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/nvidia/llama-3.1-nemotron-70b-instruct.toml
+18
View File
@@ -0,0 +1,18 @@
name = "Llama 3.1 Nemotron 70B Instruct"
description = "Nemotron model for efficient reasoning, coding, and specialized AI agents"
family = "nemotron"
release_date = "2025-04-15"
last_updated = "2025-04-15"
attachment = false
reasoning = false
temperature = true
tool_call = true
open_weights = true
[limit]
context = 128_000
output = 8_192
[modalities]
input = ["text"]
output = ["text"]
models/nvidia/llama-3.1-nemotron-safety-guard-8b-v3.toml
+18
View File
@@ -0,0 +1,18 @@
name = "Llama 3.1 Nemotron Safety Guard 8B v3"
description = "Safety model for policy screening, moderation, and risk-aware routing workflows"
family = "nemotron"
release_date = "2025-10-28"
last_updated = "2025-10-28"
attachment = false
reasoning = false
temperature = false
tool_call = false
open_weights = true
[limit]
context = 128_000
output = 4_096
[modalities]
input = ["text"]
output = ["text"]
models/nvidia/llama-3.1-nemotron-ultra-253b.toml
+18
View File
@@ -0,0 +1,18 @@
name = "Llama 3.1 Nemotron Ultra 253B"
description = "Flagship Nemotron model for high-throughput reasoning and complex agents"
family = "nemotron"
release_date = "2025-04-07"
last_updated = "2025-04-07"
attachment = false
reasoning = true
temperature = true
tool_call = true
open_weights = true
[limit]
context = 128_000
output = 8_192
[modalities]
input = ["text"]
output = ["text"]
models/nvidia/llama-3.3-nemotron-super-49b-v1.5.toml
+18
View File
@@ -0,0 +1,18 @@
name = "Llama 3.3 Nemotron Super 49B v1.5"
description = "Nemotron model for efficient reasoning, coding, and specialized AI agents"
family = "nemotron"
release_date = "2025-07-25"
last_updated = "2025-07-25"
attachment = false
reasoning = true
temperature = true
tool_call = true
open_weights = true
[limit]
context = 131_072
output = 131_072
[modalities]
input = ["text"]
output = ["text"]
models/nvidia/llama-3.3-nemotron-super-49b-v1.toml
+18
View File
@@ -0,0 +1,18 @@
name = "Llama 3.3 Nemotron Super 49B v1"
description = "Nemotron model for efficient reasoning, coding, and specialized AI agents"
family = "nemotron"
release_date = "2025-04-07"
last_updated = "2025-04-07"
attachment = false
reasoning = true
temperature = true
tool_call = true
open_weights = true
[limit]
context = 131_072
output = 131_072
[modalities]
input = ["text"]
output = ["text"]
models/nvidia/llama-nemotron-embed-vl-1b-v2.toml
+18
View File
@@ -0,0 +1,18 @@
name = "Llama Nemotron Embed VL 1B v2"
description = "Embedding model for semantic search, retrieval, clustering, and ranking pipelines"
family = "nemotron"
release_date = "2026-02-10"
last_updated = "2026-02-10"
attachment = true
reasoning = false
temperature = false
tool_call = false
open_weights = true
[limit]
context = 32_768
output = 2_048
[modalities]
input = ["text", "image"]
output = ["text"]
models/nvidia/llama-nemotron-rerank-vl-1b-v2.toml
+18
View File
@@ -0,0 +1,18 @@
name = "Llama Nemotron Rerank VL 1B v2"
description = "Reranking model for improving retrieval quality in search and recommendation systems"
family = "nemotron"
release_date = "2026-03-31"
last_updated = "2026-03-31"
attachment = true
reasoning = false
temperature = false
tool_call = false
open_weights = true
[limit]
context = 128_000
output = 4_096
[modalities]
input = ["text", "image"]
output = ["text"]
models/nvidia/mistral-nemotron.toml
+18
View File
@@ -0,0 +1,18 @@
name = "Mistral Nemotron"
description = "Mistral model for multilingual chat, reasoning, and tool-assisted workflows"
family = "nemotron"
release_date = "2025-06-11"
last_updated = "2025-06-12"
attachment = false
reasoning = false
temperature = true
tool_call = true
open_weights = true
[limit]
context = 128_000
output = 8_192
[modalities]
input = ["text"]
output = ["text"]
models/nvidia/nemotron-3-content-safety.toml
+18
View File
@@ -0,0 +1,18 @@
name = "Nemotron 3 Content Safety"
description = "Safety model for policy screening, moderation, and risk-aware routing workflows"
family = "nemotron"
release_date = "2026-04-16"
last_updated = "2026-04-16"
attachment = false
reasoning = false
temperature = false
tool_call = false
open_weights = true
[limit]
context = 128_000
output = 4_096
[modalities]
input = ["text"]
output = ["text"]
models/nvidia/nemotron-3-nano-30b-a3b.toml
+18
View File
@@ -0,0 +1,18 @@
name = "Nemotron 3 Nano 30B A3B"
description = "Small Nemotron 3 MoE for efficient coding, math, and long-context agents"
family = "nemotron"
release_date = "2025-12-15"
last_updated = "2025-12-15"
attachment = false
reasoning = true
temperature = true
tool_call = true
open_weights = true
[limit]
context = 262_144
output = 262_144
[modalities]
input = ["text"]
output = ["text"]
models/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning.toml
+18
View File
@@ -0,0 +1,18 @@
name = "Nemotron 3 Nano Omni 30B A3B Reasoning"
description = "Open Nemotron omni model combining reasoning with text, vision, and audio"
family = "nemotron"
release_date = "2026-04-28"
last_updated = "2026-04-28"
attachment = true
reasoning = true
temperature = true
tool_call = true
open_weights = true
[limit]
context = 256_000
output = 65_536
[modalities]
input = ["text", "image", "video", "audio"]
output = ["text"]
models/nvidia/nemotron-3-super-120b-a12b.toml
+18
View File
@@ -0,0 +1,18 @@
name = "Nemotron 3 Super 120B A12B"
description = "Nemotron middle tier for collaborative agents and high-volume reasoning workloads"
family = "nemotron"
release_date = "2026-03-11"
last_updated = "2026-03-11"
attachment = false
reasoning = true
temperature = true
tool_call = true
open_weights = true
[limit]
context = 262_144
output = 262_144
[modalities]
input = ["text"]
output = ["text"]
models/nvidia/nemotron-3-ultra-550b-a55b.toml
+101
View File
@@ -0,0 +1,101 @@
name = "Nemotron 3 Ultra 550B A55B"
description = "Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy"
family = "nemotron"
release_date = "2026-06-04"
last_updated = "2026-06-04"
attachment = false
reasoning = true
temperature = true
tool_call = true
open_weights = true
[limit]
context = 1_000_000
output = 128_000
[modalities]
input = ["text"]
output = ["text"]
[[benchmarks]]
name = "SWE-Bench Verified"
score = 70.7
metric = "resolved"
source = "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16"
date = "2026-06-04"
[[benchmarks]]
name = "SWE-Bench Multilingual"
score = 67.7
metric = "resolve rate"
source = "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16"
date = "2026-06-04"
[[benchmarks]]
name = "Terminal-Bench"
score = 56.4
metric = "success rate"
version = "2.1"
source = "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16"
date = "2026-06-04"
[[benchmarks]]
name = "GPQA"
score = 87.0
metric = "accuracy"
variant = "no tools"
source = "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16"
date = "2026-06-04"
[[benchmarks]]
name = "Humanity's Last Exam"
score = 26.7
metric = "accuracy"
variant = "no tools"
source = "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16"
date = "2026-06-04"
[[benchmarks]]
name = "Humanity's Last Exam"
score = 37.4
metric = "accuracy"
variant = "with tools"
source = "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16"
date = "2026-06-04"
[[benchmarks]]
name = "LiveCodeBench"
score = 89.0
metric = "pass@1"
version = "v6"
source = "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16"
date = "2026-06-04"
[[benchmarks]]
name = "MMLU-Pro"
score = 86.8
metric = "accuracy"
source = "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16"
date = "2026-06-04"
[[benchmarks]]
name = "BrowseComp"
score = 44.4
metric = "accuracy"
source = "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16"
date = "2026-06-04"
[[benchmarks]]
name = "IFBench"
score = 81.7
metric = "accuracy"
variant = "prompt loose"
source = "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16"
date = "2026-06-04"
[[benchmarks]]
name = "GDPval"
score = 46.7
metric = "wins or ties"
source = "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16"
date = "2026-06-04"
models/nvidia/nemotron-3.5-content-safety.toml
+18
View File
@@ -0,0 +1,18 @@
name = "Nemotron 3.5 Content Safety"
description = "Safety model for policy screening, moderation, and risk-aware routing workflows"
family = "nemotron"
release_date = "2026-06-04"
last_updated = "2026-06-04"
attachment = true
reasoning = true
temperature = true
tool_call = false
open_weights = true
[limit]
context = 128_000
output = 8_192
[modalities]
input = ["text", "image"]
output = ["text"]
models/nvidia/nemotron-cascade-2-30b-a3b.toml
+18
View File
@@ -0,0 +1,18 @@
name = "Nemotron Cascade 2 30B A3B"
description = "Nemotron model for efficient reasoning, coding, and specialized AI agents"
family = "nemotron"
release_date = "2026-03-24"
last_updated = "2026-04-09"
attachment = false
reasoning = true
temperature = true
tool_call = true
open_weights = true
[limit]
context = 256_000
output = 32_768
[modalities]
input = ["text"]
output = ["text"]
models/nvidia/nemotron-content-safety-reasoning-4b.toml
+18
View File
@@ -0,0 +1,18 @@
name = "Nemotron Content Safety Reasoning 4B"
description = "Safety model for policy screening, moderation, and risk-aware routing workflows"
family = "nemotron"
release_date = "2026-01-22"
last_updated = "2026-01-22"
attachment = false
reasoning = true
temperature = false
tool_call = false
open_weights = true
[limit]
context = 128_000
output = 4_096
[modalities]
input = ["text"]
output = ["text"]
models/nvidia/nemotron-mini-4b-instruct.toml
+18
View File
@@ -0,0 +1,18 @@
name = "Nemotron Mini 4B Instruct"
description = "Compact Nemotron model for efficient reasoning and deployable AI agents"
family = "nemotron"
release_date = "2024-08-21"
last_updated = "2024-08-26"
attachment = false
reasoning = false
temperature = true
tool_call = true
open_weights = true
[limit]
context = 128_000
output = 8_192
[modalities]
input = ["text"]
output = ["text"]
models/nvidia/nemotron-nano-12b-v2-vl.toml
+18
View File
@@ -0,0 +1,18 @@
name = "Nemotron Nano 12B v2 VL"
description = "Nemotron multimodal model for visual reasoning and agentic AI workflows"
family = "nemotron"
release_date = "2025-10-28"
last_updated = "2025-10-28"
attachment = true
reasoning = true
temperature = true
tool_call = true
open_weights = true
[limit]
context = 128_000
output = 128_000
[modalities]
input = ["text", "image", "video"]
output = ["text"]
models/nvidia/nemotron-nano-9b-v2.toml
+18
View File
@@ -0,0 +1,18 @@
name = "Nemotron Nano 9B v2"
description = "Compact Nemotron model for efficient reasoning and deployable AI agents"
family = "nemotron"
release_date = "2025-08-18"
last_updated = "2025-08-18"
attachment = false
reasoning = true
temperature = true
tool_call = true
open_weights = true
[limit]
context = 131_072
output = 131_072
[modalities]
input = ["text"]
output = ["text"]
models/nvidia/nemotron-voicechat.toml
+18
View File
@@ -0,0 +1,18 @@
name = "Nemotron VoiceChat"
description = "Nemotron multimodal model for visual reasoning and agentic AI workflows"
family = "nemotron"
release_date = "2026-03-16"
last_updated = "2026-03-16"
attachment = true
reasoning = false
temperature = true
tool_call = true
open_weights = true
[limit]
context = 128_000
output = 8_192
[modalities]
input = ["text", "audio"]
output = ["text"]