Léon Simmons

Avicennasis's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in autotrust/GEV-26B-Decide about 6 hours ago

MLX port for Apple silicon (System 1): Avicennasis/GEV-26B-Decide-mlx-8bit / -4bit

👍 3

3

#1 opened 1 day ago by

Avicennasis

New activity in IFM/K2-Horizon-7B 4 days ago

Fix: add the missing @capture_outputs decorator (output_hidden_states is None) Fixes the issue reported in discussion #6. `K2HorizonModel.forward` carries `@auto_docstring` but not `@capture_outputs`, so `output_hidden_states=True` returns `None` (any tool that reads the residual stream per layer fails). Adding the decorator plus the import makes `outputs.hidden_states` a tuple of len `num_hidden_layers + 1`; greedy decoding is unchanged. Verified on 0.9B: 29 states (28 layers + 1), `[0]` == embeddings and `[-1]` == `last_hidden_state`; generation byte-identical with and without the decorator. The change is the same for every full-model repo in the family (the file is byte-identical across sizes).

#5 opened 4 days ago by

Avicennasis

New activity in IFM/K2-Horizon-3.7B 4 days ago

Fix: add the missing @capture_outputs decorator (output_hidden_states is None) Fixes the issue reported in discussion #6. `K2HorizonModel.forward` carries `@auto_docstring` but not `@capture_outputs`, so `output_hidden_states=True` returns `None` (any tool that reads the residual stream per layer fails). Adding the decorator plus the import makes `outputs.hidden_states` a tuple of len `num_hidden_layers + 1`; greedy decoding is unchanged. Verified on 0.9B: 29 states (28 layers + 1), `[0]` == embeddings and `[-1]` == `last_hidden_state`; generation byte-identical with and without the decorator. The change is the same for every full-model repo in the family (the file is byte-identical across sizes).

#6 opened 4 days ago by

Avicennasis

New activity in IFM/K2-Horizon-0.9B 4 days ago

Fix: add the missing @capture_outputs decorator (output_hidden_states is None) Fixes the issue reported in discussion #6. `K2HorizonModel.forward` carries `@auto_docstring` but not `@capture_outputs`, so `output_hidden_states=True` returns `None` (any tool that reads the residual stream per layer fails). Adding the decorator plus the import makes `outputs.hidden_states` a tuple of len `num_hidden_layers + 1`; greedy decoding is unchanged. Verified on 0.9B: 29 states (28 layers + 1), `[0]` == embeddings and `[-1]` == `last_hidden_state`; generation byte-identical with and without the decorator. The change is the same for every full-model repo in the family (the file is byte-identical across sizes).

#9 opened 4 days ago by

Avicennasis

New activity in IFM/K2-Horizon-0.9B 7 days ago

[superseded by #8 - opened as a discussion by mistake] Fix output_hidden_states / attentions returning None

1

#7 opened 7 days ago by

Avicennasis

Fix `output_hidden_states` / `attentions` returning None (missing `@capture_outputs`)

#8 opened 7 days ago by

Avicennasis

`output_hidden_states=True` returns `hidden_states=None` on all K2-Horizon repos — missing `@capture_outputs` decorator in `modeling_k2_horizon.py`

#6 opened 7 days ago by

Avicennasis