wehub/anomalyco--models.dev
1
0
Fork 0
Code Issues Pull Requests Actions Deployments Models Agent Notes Packages Projects Releases Wiki Activity

chore: import upstream snapshot with attribution

Browse Source
This commit is contained in:
wehub-resource-sync
2026-07-13 12:28:55 +08:00
commit db42b91b75
6397 changed files with 146012 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
models/meta/llama-3.3-70b-instruct.toml
+44
View File
@@ -0,0 +1,44 @@
name = "Llama-3.3-70B-Instruct"
description = "Popular open Llama workhorse for multilingual chat, coding, and self-hosting"
family = "llama"
release_date = "2024-12-06"
last_updated = "2024-12-06"
attachment = true
reasoning = false
temperature = true
tool_call = true
knowledge = "2023-12"
open_weights = true
[limit]
context = 128_000
output = 4_096
[modalities]
input = ["text"]
output = ["text"]
[[weights]]
label = "Hugging Face"
url = "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct"
[[benchmarks]]
name = "Artificial Analysis Coding Index"
score = 10.7
metric = "index"
source = "https://openrouter.ai/meta-llama/llama-3.3-70b-instruct/benchmarks"
date = "2026-03-11"
[[benchmarks]]
name = "SciCode"
score = 26
metric = "percent correct"
source = "https://openrouter.ai/meta-llama/llama-3.3-70b-instruct/benchmarks"
date = "2026-03-11"
[[benchmarks]]
name = "Terminal-Bench Hard"
score = 3
metric = "success rate"
source = "https://openrouter.ai/meta-llama/llama-3.3-70b-instruct/benchmarks"
date = "2026-03-11"
models/meta/llama-4-maverick-17b-instruct.toml
+37
View File
@@ -0,0 +1,37 @@
name = "Llama 4 Maverick 17B Instruct"
description = "Open multimodal Llama for strong reasoning with efficient everyday serving"
family = "llama"
release_date = "2025-04-05"
last_updated = "2025-04-05"
attachment = true
reasoning = false
temperature = true
tool_call = true
knowledge = "2024-08"
open_weights = true
[limit]
context = 1_000_000
output = 16_384
[modalities]
input = ["text", "image"]
output = ["text"]
[[weights]]
label = "Hugging Face"
url = "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct"
[[benchmarks]]
name = "Aider Polyglot"
score = 15.6
metric = "percent correct"
source = "https://aider.chat/docs/leaderboards/"
date = "2025-04-06"
[[benchmarks]]
name = "SWE-Bench Pro"
score = 5.24
metric = "resolve rate"
dataset = "public"
source = "https://labs.scale.com/leaderboard/swe_bench_pro_public"
models/meta/llama-4-scout-17b-instruct.toml
+23
View File
@@ -0,0 +1,23 @@
name = "Llama 4 Scout 17B Instruct"
description = "Open Llama with long-context vision for efficient multimodal agents"
family = "llama"
release_date = "2025-04-05"
last_updated = "2025-04-05"
attachment = true
reasoning = false
temperature = true
tool_call = true
knowledge = "2024-08"
open_weights = true
[limit]
context = 3_500_000
output = 16_384
[modalities]
input = ["text", "image"]
output = ["text"]
[[weights]]
label = "Hugging Face"
url = "https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct"
models/meta/muse-spark-1.1.toml
+100
View File
@@ -0,0 +1,100 @@
name = "Muse Spark 1.1"
description = "Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration."
family = "muse"
release_date = "2026-04-08"
last_updated = "2026-07-09"
attachment = true
reasoning = true
temperature = true
tool_call = true
structured_output = true
open_weights = false
[limit]
context = 1_000_000
output = 32_000
[modalities]
input = ["text", "image", "pdf", "video"]
output = ["text"]
[[benchmarks]]
name = "SWE-Bench Pro"
score = 61.5
metric = "resolve rate"
source = "https://ai.meta.com/blog/introducing-muse-spark-meta-model-api/"
date = "2026-07-09"
[[benchmarks]]
name = "Terminal-Bench"
score = 80.0
metric = "success rate"
version = "2.1"
source = "https://ai.meta.com/blog/introducing-muse-spark-meta-model-api/"
date = "2026-07-09"
[[benchmarks]]
name = "DeepSWE"
score = 53.3
metric = "resolve rate"
version = "1.1"
source = "https://ai.meta.com/blog/introducing-muse-spark-meta-model-api/"
date = "2026-07-09"
[[benchmarks]]
name = "MCP Atlas"
score = 88.1
metric = "success rate"
source = "https://ai.meta.com/blog/introducing-muse-spark-meta-model-api/"
date = "2026-07-09"
[[benchmarks]]
name = "JobBench"
score = 54.7
metric = "success rate"
source = "https://ai.meta.com/blog/introducing-muse-spark-meta-model-api/"
date = "2026-07-09"
[[benchmarks]]
name = "Toolathlon-Verified"
score = 75.6
metric = "success rate"
source = "https://ai.meta.com/blog/introducing-muse-spark-meta-model-api/"
date = "2026-07-09"
[[benchmarks]]
name = "Humanity's Last Exam"
score = 62.1
metric = "accuracy"
variant = "with tools"
source = "https://ai.meta.com/blog/introducing-muse-spark-meta-model-api/"
date = "2026-07-09"
[[benchmarks]]
name = "OSWorld-Verified"
score = 80.8
metric = "success rate"
source = "https://ai.meta.com/blog/introducing-muse-spark-meta-model-api/"
date = "2026-07-09"
[[benchmarks]]
name = "Finance Agent"
score = 57.2
metric = "accuracy"
version = "v2"
source = "https://ai.meta.com/blog/introducing-muse-spark-meta-model-api/"
date = "2026-07-09"
[[benchmarks]]
name = "CharXiv Reasoning"
score = 88.4
metric = "accuracy"
source = "https://ai.meta.com/blog/introducing-muse-spark-meta-model-api/"
date = "2026-07-09"
[[benchmarks]]
name = "BabyVision"
score = 76.3
metric = "accuracy"
source = "https://ai.meta.com/blog/introducing-muse-spark-meta-model-api/"
date = "2026-07-09"