Skip to content
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

Fix: Failing LLM tests #551

Merged
merged 2 commits into from
Sep 26, 2024
Merged

Fix: Failing LLM tests #551

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e57e962
Fix: Failing tests on `OpenAIModel`
RafaelJohn9 Sep 26, 2024
8bf3413
Fix: Perplexity and DeepInfra model
RafaelJohn9 Sep 26, 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
101 changes: 51 additions & 50 deletions pkgs/swarmauri/swarmauri/llms/concrete/DeepInfraModel.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,56 +15,57 @@ class DeepInfraModel(LLMBase):
"""

api_key: str
allowed_models: List[str] = ['01-ai/Yi-34B-Chat',
'Austism/chronos-hermes-13b-v2',
'Gryphe/MythoMax-L2-13b',
'Gryphe/MythoMax-L2-13b-turbo',
'HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1',
'Phind/Phind-CodeLlama-34B-v2',
'Qwen/Qwen2-72B-Instruct',
'Qwen/Qwen2-7B-Instruct',
'Qwen/Qwen2.5-72B-Instruct',
'Sao10K/L3-70B-Euryale-v2.1',
'Sao10K/L3.1-70B-Euryale-v2.2',
'bigcode/starcoder2-15b',
'bigcode/starcoder2-15b-instruct-v0.1',
'codellama/CodeLlama-34b-Instruct-hf',
'codellama/CodeLlama-70b-Instruct-hf',
'cognitivecomputations/dolphin-2.6-mixtral-8x7b',
'cognitivecomputations/dolphin-2.9.1-llama-3-70b',
'databricks/dbrx-instruct',
'deepinfra/airoboros-70b',
'google/codegemma-7b-it',
'google/gemma-1.1-7b-it',
'google/gemma-2-27b-it',
'google/gemma-2-9b-it',
'lizpreciatior/lzlv_70b_fp16_hf',
'mattshumer/Reflection-Llama-3.1-70B',
'mattshumer/Reflection-Llama-3.1-70B',
'meta-llama/Llama-2-13b-chat-hf',
'meta-llama/Llama-2-70b-chat-hf',
'meta-llama/Llama-2-7b-chat-hf',
'meta-llama/Meta-Llama-3-70B-Instruct',
'meta-llama/Meta-Llama-3-8B-Instruct',
'meta-llama/Meta-Llama-3.1-405B-Instruct',
'meta-llama/Meta-Llama-3.1-70B-Instruct',
'meta-llama/Meta-Llama-3.1-8B-Instruct',
'microsoft/Phi-3-medium-4k-instruct',
'microsoft/WizardLM-2-7B',
'microsoft/WizardLM-2-8x22B',
'mistralai/Mistral-7B-Instruct-v0.1',
'mistralai/Mistral-7B-Instruct-v0.2',
'mistralai/Mistral-7B-Instruct-v0.3',
'mistralai/Mistral-Nemo-Instruct-2407',
'mistralai/Mixtral-8x22B-Instruct-v0.1',
'mistralai/Mixtral-8x22B-v0.1',
'mistralai/Mixtral-8x22B-v0.1',
'mistralai/Mixtral-8x7B-Instruct-v0.1',
'nvidia/Nemotron-4-340B-Instruct',
'openbmb/MiniCPM-Llama3-V-2_5',
'openchat/openchat-3.6-8b',
'openchat/openchat_3.5'
]
allowed_models: List[str] = [
"01-ai/Yi-34B-Chat",
"Gryphe/MythoMax-L2-13b", # not consistent with results
"HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1",
"Phind/Phind-CodeLlama-34B-v2",
"Qwen/Qwen2-72B-Instruct",
"Qwen/Qwen2-7B-Instruct",
"Qwen/Qwen2.5-72B-Instruct",
"Sao10K/L3-70B-Euryale-v2.1",
"Sao10K/L3.1-70B-Euryale-v2.2",
"bigcode/starcoder2-15b",
"bigcode/starcoder2-15b-instruct-v0.1",
"codellama/CodeLlama-34b-Instruct-hf",
"codellama/CodeLlama-70b-Instruct-hf",
"cognitivecomputations/dolphin-2.6-mixtral-8x7b",
"cognitivecomputations/dolphin-2.9.1-llama-3-70b",
"databricks/dbrx-instruct",
"google/codegemma-7b-it",
"google/gemma-1.1-7b-it",
"google/gemma-2-27b-it",
"google/gemma-2-9b-it",
"lizpreciatior/lzlv_70b_fp16_hf", # not consistent with results
"mattshumer/Reflection-Llama-3.1-70B",
"mattshumer/Reflection-Llama-3.1-70B",
"meta-llama/Llama-2-13b-chat-hf",
"meta-llama/Llama-2-70b-chat-hf",
"meta-llama/Llama-2-7b-chat-hf",
"meta-llama/Meta-Llama-3-70B-Instruct",
"meta-llama/Meta-Llama-3-8B-Instruct",
"meta-llama/Meta-Llama-3.1-405B-Instruct",
"meta-llama/Meta-Llama-3.1-70B-Instruct",
"meta-llama/Meta-Llama-3.1-8B-Instruct",
"microsoft/Phi-3-medium-4k-instruct",
"microsoft/WizardLM-2-7B",
"microsoft/WizardLM-2-8x22B",
"mistralai/Mistral-7B-Instruct-v0.1",
"mistralai/Mistral-7B-Instruct-v0.2",
"mistralai/Mistral-7B-Instruct-v0.3",
"mistralai/Mistral-Nemo-Instruct-2407",
"mistralai/Mixtral-8x22B-Instruct-v0.1",
"mistralai/Mixtral-8x22B-v0.1",
"mistralai/Mixtral-8x22B-v0.1",
"mistralai/Mixtral-8x7B-Instruct-v0.1",
"nvidia/Nemotron-4-340B-Instruct",
"openbmb/MiniCPM-Llama3-V-2_5",
"openchat/openchat-3.6-8b",
"openchat/openchat_3.5", # not compliant with system context
# "deepinfra/airoboros-70b", # deprecated: https://deepinfra.com/deepinfra/airoboros-70b
# 'Gryphe/MythoMax-L2-13b-turbo', # deprecated: https://deepinfra.com/Gryphe/MythoMax-L2-13b-turbo/api
# "Austism/chronos-hermes-13b-v2", # deprecating: https://deepinfra.com/Austism/chronos-hermes-13b-v2/api
]

name: str = "Qwen/Qwen2-72B-Instruct"
type: Literal["DeepInfraModel"] = "DeepInfraModel"
Expand Down
17 changes: 10 additions & 7 deletions pkgs/swarmauri/swarmauri/llms/concrete/OpenAIModel.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,19 +24,19 @@ class OpenAIModel(LLMBase):
"gpt-3.5-turbo",
"gpt-4o-mini",
"chatgpt-4o-latest",
"gpt-3.5-turbo-instruct",
"o1-preview",
"o1-mini",
"gpt-4o-2024-05-13",
"gpt-4o-2024-08-06",
"gpt-4o-mini-2024-07-18",
"o1-preview-2024-09-12",
"o1-mini-2024-09-12",
"gpt-4-turbo-2024-04-09",
"gpt-4-0125-preview",
"gpt-4-0613",
"gpt-4-0314",
"gpt-3.5-turbo-0125",
# "gpt-3.5-turbo-instruct", # gpt-3.5-turbo-instruct does not support v1/chat/completions endpoint. only supports (/v1/completions)
# "o1-preview", # Does not support max_tokens and temperature
# "o1-mini", # Does not support max_tokens and temperature
# "o1-preview-2024-09-12", # Does not support max_tokens and temperature
# "o1-mini-2024-09-12", # Does not support max_tokens and temperature
# "gpt-4-0314", # it's deprecated
]
name: str = "gpt-3.5-turbo"
type: Literal["OpenAIModel"] = "OpenAIModel"
Expand All @@ -57,7 +57,7 @@ def predict(
temperature=0.7,
max_tokens=256,
enable_json=False,
stop: List[str] = None,
stop: List[str] = ["\n"],
):
"""
Generate predictions using the OpenAI model.
Expand All @@ -67,6 +67,9 @@ def predict(
- temperature (float): Sampling temperature.
- max_tokens (int): Maximum number of tokens to generate.
- enable_json (bool): Format response as JSON.
- stop (List[str]): List of tokens at which to stop generation.
being None causes some models to throw status 400
(*chatgpt-4o-latest*)

Returns:
- The generated message content.
Expand Down
15 changes: 8 additions & 7 deletions pkgs/swarmauri/swarmauri/llms/concrete/PerplexityModel.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,19 +16,20 @@ class PerplexityModel(LLMBase):

api_key: str
allowed_models: List[str] = [
"llama-3-sonar-small-32k-chat",
"llama-3-sonar-small-32k-online",
"llama-3-sonar-large-32k-chat",
"llama-3-sonar-large-32k-online",
"llama-3-8b-instruct",
"llama-3-70b-instruct",
"llama-3.1-70b-instruct",
"llama-3.1-sonar-small-128k-online",
"llama-3.1-sonar-large-128k-online",
"llama-3.1-sonar-huge-128k-online",
"llama-3.1-sonar-small-128k-chat",
"llama-3.1-sonar-large-128k-chat",
"llama-3.1-8b-instruct",
"llama-3.1-70b-instruct",
# deprecated: https://docs.perplexity.ai/changelog/changelog#introducing-new-and-improved-sonar-models
# "llama-3-sonar-small-32k-chat",
# "llama-3-sonar-small-32k-online",
# "llama-3-sonar-large-32k-chat",
# "llama-3-sonar-large-32k-online",
# "llama-3-8b-instruct",
# "llama-3-70b-instruct",
]
name: str = "llama-3.1-70b-instruct"
type: Literal["PerplexityModel"] = "PerplexityModel"
Expand Down
Loading