Hugging Face's logo

oopere
/
Qwen3.5-0.65B-Base-Rearchitected

Safetensors
English
qwen3_5_text
optipfair
rearchitecting-llms
knowledge-distillation
depth-pruning
model-optimization
small-language-model
qwen
educational
Model card Files
xet
 Community
oopere commited on
Commit
f96089c
·
verified ·
1 Parent(s): 1d01671

Initial upload: Depth-pruned + KD model from Chapter 6

Browse files
Files changed (3) hide show
  1. config.json +1 -1
  2. generation_config.json +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -65,7 +65,7 @@
65
  "rope_type": "default"
66
  },
67
  "tie_word_embeddings": true,
68
- "transformers_version": "5.3.0",
69
  "use_cache": false,
70
  "vocab_size": 248320
71
  }
 
65
  "rope_type": "default"
66
  },
67
  "tie_word_embeddings": true,
68
+ "transformers_version": "5.9.0",
69
  "use_cache": false,
70
  "vocab_size": 248320
71
  }
generation_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_from_model_config": true,
3
  "eos_token_id": 248044,
4
- "transformers_version": "5.3.0",
5
  "use_cache": true
6
  }
 
1
  {
2
  "_from_model_config": true,
3
  "eos_token_id": 248044,
4
+ "transformers_version": "5.9.0",
5
  "use_cache": true
6
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d57dceff1b35cbcafca03ba478bdaef99a6bc13e3ebaa297d11ca1f0f23a407d
3
  size 1332377368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7566f1e12a2302c25da59cf76216af83dc5543549f62b9e38c8af0a9aec61ff5
3
  size 1332377368