Hugging Face's logo

trl-internal-testing
/
tiny-DeepseekV3ForCausalLM

Text Generation
Transformers
Safetensors
deepseek_v3
trl
conversational
text-generation-inference
Model card Files
xet
Community
1
qgallouedec HF Staff commited on
Commit
087120c
·
verified ·
1 Parent(s): c40ec2c

Upload DeepseekV3ForCausalLM

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
@@ -37,7 +37,7 @@
37
  "routed_scaling_factor": 2.5,
38
  "tie_word_embeddings": false,
39
  "topk_group": 4,
40
- "transformers_version": "4.57.0.dev0",
41
  "use_cache": true,
42
  "v_head_dim": 128,
43
  "vocab_size": 128815
 
37
  "routed_scaling_factor": 2.5,
38
  "tie_word_embeddings": false,
39
  "topk_group": 4,
40
+ "transformers_version": "4.57.3",
41
  "use_cache": true,
42
  "v_head_dim": 128,
43
  "vocab_size": 128815
generation_config.json CHANGED
@@ -2,5 +2,5 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 0,
4
  "eos_token_id": 1,
5
- "transformers_version": "4.57.0.dev0"
6
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 0,
4
  "eos_token_id": 1,
5
+ "transformers_version": "4.57.3"
6
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4029cdf7a5f9a0a7844863ac6bcf33b70438c50a78d7960d3b7ba479c2557dc6
3
  size 22069200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d52bdbce636be59060d15b69d95aeb5c5aefff86c128995c666209186b4cf8a
3
  size 22069200