Skip to content

Meta Llama Models Added #159

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 11 commits into from
Aug 20, 2025
Merged

Meta Llama Models Added #159

Changes from all commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
6d2f0c2
add : LLAMA models added to the `LLMModel`.
sadrasabouri Aug 8, 2025
6f79ac0
update : new name structure added.
sadrasabouri Aug 11, 2025
c50dea9
fix : names fixed.
sadrasabouri Aug 11, 2025
971310b
fix : names fixed.
sadrasabouri Aug 11, 2025
1f3b278
update : `-` use changed to `.`
sadrasabouri Aug 11, 2025
279568c
update : vision and instruct models added.
sadrasabouri Aug 11, 2025
198a048
edit : META_LLAMAs converted to LLAMA.
sadrasabouri Aug 13, 2025
ddacce7
fix : `meta-*` --> `*`.
sadrasabouri Aug 13, 2025
c9a1378
fix : GEMM --> GEMMA.
sadrasabouri Aug 17, 2025
0437672
fix : requested changes applied.
sadrasabouri Aug 17, 2025
200fa71
remove : hallucinated model names removed.
sadrasabouri Aug 18, 2025
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
62 changes: 53 additions & 9 deletions memor/params.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -86,9 +86,53 @@ class LLMModel(Enum):
CLAUDE_2 = "claude-2"
CLAUDE_INSTANT = "claude-instant"

LLAMA3_70B = "llama3-70b"
LLAMA3_8B = "llama3-8b"
LLAMA_2_7B = "llama-2-7b"
LLAMA_2_13B = "llama-2-13b"
LLAMA_2_70B = "llama-2-70b"
LLAMA_3_8B = "llama-3-8b"
LLAMA_3_8B_INSTRUCT = "llama-3-8b-instruct"
LLAMA_3_70B = "llama-3-70b"
LLAMA_3_70B_INSTRUCT = "llama-3-70b-instruct"
LLAMA_3_1_8B = "llama-3.1-8b"
LLAMA_3_1_8B_INSTRUCT = "llama-3.1-8b-instruct"
LLAMA_3_1_70B = "llama-3.1-70b"
LLAMA_3_1_70B_INSTRUCT = "llama-3.1-70b-instruct"
LLAMA_3_1_405B = "llama-3.1-405b"
LLAMA_3_1_405B_INSTRUCT = "llama-3.1-405b-instruct"
LLAMA_3_2_1B = "llama-3.2-1b"
LLAMA_3_2_1B_INSTRUCT = "llama-3.2-1b-instruct"
LLAMA_3_2_3B = "llama-3.2-3b"
LLAMA_3_2_3B_INSTRUCT = "llama-3.2-3b-instruct"
LLAMA_3_2_11B_VISION = "llama-3.2-11b-vision"
LLAMA_3_2_11B_VISION_INSTRUCT = "llama-3.2-11b-vision-instruct"
LLAMA_3_2_90B_VISION = "llama-3.2-90b-vision"
LLAMA_3_2_90B_VISION_INSTRUCT = "llama-3.2-90b-vision-instruct"
LLAMA_3_3_70B_INSTRUCT = "llama-3.3-70b-instruct"
LLAMA_4_MAVERICK_17B_128E = "llama-4-maverick-17b-128e"
LLAMA_4_MAVERICK_17B_128E_INSTRUCT = "llama-4-maverick-17b-128e-instruct"
LLAMA_GUARD_7B = "llama-guard-7b"
LLAMA_GUARD_2_8B = "llama-guard-2-8b"
LLAMA_GUARD_3_1B = "llama-guard-3-1b"
LLAMA_GUARD_3_8B = "llama-guard-3-8b"
LLAMA_GUARD_3_11B_VISION = "llama-guard-3-11b-vision"
LLAMA_GUARD_4_12B = "llama-guard-4-12b"
LLAMA_PROMPT_GUARD_86M = "llama-prompt-guard-86m"
LLAMA_PROMPT_GUARD_2_22M = "llama-prompt-guard-2-22m"
LLAMA_PROMPT_GUARD_2_86M = "llama-prompt-guard-2-86m"
LLAMA_4_SCOUT_17B_16E = "llama-4-scout-17b-16e"
LLAMA_4_SCOUT_17B_16E_INSTRUCT = "llama-4-scout-17b-16e-instruct"
CODE_LLAMA_7B = "code-llama-7b"
CODE_LLAMA_7B_INSTRUCT = "code-llama-7b-instruct"
CODE_LLAMA_7B_PYTHON = "code-llama-7b-python"
CODE_LLAMA_13B = "code-llama-13b"
CODE_LLAMA_13B_INSTRUCT = "code-llama-13b-instruct"
CODE_LLAMA_13B_PYTHON = "code-llama-13b-python"
CODE_LLAMA_34B = "code-llama-34b"
CODE_LLAMA_34B_INSTRUCT = "code-llama-34b-instruct"
CODE_LLAMA_34B_PYTHON = "code-llama-34b-python"
CODE_LLAMA_70B = "code-llama-70b"
CODE_LLAMA_70B_INSTRUCT = "code-llama-70b-instruct"
CODE_LLAMA_70B_PYTHON = "code-llama-70b-python"

MISTRAL_7B = "mistral-7b"
MIXTRAL_8X7B = "mixtral-8x7b"
Expand All @@ -102,13 +146,13 @@ class LLMModel(Enum):
PIXTRAL = "pixtral-12b"

GEMMA_7B = "gemma-7b"
GEMMA2_9B = "gemma2-9b"
GEMMA3_1B = "gemma3-1b"
GEMMA3_4B = "gemma3-4b"
GEMMA3_12B = "gemma3-12b"
GEMMA3_27B = "gemma3-27b"
GEMMA3N_E2B = "gemma3n-e2b"
GEMMA3N_E4B = "gemma3n-e4b"
GEMMA_2_9B = "gemma-2-9b"
GEMMA_3_1B = "gemma-3-1b"
GEMMA_3_4B = "gemma-3-4b"
GEMMA_3_12B = "gemma-3-12b"
GEMMA_3_27B = "gemma-3-27b"
GEMMA_3N_E2B = "gemma-3n-e2b"
GEMMA_3N_E4B = "gemma-3n-e4b"
CODEGEMMA_2B = "codegemma-2b"
CODEGEMMA_7B = "codegemma-7b"
RECURRENTGEMMA_2B = "recurrentgemma-2b"
Expand Down