kz919
/

QwQ-0.5B-Distilled-SFT

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

kz919 commited on 4 days ago

Commit

5916c2d

·

verified ·

1 Parent(s): adcac77

Upload Qwen2ForCausalLM

Files changed (2) hide show

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

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/scratch/09979/kaizhaol/sft_model_8dp/checkpoint-702/",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
@@ -11,7 +11,7 @@
   "initializer_range": 0.02,
   "intermediate_size": 4864,
   "max_position_embeddings": 32768,
-  "max_window_layers": 24,
   "model_type": "qwen2",
   "num_attention_heads": 14,
   "num_hidden_layers": 24,

 {
+  "_name_or_path": "/scratch/09979/kaizhaol/sft_model_8dp_small_batch_v3/checkpoint-11646/",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
   "initializer_range": 0.02,
   "intermediate_size": 4864,
   "max_position_embeddings": 32768,
+  "max_window_layers": 21,
   "model_type": "qwen2",
   "num_attention_heads": 14,
   "num_hidden_layers": 24,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:929c2eb5b004a5ce075984524b1013e37ad71d20a0470ea360b3d829088f8e4d
 size 988097824

 version https://git-lfs.github.com/spec/v1
+oid sha256:5b88a84538252528f570918443ac27765ded64fab86bcf63eb0dd43e42035934
 size 988097824