Skip to content

feat: Added AIM support for Meta Llama3 models in AWS Bedrock #2306

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Jun 27, 2024
Merged

feat: Added AIM support for Meta Llama3 models in AWS Bedrock #2306

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
bda1373
feat: Added AIM support for Meta Llama3 models in AWS Bedrock
amychisholm03 Jun 26, 2024
fcefe6e
test: consolidate llama2 and llama3 for some tests
amychisholm03 Jun 27, 2024
bfe2286
chore: updated ai support page for llama3
amychisholm03 Jun 27, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
test: consolidate llama2 and llama3 for some tests
  • Loading branch information
@amychisholm03
amychisholm03 committed Jun 27, 2024
commit fcefe6eea7d9a3f1b745a8ec231190965ad1bb1c
9 changes: 3 additions & 6 deletions test/lib/aws-server-stubs/ai-server/index.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -114,14 +114,11 @@ function handler(req, res) {
}

case 'meta.llama2-13b-chat-v1':
case 'meta.llama2-70b-chat-v1': {
response = responses.llama2.get(payload.prompt)
break
}

case 'meta.llama2-70b-chat-v1':
// llama3 responses are indentical, just return llama2 data
case 'meta.llama3-8b-instruct-v1:0':
case 'meta.llama3-70b-instruct-v1:0': {
response = responses.llama3.get(payload.prompt)
response = responses.llama.get(payload.prompt)
break
}

Expand Down
6 changes: 2 additions & 4 deletions test/lib/aws-server-stubs/ai-server/responses/index.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,15 +10,13 @@ const amazon = require('./amazon')
const claude = require('./claude')
const claude3 = require('./claude3')
const cohere = require('./cohere')
const llama2 = require('./llama2')
const llama3 = require('./llama3')
const llama = require('./llama')

module.exports = {
ai21,
amazon,
claude,
claude3,
cohere,
llama2,
llama3
llama
}
6 changes: 3 additions & 3 deletions ...erver-stubs/ai-server/responses/llama2.js → ...server-stubs/ai-server/responses/llama.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@
const responses = new Map()
const { contentType, reqId } = require('./constants')

responses.set('text llama2 ultimate question', {
responses.set('text llama ultimate question', {
headers: {
'content-type': contentType,
'x-amzn-requestid': reqId,
Expand All @@ -25,7 +25,7 @@ responses.set('text llama2 ultimate question', {
}
})

responses.set('text llama2 ultimate question streamed', {
responses.set('text llama ultimate question streamed', {
headers: {
'content-type': 'application/vnd.amazon.eventstream',
'x-amzn-requestid': reqId,
Expand Down Expand Up @@ -68,7 +68,7 @@ responses.set('text llama2 ultimate question streamed', {
]
})

responses.set('text llama2 ultimate question error', {
responses.set('text llama ultimate question error', {
headers: {
'content-type': contentType,
'x-amzn-requestid': reqId,
Expand Down
84 changes: 0 additions & 84 deletions test/lib/aws-server-stubs/ai-server/responses/llama3.js
View file
Open in desktop

This file was deleted.

10 changes: 3 additions & 7 deletions test/versioned/aws-sdk-v3/bedrock-chat-completions.tap.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,11 +48,7 @@ const requests = {
body: JSON.stringify({ prompt, temperature: 0.5, max_tokens: 100 }),
modelId
}),
llama2: (prompt, modelId) => ({
body: JSON.stringify({ prompt, max_gen_length: 100, temperature: 0.5 }),
modelId
}),
llama3: (prompt, modelId) => ({
llama: (prompt, modelId) => ({
body: JSON.stringify({ prompt, max_gen_length: 100, temperature: 0.5 }),
modelId
})
Expand Down Expand Up @@ -102,8 +98,8 @@ tap.afterEach(async (t) => {
{ modelId: 'anthropic.claude-v2', resKey: 'claude' },
{ modelId: 'anthropic.claude-3-haiku-20240307-v1:0', resKey: 'claude3' },
{ modelId: 'cohere.command-text-v14', resKey: 'cohere' },
{ modelId: 'meta.llama2-13b-chat-v1', resKey: 'llama2' },
{ modelId: 'meta.llama3-8b-instruct-v1:0', resKey: 'llama3' }
{ modelId: 'meta.llama2-13b-chat-v1', resKey: 'llama' },
{ modelId: 'meta.llama3-8b-instruct-v1:0', resKey: 'llama' }
].forEach(({ modelId, resKey }) => {
tap.test(`${modelId}: should properly create completion segment`, (t) => {
const { bedrock, client, responses, agent, expectedExternalPath } = t.context
Expand Down