nm-autobot commited on
Commit
590eadd
·
verified ·
1 Parent(s): 9d84677

Upload folder using huggingface_hub

Browse files
Files changed (2) hide show
  1. config.json +6 -3
  2. generation_config.json +1 -1
config.json CHANGED
@@ -25,14 +25,18 @@
25
  "Linear"
26
  ],
27
  "weights": {
 
 
28
  "dynamic": false,
29
  "group_size": 16,
30
  "num_bits": 4,
31
  "observer": "memoryless_minmax",
 
32
  "scale_dtype": "torch.float8_e4m3fn",
33
  "strategy": "tensor_group",
34
  "symmetric": true,
35
- "type": "float"
 
36
  }
37
  }
38
  },
@@ -42,12 +46,11 @@
42
  "lm_head"
43
  ],
44
  "kv_cache_scheme": null,
45
- "moe_sparsity_config": null,
46
  "quant_method": "compressed-tensors",
47
  "quantization_status": "compressed",
48
  "sparsity_config": {},
49
  "transform_config": {},
50
- "version": "0.19.1.dev39+g7195055d"
51
  },
52
  "rms_norm_eps": 1e-05,
53
  "rope_scaling": null,
 
25
  "Linear"
26
  ],
27
  "weights": {
28
+ "actorder": null,
29
+ "block_structure": null,
30
  "dynamic": false,
31
  "group_size": 16,
32
  "num_bits": 4,
33
  "observer": "memoryless_minmax",
34
+ "observer_kwargs": {},
35
  "scale_dtype": "torch.float8_e4m3fn",
36
  "strategy": "tensor_group",
37
  "symmetric": true,
38
+ "type": "float",
39
+ "zp_dtype": null
40
  }
41
  }
42
  },
 
46
  "lm_head"
47
  ],
48
  "kv_cache_scheme": null,
 
49
  "quant_method": "compressed-tensors",
50
  "quantization_status": "compressed",
51
  "sparsity_config": {},
52
  "transform_config": {},
53
+ "version": "0.19.1.dev0"
54
  },
55
  "rms_norm_eps": 1e-05,
56
  "rope_scaling": null,
generation_config.json CHANGED
@@ -3,5 +3,5 @@
3
  "eos_token_id": 2,
4
  "max_length": 2048,
5
  "pad_token_id": 0,
6
- "transformers_version": "5.20.2"
7
  }
 
3
  "eos_token_id": 2,
4
  "max_length": 2048,
5
  "pad_token_id": 0,
6
+ "transformers_version": "5.17.0"
7
  }