Hugging Face's logo

210Codelabs
/
AdaptIQ-7B

Text Generation
Transformers
adaptiq
210-code-labs
code
agent
routed-experts
openai-compatible
Model card Files
xet
 Community
210Codelabs commited on
Commit
b45d5ad
·
verified ·
1 Parent(s): b93c2dc

Publish AdaptIQ-7B artifacts

Browse files
Files changed (3) hide show
  1. README.md +1 -1
  2. ROUTED_EXPERTS.txt +1 -1
  3. adaptiq_manifest.json +3 -3
README.md CHANGED
@@ -26,7 +26,7 @@ architectures:
26
  |---|---|
27
  | Text / reasoning | `mistralai/Mistral-7B-Instruct-v0.3` |
28
  | Code / debugging | `ibm-granite/granite-8b-code-instruct` |
29
- | Image generation | `black-forest-labs/FLUX.1-schnell` |
30
 
31
  Composition method: `routed_experts`. `alpha=0.5` is retained only for compatible linear-merge
32
  experiments and is not used by the routed-expert release path.
 
26
  |---|---|
27
  | Text / reasoning | `mistralai/Mistral-7B-Instruct-v0.3` |
28
  | Code / debugging | `ibm-granite/granite-8b-code-instruct` |
29
+ | Image generation | `stabilityai/sd-turbo` |
30
 
31
  Composition method: `routed_experts`. `alpha=0.5` is retained only for compatible linear-merge
32
  experiments and is not used by the routed-expert release path.
ROUTED_EXPERTS.txt CHANGED
@@ -1,4 +1,4 @@
1
  AdaptIQ uses routed expert composition for this variant.
2
  text=mistralai/Mistral-7B-Instruct-v0.3
3
  code=ibm-granite/granite-8b-code-instruct
4
- image=black-forest-labs/FLUX.1-schnell
 
1
  AdaptIQ uses routed expert composition for this variant.
2
  text=mistralai/Mistral-7B-Instruct-v0.3
3
  code=ibm-granite/granite-8b-code-instruct
4
+ image=stabilityai/sd-turbo
adaptiq_manifest.json CHANGED
@@ -8,7 +8,7 @@
8
  "mistralai/Mistral-7B-Instruct-v0.3",
9
  "ibm-granite/granite-8b-code-instruct"
10
  ],
11
- "image_expert": "black-forest-labs/FLUX.1-schnell",
12
  "composition": {
13
  "method": "routed_experts",
14
  "alpha": 0.5,
@@ -26,9 +26,9 @@
26
  "license": "apache-2.0"
27
  },
28
  "image": {
29
- "repo": "black-forest-labs/FLUX.1-schnell",
30
  "revision": "main",
31
- "license": "apache-2.0"
32
  }
33
  },
34
  "brand": "AdaptIQ",
 
8
  "mistralai/Mistral-7B-Instruct-v0.3",
9
  "ibm-granite/granite-8b-code-instruct"
10
  ],
11
+ "image_expert": "stabilityai/sd-turbo",
12
  "composition": {
13
  "method": "routed_experts",
14
  "alpha": 0.5,
 
26
  "license": "apache-2.0"
27
  },
28
  "image": {
29
+ "repo": "stabilityai/sd-turbo",
30
  "revision": "main",
31
+ "license": "stability-ai-community"
32
  }
33
  },
34
  "brand": "AdaptIQ",