Skip to content

Commit de299ca

Browse files
localai-botmudler
andauthored
chore(model-gallery): ⬆️ update checksum (#10371)
⬆️ Checksum updates in gallery/index.yaml Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
1 parent 980ec4a commit de299ca

1 file changed

Lines changed: 2 additions & 39 deletions

File tree

gallery/index.yaml

Lines changed: 2 additions & 39 deletions
Original file line numberDiff line numberDiff line change
@@ -46,8 +46,8 @@
4646
use_tokenizer_template: true
4747
files:
4848
- filename: llama-cpp/models/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF/gemma4-coding-Q4_K_M.gguf
49-
sha256: 4011bb86572a587783a553b54927314a2ed8395befa59db202ee775d183cd751
5049
uri: https://huggingface.co/yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF/resolve/main/gemma4-coding-Q4_K_M.gguf
50+
sha256: 1fe90b72e105d7bc71650aa59883edece3e84751af489075217a7ae717b1fe8d
5151
- name: "serenity-26b-a4b"
5252
url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
5353
urls:
@@ -203,35 +203,7 @@
203203
url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
204204
urls:
205205
- https://huggingface.co/Jackrong/Qwopus3.6-27B-Coder-MTP-GGUF
206-
description: |
207-
🪐 Qwopus3.6-27B-v2
208-
SFT Release
209-
210-
Reasoning-Enhanced Dense Language Model Fine-Tuned on Qwen3.6-27B
211-
212-
🧬 Trace Inversion & Negentropy
213-
🧠 27B Parameters
214-
🔥 3-Stage Curriculum SFT
215-
🛠️ Vision & Tool-use Support
216-
217-
💡 What is Qwopus3.6-27B-v2?
218-
🪐 Qwopus3.6-27B-v2 is a reasoning-enhanced dense language model built on top of Qwen3.6-27B. By leveraging a multi-stage curriculum learning pipeline and augmented with Trace Inversion datasets (claude-opus-4.6/4.7-traceInversion), it reverse-engineers the compressed "Reasoning Bubbles" of commercial LLMs into structured, step-by-step synthetic reasoning traces, successfully eliminating logical shortcuts and knowledge fractures.
219-
220-
🧩 Structured Reasoning
221-
Injects reconstructed deep CoT chains to eliminate logical shortcuts via Trace Inversion.
222-
223-
🪶 Style Consistency
224-
Enforces strict constraints on the format and convergence of &lt;think&gt; tags.
225-
226-
🔁 Distillation Alignment
227-
Ensures high-quality cross-source SFT data alignment to narrow the capacity gap.
228-
229-
⚡ RL Scalability
230-
Sets up a stable formatting pipeline optimized for downstream Reinforcement Learning (RL).
231-
232-
## 💡 1. Base Model, Training Library & Cooperation
233-
234-
...
206+
description: "\U0001FA90 Qwopus3.6-27B-v2\nSFT Release\n\nReasoning-Enhanced Dense Language Model Fine-Tuned on Qwen3.6-27B\n\n\U0001F9EC Trace Inversion & Negentropy\n\U0001F9E0 27B Parameters\n\U0001F525 3-Stage Curriculum SFT\n\U0001F6E0️ Vision & Tool-use Support\n\n\U0001F4A1 What is Qwopus3.6-27B-v2?\n\U0001FA90 Qwopus3.6-27B-v2 is a reasoning-enhanced dense language model built on top of Qwen3.6-27B. By leveraging a multi-stage curriculum learning pipeline and augmented with Trace Inversion datasets (claude-opus-4.6/4.7-traceInversion), it reverse-engineers the compressed \"Reasoning Bubbles\" of commercial LLMs into structured, step-by-step synthetic reasoning traces, successfully eliminating logical shortcuts and knowledge fractures.\n\n\U0001F9E9 Structured Reasoning\nInjects reconstructed deep CoT chains to eliminate logical shortcuts via Trace Inversion.\n\n\U0001FAB6 Style Consistency\nEnforces strict constraints on the format and convergence of &lt;think&gt; tags.\n\n\U0001F501 Distillation Alignment\nEnsures high-quality cross-source SFT data alignment to narrow the capacity gap.\n\n⚡ RL Scalability\nSets up a stable formatting pipeline optimized for downstream Reinforcement Learning (RL).\n\n## \U0001F4A1 1. Base Model, Training Library & Cooperation\n\n...\n"
235207
license: "apache-2.0"
236208
tags:
237209
- llm
@@ -8049,7 +8021,6 @@
80498021
- filename: depth-anything-base-q4_k.gguf
80508022
uri: huggingface://mudler/depth-anything.cpp-gguf/depth-anything-base-q4_k.gguf
80518023
sha256: "43cd45d00f9024f4319f4beabd73155db5132e4b575bc52eff4131262c9d78f1"
8052-
80538024
- !!merge <<: *depth-anything-3-base
80548025
name: depth-anything-3-base-q8_0
80558026
description: |
@@ -8063,7 +8034,6 @@
80638034
- filename: depth-anything-base-q8_0.gguf
80648035
uri: huggingface://mudler/depth-anything.cpp-gguf/depth-anything-base-q8_0.gguf
80658036
sha256: "71b1c953113657f9a4fbef43ab6a16fe7a6f87b36da113a184f13c4a564968a0"
8066-
80678037
- !!merge <<: *depth-anything-3-base
80688038
name: depth-anything-3-base-f16
80698039
description: |
@@ -8077,7 +8047,6 @@
80778047
- filename: depth-anything-base-f16.gguf
80788048
uri: huggingface://mudler/depth-anything.cpp-gguf/depth-anything-base-f16.gguf
80798049
sha256: "2975419c99702ca646d5b7120c53e35c9fee158f0a803577241d16957f75624b"
8080-
80818050
- !!merge <<: *depth-anything-3-base
80828051
name: depth-anything-3-base-f32
80838052
description: |
@@ -8091,7 +8060,6 @@
80918060
- filename: depth-anything-base-f32.gguf
80928061
uri: huggingface://mudler/depth-anything.cpp-gguf/depth-anything-base-f32.gguf
80938062
sha256: "1b13b166e8a8b4f2c862f42d36edb2f9aab995a18cc527a52b9f160b99c6b8da"
8094-
80958063
- !!merge <<: *depth-anything-3-base
80968064
name: depth-anything-3-giant
80978065
description: |
@@ -8112,7 +8080,6 @@
81128080
- filename: depth-anything-giant-f32.gguf
81138081
uri: huggingface://mudler/depth-anything.cpp-gguf/depth-anything-giant-f32.gguf
81148082
sha256: "392edf64626be6a985487beb39c8d54cdc14f7feb2b53323742c96b71e7e7181"
8115-
81168083
- !!merge <<: *depth-anything-3-base
81178084
name: depth-anything-3-small
81188085
description: |
@@ -8126,7 +8093,6 @@
81268093
- filename: depth-anything-small-f32.gguf
81278094
uri: huggingface://mudler/depth-anything.cpp-gguf/depth-anything-small-f32.gguf
81288095
sha256: "eab5597e01dedde1a20c038590ae8c887b85ec35b882581138c08308e92c41e5"
8129-
81308096
- !!merge <<: *depth-anything-3-base
81318097
name: depth-anything-3-large
81328098
description: |
@@ -8147,7 +8113,6 @@
81478113
- filename: depth-anything-large-f32.gguf
81488114
uri: huggingface://mudler/depth-anything.cpp-gguf/depth-anything-large-f32.gguf
81498115
sha256: "a79eb3e19e8ec49f4daac484fb5fb67e15baac61518d229cf819e40c87080906"
8150-
81518116
- !!merge <<: *depth-anything-3-base
81528117
name: depth-anything-3-mono-large
81538118
description: |
@@ -8162,7 +8127,6 @@
81628127
- filename: depth-anything-mono-large-f32.gguf
81638128
uri: huggingface://mudler/depth-anything.cpp-gguf/depth-anything-mono-large-f32.gguf
81648129
sha256: "291b1a554af907c3f79986ee225da8933be5f7a31d73c81d06784cda284535de"
8165-
81668130
- !!merge <<: *depth-anything-3-base
81678131
name: depth-anything-3-metric-large
81688132
description: |
@@ -8178,7 +8142,6 @@
81788142
- filename: depth-anything-metric-large-f32.gguf
81798143
uri: huggingface://mudler/depth-anything.cpp-gguf/depth-anything-metric-large-f32.gguf
81808144
sha256: "d10b7450c2238244b2d72e2749537a1876255180149cd630a18bc1619c9286be"
8181-
81828145
- !!merge <<: *depth-anything-3-base
81838146
name: depth-anything-3-nested
81848147
description: |

0 commit comments

Comments
 (0)