Hugging Face's logo

JamAndTeaStudios
/
gemma-2-9b-it-FP8-Dynamic

Text Generation
Transformers
Safetensors
English
gemma2
chat
conversational
text-generation-inference
compressed-tensors
Model card Files
xet
 Community
Yudi Xue commited on
Commit
a46317a
·
verified ·
1 Parent(s): 4edbdf9

Upload Gemma2ForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +2 -3
  2. generation_config.json +1 -1
  3. recipe.yaml +2 -2
config.json CHANGED
@@ -1,5 +1,4 @@
1
  {
2
- "_name_or_path": "google/gemma-2-9b-it",
3
  "architectures": [
4
  "Gemma2ForCausalLM"
5
  ],
@@ -56,7 +55,7 @@
56
  }
57
  },
58
  "format": "float-quantized",
59
- "global_compression_ratio": 1.4071500774200931,
60
  "ignore": [
61
  "lm_head"
62
  ],
@@ -70,7 +69,7 @@
70
  "sliding_window": 4096,
71
  "sliding_window_size": 4096,
72
  "torch_dtype": "bfloat16",
73
- "transformers_version": "4.48.1",
74
  "use_cache": true,
75
  "vocab_size": 256000
76
  }
 
1
  {
 
2
  "architectures": [
3
  "Gemma2ForCausalLM"
4
  ],
 
55
  }
56
  },
57
  "format": "float-quantized",
58
+ "global_compression_ratio": null,
59
  "ignore": [
60
  "lm_head"
61
  ],
 
69
  "sliding_window": 4096,
70
  "sliding_window_size": 4096,
71
  "torch_dtype": "bfloat16",
72
+ "transformers_version": "4.51.3",
73
  "use_cache": true,
74
  "vocab_size": 256000
75
  }
generation_config.json CHANGED
@@ -4,5 +4,5 @@
4
  "cache_implementation": "hybrid",
5
  "eos_token_id": 1,
6
  "pad_token_id": 0,
7
- "transformers_version": "4.48.1"
8
  }
 
4
  "cache_implementation": "hybrid",
5
  "eos_token_id": 1,
6
  "pad_token_id": 0,
7
+ "transformers_version": "4.51.3"
8
  }
recipe.yaml CHANGED
@@ -1,5 +1,5 @@
1
- DEFAULT_stage:
2
- DEFAULT_modifiers:
3
  QuantizationModifier:
4
  ignore: [lm_head]
5
  targets: [Linear]
 
1
+ default_stage:
2
+ default_modifiers:
3
  QuantizationModifier:
4
  ignore: [lm_head]
5
  targets: [Linear]