vikhyatk commited on
Commit
7588708
·
verified ·
1 Parent(s): 3461d5c

Upload HfMoondream

Browse files
Files changed (3) hide show
  1. README.md +1 -1
  2. model.safetensors +2 -2
  3. text.py +1 -1
README.md CHANGED
@@ -7,7 +7,7 @@ Moondream is a small vision language model designed to run efficiently everywher
7
 
8
  [Website](https://moondream.ai/) / [Demo](https://moondream.ai/playground) / [GitHub](https://github.com/vikhyat/moondream)
9
 
10
- This repository contains the 2025-04-14 **4bit** release of Moondream. On an Nvidia RTX 3090, it uses 2,305 MB of VRAM and runs at a speed of 187 tokens/second. We used quantization-aware training techniques to build this version of the model, allowing us to achieve a 45% reduction in memory usage with only an (TK)% drop in accuracy.
11
 
12
  There's more information about this version of the model in our [release blog post](https://moondream.ai/blog/smaller-faster-moondream-with-qat). Other revisions, as well as release history, can be found [here](https://huggingface.co/vikhyatk/moondream2).
13
 
 
7
 
8
  [Website](https://moondream.ai/) / [Demo](https://moondream.ai/playground) / [GitHub](https://github.com/vikhyat/moondream)
9
 
10
+ This repository contains the 2025-04-14 **4bit** release of Moondream. On an Nvidia RTX 3090, it uses 2,305 MB of VRAM and runs at a speed of 187 tokens/second. We used quantization-aware training techniques to build this version of the model, allowing us to achieve a 45% reduction in memory usage with only an 2% drop in accuracy.
11
 
12
  There's more information about this version of the model in our [release blog post](https://moondream.ai/blog/smaller-faster-moondream-with-qat). Other revisions, as well as release history, can be found [here](https://huggingface.co/vikhyatk/moondream2).
13
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:325876fadb939f7c65f545d5d37b03f5035681b87bad1073f6d2e804ce2f4068
3
- size 1881750512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfce186edf359fff98d0c077ae389b980b6cae99279d157fc00b2d03ca65968f
3
+ size 2032380848
text.py CHANGED
@@ -187,7 +187,7 @@ def build_text_model(config: TextConfig, dtype: torch.dtype) -> nn.Module:
187
  ]
188
  ),
189
  "post_ln": nn.LayerNorm(config.dim, dtype=dtype),
190
- "lm_head": linear_cls(config.dim, config.vocab_size, dtype=dtype),
191
  }
192
  )
193
  text.wte = nn.Parameter(torch.empty(config.vocab_size, config.dim, dtype=dtype))
 
187
  ]
188
  ),
189
  "post_ln": nn.LayerNorm(config.dim, dtype=dtype),
190
+ "lm_head": nn.Linear(config.dim, config.vocab_size, dtype=dtype),
191
  }
192
  )
193
  text.wte = nn.Parameter(torch.empty(config.vocab_size, config.dim, dtype=dtype))