trl-internal-testing
/

tiny-DeepseekV3ForCausalLM

Text Generation

text-generation-inference

Model card Files Files and versions

qgallouedec HF Staff commited on Sep 23, 2025

Commit

0d0a303

·

verified ·

1 Parent(s): 328446a

Upload DeepseekV3ForCausalLM

Files changed (2) hide show

config.json +1 -1
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -10,7 +10,7 @@
     "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
   },
   "bos_token_id": 0,
-  "dtype": "float32",
   "eos_token_id": 1,
   "ep_size": 1,
   "first_k_dense_replace": 3,

     "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
   },
   "bos_token_id": 0,
+  "dtype": "bfloat16",
   "eos_token_id": 1,
   "ep_size": 1,
   "first_k_dense_replace": 3,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88aa70add1627a948ee4dda3a734b6bf225c2cb5452b7d84bb668c0d55b1b1ea
-size 22098960

 version https://git-lfs.github.com/spec/v1
+oid sha256:c72877b9a5ecadf56f7cffc5c049fc47b19dc80428ce660de005e65f32a1957e
+size 11050936