction Tuned + en_US: Gemma 2 9B Instruction Tuned +model_type: llm +features: + - agent-thought +model_properties: + mode: chat + context_size: 8192 +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 index ab5f6ab05e..01323a1b8a 100644 --- 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 @@ -1,7 +1,8 @@ model: llama-3.1-70b-versatile +deprecated: true label: - zh_Hans: Llama-3.1-70b-versatile - en_US: Llama-3.1-70b-versatile + zh_Hans: Llama-3.1-70b-versatile (DEPRECATED) + en_US: Llama-3.1-70b-versatile (DEPRECATED) model_type: llm features: - agent-thought diff --git a/api/core/model_runtime/model_providers/groq/llm/llama-3.2-11b-text-preview.yaml b/api/core/model_runtime/model_providers/groq/llm/llama-3.2-11b-text-preview.yaml index 019d453723..3f30d81ae4 100644 --- a/api/core/model_runtime/model_providers/groq/llm/llama-3.2-11b-text-preview.yaml +++ b/api/core/model_runtime/model_providers/groq/llm/llama-3.2-11b-text-preview.yaml @@ -1,4 +1,5 @@ model: llama-3.2-11b-text-preview +deprecated: true label: zh_Hans: Llama 3.2 11B Text (Preview) en_US: Llama 3.2 11B Text (Preview) diff --git a/api/core/model_runtime/model_providers/groq/llm/llama-3.2-90b-text-preview.yaml b/api/core/model_runtime/model_providers/groq/llm/llama-3.2-90b-text-preview.yaml index 3b34e7c079..0391a7c890 100644 --- a/api/core/model_runtime/model_providers/groq/llm/llama-3.2-90b-text-preview.yaml +++ b/api/core/model_runtime/model_providers/groq/llm/llama-3.2-90b-text-preview.yaml @@ -1,4 +1,5 @@ model: llama-3.2-90b-text-preview +depraceted: true label: zh_Hans: Llama 3.2 90B Text (Preview) en_US: Llama 3.2 90B Text (Preview) diff --git "a/api/core/model_runtime/model_providers/groq/llm/llama-3.3-70b-specdec\t.yaml" "b/api/core/model_runtime/model_providers/groq/llm/llama-3.3-70b-specdec\t.yaml" new file mode 100644 index 0000000000..ac6d529c34 --- /dev/null +++ "b/api/core/model_runtime/model_providers/groq/llm/llama-3.3-70b-specdec\t.yaml" @@ -0,0 +1,25 @@ +model: llama-3.3-70b-specdec +label: + zh_Hans: Llama 3.3 70b Speculative Decoding (PREVIEW) + en_US: Llama 3.3 70b Speculative Decoding (PREVIEW) +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 \ No newline at end of file diff --git a/api/core/model_runtime/model_providers/groq/llm/llama3-groq-70b-8192-tool-use-preview.yaml b/api/core/model_runtime/model_providers/groq/llm/llama3-groq-70b-8192-tool-use-preview.yaml new file mode 100644 index 0000000000..32ccbf1f4d --- /dev/null +++ b/api/core/model_runtime/model_providers/groq/llm/llama3-groq-70b-8192-tool-use-preview.yaml @@ -0,0 +1,25 @@ +model: llama3-groq-70b-8192-tool-use-preview +label: + zh_Hans: Llama3-groq-70b-8192-tool-use (PREVIEW) + en_US: Llama3-groq-70b-8192-tool-use (PREVIEW) +model_type: llm +features: + - agent-thought +model_properties: + mode: chat + context_size: 8192 +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: '0.08' + unit: '0.000001' + currency: USD