danielhanchen commited on
Commit
e079ee2
·
verified ·
1 Parent(s): 2cf226a

Add files using upload-large-folder tool

Browse files
config.json CHANGED
@@ -88,9 +88,11 @@
88
  "num_bits": 8,
89
  "observer": null,
90
  "observer_kwargs": {},
 
91
  "strategy": "token",
92
  "symmetric": true,
93
- "type": "float"
 
94
  },
95
  "output_activations": null,
96
  "targets": [
@@ -105,9 +107,11 @@
105
  "num_bits": 8,
106
  "observer": "minmax",
107
  "observer_kwargs": {},
 
108
  "strategy": "channel",
109
  "symmetric": true,
110
- "type": "float"
 
111
  }
112
  }
113
  },
@@ -161,7 +165,7 @@
161
  "quantization_status": "compressed",
162
  "sparsity_config": {},
163
  "transform_config": {},
164
- "version": "0.12.2.a20251002"
165
  },
166
  "residual_multiplier": 0.22,
167
  "rms_norm_eps": 1e-05,
@@ -169,8 +173,8 @@
169
  "rope_theta": 10000,
170
  "router_aux_loss_coef": 0.0,
171
  "shared_intermediate_size": 1024,
172
- "tie_word_embeddings": false,
173
- "transformers_version": "4.57.0",
174
  "unsloth_fixed": true,
175
  "use_cache": true,
176
  "vocab_size": 100352
 
88
  "num_bits": 8,
89
  "observer": null,
90
  "observer_kwargs": {},
91
+ "scale_dtype": null,
92
  "strategy": "token",
93
  "symmetric": true,
94
+ "type": "float",
95
+ "zp_dtype": null
96
  },
97
  "output_activations": null,
98
  "targets": [
 
107
  "num_bits": 8,
108
  "observer": "minmax",
109
  "observer_kwargs": {},
110
+ "scale_dtype": null,
111
  "strategy": "channel",
112
  "symmetric": true,
113
+ "type": "float",
114
+ "zp_dtype": null
115
  }
116
  }
117
  },
 
165
  "quantization_status": "compressed",
166
  "sparsity_config": {},
167
  "transform_config": {},
168
+ "version": "0.12.3.a20251114"
169
  },
170
  "residual_multiplier": 0.22,
171
  "rms_norm_eps": 1e-05,
 
173
  "rope_theta": 10000,
174
  "router_aux_loss_coef": 0.0,
175
  "shared_intermediate_size": 1024,
176
+ "tie_word_embeddings": true,
177
+ "transformers_version": "4.57.1",
178
  "unsloth_fixed": true,
179
  "use_cache": true,
180
  "vocab_size": 100352
generation_config.json CHANGED
@@ -4,5 +4,5 @@
4
  "eos_token_id": 100257,
5
  "max_length": 131072,
6
  "pad_token_id": 100256,
7
- "transformers_version": "4.57.0"
8
  }
 
4
  "eos_token_id": 100257,
5
  "max_length": 131072,
6
  "pad_token_id": 100256,
7
+ "transformers_version": "4.57.1"
8
  }
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9d6e55462bbb95b5b14f52de8facc1d7b1fe5d16f047c9eeb7c13ae64835e60
3
  size 4999103976
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e80671bd29d8523c598fa21fb569c79ae06e3102f701f27f326cccd5a7f35917
3
  size 4999103976
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37778dba5a60ce8eca29fa432fe933b012c4d508388b9e4aa29dceba4537f192
3
- size 2421227416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:963e7dcb29b2a8249147a492b1650b108695a71ee01f1d6615c18767ad183fd6
3
+ size 2112945144
model.safetensors.index.json CHANGED
@@ -1,10 +1,9 @@
1
  {
2
  "metadata": {
3
- "total_parameters": 7100178688,
4
- "total_size": 7420232192
5
  },
6
  "weight_map": {
7
- "lm_head.weight": "model-00002-of-00002.safetensors",
8
  "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
9
  "model.layers.0.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
10
  "model.layers.0.block_sparse_moe.input_linear.weight_scale": "model-00001-of-00002.safetensors",
 
1
  {
2
  "metadata": {
3
+ "total_parameters": 6946038016,
4
+ "total_size": 7111950848
5
  },
6
  "weight_map": {
 
7
  "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
  "model.layers.0.block_sparse_moe.input_linear.weight": "model-00001-of-00002.safetensors",
9
  "model.layers.0.block_sparse_moe.input_linear.weight_scale": "model-00001-of-00002.safetensors",