From 49bcac6090644f7fc013339c52270fef4ce4cc4f Mon Sep 17 00:00:00 2001 From: jmansdorfer Date: Mon, 22 Apr 2024 12:39:44 -0400 Subject: [PATCH 1/6] adding llama3 to model docs --- fern/docs/pages/models/details.mdx | 1 + fern/docs/pages/models/prompts.mdx | 10 ++++++++++ 2 files changed, 11 insertions(+) diff --git a/fern/docs/pages/models/details.mdx b/fern/docs/pages/models/details.mdx index 115b366..74e47b3 100644 --- a/fern/docs/pages/models/details.mdx +++ b/fern/docs/pages/models/details.mdx @@ -26,6 +26,7 @@ Open access models are amazing these days! Each of these models was trained by a | Yi-34B-Chat | Chat | Instruction following in English or Chinese | [ChatML](prompts#chatml) | 2048 | [link](https://huggingface.co/01-ai/Yi-34B-Chat) | | deepseek-coder-6.7b-instruct | Code Generation | Generating computer code or answering tech questions | [Deepseek](prompts#deepseek) | 4096 | [link](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct) | | sqlcoder-7b-2 | Code Generation | Generating SQL queries from natural language prompts | [SQLCoder](prompts#sqlcoder) | 4096 | [link](https://huggingface.co/defog/sqlcoder-7b-2) | +| Meta-Llama-3- 8B-Instruct | Text Generation | Generating output in response to arbitrary instructions | [Llama3](prompts#llama3) | 4096 | [link](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) | ### Other models available diff --git a/fern/docs/pages/models/prompts.mdx b/fern/docs/pages/models/prompts.mdx index d5565fb..0bf7d10 100644 --- a/fern/docs/pages/models/prompts.mdx +++ b/fern/docs/pages/models/prompts.mdx @@ -98,3 +98,13 @@ Given the database schema, here is the SQL query that [QUESTION]{user_question}[ {context or user message} ### Response: ``` + +## Llama3 + +(Replace the portions of the prompt below in the parentheses `(...)` with the appropriate information, and do not keep the parentheses) + +``` +<|begin_of_text|><|start_header_id|>system<|end_header_id|> +{{ (system prompt) }}<|eot_id|><|start_header_id|>user<|end_header_id|> +{{ (context or user message) }}<|eot_id|><|start_header_id|>assistant<|end_header_id|> +``` \ No newline at end of file From 11b3a595028984857aaef20cc2c156f60f262c21 Mon Sep 17 00:00:00 2001 From: jmansdorfer Date: Mon, 22 Apr 2024 13:34:27 -0400 Subject: [PATCH 2/6] fixing prompt format --- fern/docs/pages/models/prompts.mdx | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/fern/docs/pages/models/prompts.mdx b/fern/docs/pages/models/prompts.mdx index 0bf7d10..673ffc0 100644 --- a/fern/docs/pages/models/prompts.mdx +++ b/fern/docs/pages/models/prompts.mdx @@ -101,10 +101,10 @@ Given the database schema, here is the SQL query that [QUESTION]{user_question}[ ## Llama3 -(Replace the portions of the prompt below in the parentheses `(...)` with the appropriate information, and do not keep the parentheses) +(Replace the portions of the prompt below in curly braces `{...}` with the appropriate information, and do not keep the curly braces) ``` <|begin_of_text|><|start_header_id|>system<|end_header_id|> -{{ (system prompt) }}<|eot_id|><|start_header_id|>user<|end_header_id|> -{{ (context or user message) }}<|eot_id|><|start_header_id|>assistant<|end_header_id|> +{system prompt}<|eot_id|><|start_header_id|>user<|end_header_id|> +{context or user message}<|eot_id|><|start_header_id|>assistant<|end_header_id|> ``` \ No newline at end of file From 5072f9fe587ec27facbfd66bde9151fc9fb08a3e Mon Sep 17 00:00:00 2001 From: jmansdorfer Date: Mon, 22 Apr 2024 14:42:39 -0400 Subject: [PATCH 3/6] removing sqlcoder from model and prompt lists --- fern/docs/pages/models/details.mdx | 1 - fern/docs/pages/models/prompts.mdx | 17 ----------------- 2 files changed, 18 deletions(-) diff --git a/fern/docs/pages/models/details.mdx b/fern/docs/pages/models/details.mdx index 74e47b3..8e3ccc3 100644 --- a/fern/docs/pages/models/details.mdx +++ b/fern/docs/pages/models/details.mdx @@ -25,7 +25,6 @@ Open access models are amazing these days! Each of these models was trained by a | Neural-Chat-7B | Chat | Instruction following or chat-like applications | [Neural Chat](prompts#neural-chat) | 4096 | [link](https://huggingface.co/Intel/neural-chat-7b-v3-1) | | Yi-34B-Chat | Chat | Instruction following in English or Chinese | [ChatML](prompts#chatml) | 2048 | [link](https://huggingface.co/01-ai/Yi-34B-Chat) | | deepseek-coder-6.7b-instruct | Code Generation | Generating computer code or answering tech questions | [Deepseek](prompts#deepseek) | 4096 | [link](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct) | -| sqlcoder-7b-2 | Code Generation | Generating SQL queries from natural language prompts | [SQLCoder](prompts#sqlcoder) | 4096 | [link](https://huggingface.co/defog/sqlcoder-7b-2) | | Meta-Llama-3- 8B-Instruct | Text Generation | Generating output in response to arbitrary instructions | [Llama3](prompts#llama3) | 4096 | [link](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) | ### Other models available diff --git a/fern/docs/pages/models/prompts.mdx b/fern/docs/pages/models/prompts.mdx index 673ffc0..12e7e0e 100644 --- a/fern/docs/pages/models/prompts.mdx +++ b/fern/docs/pages/models/prompts.mdx @@ -71,23 +71,6 @@ For prompts where context is injected: <|im_start|>assistant<|im_end|> ``` -## SQLCoder - -(Replace the portions of the prompt below in curly braces `{...}` with the appropriate information, and do not keep the curly braces) - -``` -### Task -Generate a SQL query to answer [QUESTION]{user_question}[/QUESTION] - -### Database Schema -The query will run on a database with the following schema: -{table_metadata_string_DDL_statements} - -### Answer -Given the database schema, here is the SQL query that [QUESTION]{user_question}[/QUESTION] -[SQL] -``` - ## Deepseek (Replace the portions of the prompt below in curly braces `{...}` with the appropriate information, and do not keep the curly braces) From e211ee1e9350454fcb09881483316e2c579e66c6 Mon Sep 17 00:00:00 2001 From: jmansdorfer Date: Mon, 22 Apr 2024 16:06:13 -0400 Subject: [PATCH 4/6] fixing random extra whitespace in llama3 model name --- fern/docs/pages/models/details.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fern/docs/pages/models/details.mdx b/fern/docs/pages/models/details.mdx index 8e3ccc3..aa09ef6 100644 --- a/fern/docs/pages/models/details.mdx +++ b/fern/docs/pages/models/details.mdx @@ -25,7 +25,7 @@ Open access models are amazing these days! Each of these models was trained by a | Neural-Chat-7B | Chat | Instruction following or chat-like applications | [Neural Chat](prompts#neural-chat) | 4096 | [link](https://huggingface.co/Intel/neural-chat-7b-v3-1) | | Yi-34B-Chat | Chat | Instruction following in English or Chinese | [ChatML](prompts#chatml) | 2048 | [link](https://huggingface.co/01-ai/Yi-34B-Chat) | | deepseek-coder-6.7b-instruct | Code Generation | Generating computer code or answering tech questions | [Deepseek](prompts#deepseek) | 4096 | [link](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct) | -| Meta-Llama-3- 8B-Instruct | Text Generation | Generating output in response to arbitrary instructions | [Llama3](prompts#llama3) | 4096 | [link](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) | +| Meta-Llama-3-8B-Instruct | Text Generation | Generating output in response to arbitrary instructions | [Llama3](prompts#llama3) | 4096 | [link](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) | ### Other models available From f88395660fefee4f3d6651d65249c74d026d1bd7 Mon Sep 17 00:00:00 2001 From: jmansdorfer Date: Mon, 22 Apr 2024 16:31:25 -0400 Subject: [PATCH 5/6] moving llama3 listing to top of model list --- fern/docs/pages/models/details.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fern/docs/pages/models/details.mdx b/fern/docs/pages/models/details.mdx index aa09ef6..89308f7 100644 --- a/fern/docs/pages/models/details.mdx +++ b/fern/docs/pages/models/details.mdx @@ -20,12 +20,12 @@ Open access models are amazing these days! Each of these models was trained by a | Model Name | Type | Use Case | Prompt Format | Context Length | More Info | | ---------------------------- | --------------- | ------------------------------------------------------- | ---------------------------------- | -------------- | ----------------------------------------------------------------------- | +| Meta-Llama-3-8B-Instruct | Text Generation | Generating output in response to arbitrary instructions | [Llama3](prompts#llama3) | 4096 | [link](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) | | Nous-Hermes-Llama2-13B | Text Generation | Generating output in response to arbitrary instructions | [Alpaca](prompts#alpaca) | 4096 | [link](https://huggingface.co/NousResearch/Nous-Hermes-Llama2-13b) | | Hermes-2-Pro-Mistral-7B | Chat | Instruction following or chat-like applications | [ChatML](prompts#chatml) | 4096 | [link](https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B) | | Neural-Chat-7B | Chat | Instruction following or chat-like applications | [Neural Chat](prompts#neural-chat) | 4096 | [link](https://huggingface.co/Intel/neural-chat-7b-v3-1) | | Yi-34B-Chat | Chat | Instruction following in English or Chinese | [ChatML](prompts#chatml) | 2048 | [link](https://huggingface.co/01-ai/Yi-34B-Chat) | | deepseek-coder-6.7b-instruct | Code Generation | Generating computer code or answering tech questions | [Deepseek](prompts#deepseek) | 4096 | [link](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct) | -| Meta-Llama-3-8B-Instruct | Text Generation | Generating output in response to arbitrary instructions | [Llama3](prompts#llama3) | 4096 | [link](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) | ### Other models available From 2710a01f2d87f15da67f9f4682aac1ad4b3b5364 Mon Sep 17 00:00:00 2001 From: jmansdorfer Date: Mon, 22 Apr 2024 16:34:55 -0400 Subject: [PATCH 6/6] changing llama3 model type --- fern/docs/pages/models/details.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fern/docs/pages/models/details.mdx b/fern/docs/pages/models/details.mdx index 89308f7..d12c8d7 100644 --- a/fern/docs/pages/models/details.mdx +++ b/fern/docs/pages/models/details.mdx @@ -20,7 +20,7 @@ Open access models are amazing these days! Each of these models was trained by a | Model Name | Type | Use Case | Prompt Format | Context Length | More Info | | ---------------------------- | --------------- | ------------------------------------------------------- | ---------------------------------- | -------------- | ----------------------------------------------------------------------- | -| Meta-Llama-3-8B-Instruct | Text Generation | Generating output in response to arbitrary instructions | [Llama3](prompts#llama3) | 4096 | [link](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) | +| Meta-Llama-3-8B-Instruct | Chat | Instruction following or chat-like applications | [Llama3](prompts#llama3) | 4096 | [link](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) | | Nous-Hermes-Llama2-13B | Text Generation | Generating output in response to arbitrary instructions | [Alpaca](prompts#alpaca) | 4096 | [link](https://huggingface.co/NousResearch/Nous-Hermes-Llama2-13b) | | Hermes-2-Pro-Mistral-7B | Chat | Instruction following or chat-like applications | [ChatML](prompts#chatml) | 4096 | [link](https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B) | | Neural-Chat-7B | Chat | Instruction following or chat-like applications | [Neural Chat](prompts#neural-chat) | 4096 | [link](https://huggingface.co/Intel/neural-chat-7b-v3-1) |