JamAndTeaStudios
/

Qwen2.5-7B-Instruct-1M-FP8-Dynamic

Text Generation

text-generation-inference

compressed-tensors

Model card Files Files and versions Community

Yudi Xue commited on Apr 21

Commit

09e5d42

·

verified ·

1 Parent(s): ba85e25

Upload Qwen2ForCausalLM

Files changed (3) hide show

config.json +3 -3
generation_config.json +1 -1
recipe.yaml +2 -2

config.json CHANGED Viewed

@@ -55,7 +55,7 @@
       }
     },
     "format": "float-quantized",
-    "global_compression_ratio": 1.5268082955288436,
     "ignore": [
       "lm_head"
     ],
@@ -66,10 +66,10 @@
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000000.0,
-  "sliding_window": null,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.48.1",
   "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 152064

       }
     },
     "format": "float-quantized",
+    "global_compression_ratio": null,
     "ignore": [
       "lm_head"
     ],
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000000.0,
+  "sliding_window": 32768,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
   "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 152064

generation_config.json CHANGED Viewed

@@ -10,5 +10,5 @@
   "temperature": 0.7,
   "top_k": 20,
   "top_p": 0.8,
-  "transformers_version": "4.48.1"
 }

   "temperature": 0.7,
   "top_k": 20,
   "top_p": 0.8,
+  "transformers_version": "4.49.0"
 }

recipe.yaml CHANGED Viewed

@@ -1,5 +1,5 @@
-DEFAULT_stage:
-  DEFAULT_modifiers:
     QuantizationModifier:
       ignore: [lm_head]
       targets: [Linear]

+default_stage:
+  default_modifiers:
     QuantizationModifier:
       ignore: [lm_head]
       targets: [Linear]