nm-autobot commited on
Commit
b5ef800
·
verified ·
1 Parent(s): f4706b3

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. config.json +20 -5
  2. generation_config.json +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -25,37 +25,53 @@
25
  "re:.*self_attn\\.(k|q|o|v)_proj$"
26
  ],
27
  "weights": {
 
 
28
  "dynamic": false,
29
  "group_size": 128,
30
  "num_bits": 4,
31
  "observer": "memoryless_minmax",
 
 
32
  "strategy": "group",
33
  "symmetric": true,
34
- "type": "int"
 
35
  }
36
  },
37
  "group_1": {
38
  "format": "int-quantized",
39
  "input_activations": {
 
 
40
  "dynamic": true,
41
  "group_size": null,
42
  "num_bits": 8,
 
 
 
43
  "strategy": "token",
44
  "symmetric": true,
45
- "type": "int"
 
46
  },
47
  "output_activations": null,
48
  "targets": [
49
  "re:.*mlp\\.(down|gate|up)_proj$"
50
  ],
51
  "weights": {
 
 
52
  "dynamic": false,
53
  "group_size": null,
54
  "num_bits": 8,
55
  "observer": "memoryless_minmax",
 
 
56
  "strategy": "channel",
57
  "symmetric": true,
58
- "type": "int"
 
59
  }
60
  }
61
  },
@@ -65,12 +81,11 @@
65
  "lm_head"
66
  ],
67
  "kv_cache_scheme": null,
68
- "moe_sparsity_config": null,
69
  "quant_method": "compressed-tensors",
70
  "quantization_status": "compressed",
71
  "sparsity_config": {},
72
  "transform_config": {},
73
- "version": "0.19.1.dev41+g0ccb6a99"
74
  },
75
  "rms_norm_eps": 1e-05,
76
  "rope_scaling": null,
 
25
  "re:.*self_attn\\.(k|q|o|v)_proj$"
26
  ],
27
  "weights": {
28
+ "actorder": null,
29
+ "block_structure": null,
30
  "dynamic": false,
31
  "group_size": 128,
32
  "num_bits": 4,
33
  "observer": "memoryless_minmax",
34
+ "observer_kwargs": {},
35
+ "scale_dtype": null,
36
  "strategy": "group",
37
  "symmetric": true,
38
+ "type": "int",
39
+ "zp_dtype": null
40
  }
41
  },
42
  "group_1": {
43
  "format": "int-quantized",
44
  "input_activations": {
45
+ "actorder": null,
46
+ "block_structure": null,
47
  "dynamic": true,
48
  "group_size": null,
49
  "num_bits": 8,
50
+ "observer": null,
51
+ "observer_kwargs": {},
52
+ "scale_dtype": null,
53
  "strategy": "token",
54
  "symmetric": true,
55
+ "type": "int",
56
+ "zp_dtype": null
57
  },
58
  "output_activations": null,
59
  "targets": [
60
  "re:.*mlp\\.(down|gate|up)_proj$"
61
  ],
62
  "weights": {
63
+ "actorder": null,
64
+ "block_structure": null,
65
  "dynamic": false,
66
  "group_size": null,
67
  "num_bits": 8,
68
  "observer": "memoryless_minmax",
69
+ "observer_kwargs": {},
70
+ "scale_dtype": null,
71
  "strategy": "channel",
72
  "symmetric": true,
73
+ "type": "int",
74
+ "zp_dtype": null
75
  }
76
  }
77
  },
 
81
  "lm_head"
82
  ],
83
  "kv_cache_scheme": null,
 
84
  "quant_method": "compressed-tensors",
85
  "quantization_status": "compressed",
86
  "sparsity_config": {},
87
  "transform_config": {},
88
+ "version": "0.19.0"
89
  },
90
  "rms_norm_eps": 1e-05,
91
  "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
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8ca2e2456e7f6f47586dc9b75304895e19ab25238b65c972b164c7a31756de1
3
  size 1131284624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:275400f688a689e59ced1e22beb1bf51d2eeb182c12a96cdf5bba23f4640fb6d
3
  size 1131284624