Upload Phi3ForCausalLM
Browse files- config.json +19 -10
- generation_config.json +1 -1
- pytorch_model.bin +2 -2
config.json
CHANGED
|
@@ -5,9 +5,9 @@
|
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"auto_map": {
|
| 8 |
-
"AutoConfig": "
|
| 9 |
-
"AutoModelForCausalLM": "
|
| 10 |
-
"AutoTokenizer": "
|
| 11 |
},
|
| 12 |
"bos_token_id": 199999,
|
| 13 |
"embd_pdrop": 0.0,
|
|
@@ -29,6 +29,7 @@
|
|
| 29 |
"pad_token_id": 199999,
|
| 30 |
"partial_rotary_factor": 0.75,
|
| 31 |
"quantization_config": {
|
|
|
|
| 32 |
"modules_to_not_convert": null,
|
| 33 |
"quant_method": "torchao",
|
| 34 |
"quant_type": {
|
|
@@ -38,11 +39,18 @@
|
|
| 38 |
"_data": "float8_e4m3fn",
|
| 39 |
"_type": "torch.dtype"
|
| 40 |
},
|
| 41 |
-
"granularity":
|
| 42 |
-
|
| 43 |
-
|
| 44 |
-
|
| 45 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
"mm_config": {
|
| 47 |
"_data": {
|
| 48 |
"emulate": false,
|
|
@@ -62,7 +70,8 @@
|
|
| 62 |
"_version": 1
|
| 63 |
}
|
| 64 |
},
|
| 65 |
-
"quant_type_kwargs": {}
|
|
|
|
| 66 |
},
|
| 67 |
"resid_pdrop": 0.0,
|
| 68 |
"rms_norm_eps": 1e-05,
|
|
@@ -173,7 +182,7 @@
|
|
| 173 |
"sliding_window": 262144,
|
| 174 |
"tie_word_embeddings": true,
|
| 175 |
"torch_dtype": "bfloat16",
|
| 176 |
-
"transformers_version": "4.
|
| 177 |
"use_cache": true,
|
| 178 |
"vocab_size": 200064
|
| 179 |
}
|
|
|
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"auto_map": {
|
| 8 |
+
"AutoConfig": "configuration_phi3.Phi3Config",
|
| 9 |
+
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM",
|
| 10 |
+
"AutoTokenizer": "Xenova/gpt-4o"
|
| 11 |
},
|
| 12 |
"bos_token_id": 199999,
|
| 13 |
"embd_pdrop": 0.0,
|
|
|
|
| 29 |
"pad_token_id": 199999,
|
| 30 |
"partial_rotary_factor": 0.75,
|
| 31 |
"quantization_config": {
|
| 32 |
+
"include_input_output_embeddings": false,
|
| 33 |
"modules_to_not_convert": null,
|
| 34 |
"quant_method": "torchao",
|
| 35 |
"quant_type": {
|
|
|
|
| 39 |
"_data": "float8_e4m3fn",
|
| 40 |
"_type": "torch.dtype"
|
| 41 |
},
|
| 42 |
+
"granularity": [
|
| 43 |
+
{
|
| 44 |
+
"_data": {},
|
| 45 |
+
"_type": "PerRow",
|
| 46 |
+
"_version": 1
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"_data": {},
|
| 50 |
+
"_type": "PerRow",
|
| 51 |
+
"_version": 1
|
| 52 |
+
}
|
| 53 |
+
],
|
| 54 |
"mm_config": {
|
| 55 |
"_data": {
|
| 56 |
"emulate": false,
|
|
|
|
| 70 |
"_version": 1
|
| 71 |
}
|
| 72 |
},
|
| 73 |
+
"quant_type_kwargs": {},
|
| 74 |
+
"untie_embedding_weights": false
|
| 75 |
},
|
| 76 |
"resid_pdrop": 0.0,
|
| 77 |
"rms_norm_eps": 1e-05,
|
|
|
|
| 182 |
"sliding_window": 262144,
|
| 183 |
"tie_word_embeddings": true,
|
| 184 |
"torch_dtype": "bfloat16",
|
| 185 |
+
"transformers_version": "4.53.0.dev0",
|
| 186 |
"use_cache": true,
|
| 187 |
"vocab_size": 200064
|
| 188 |
}
|
generation_config.json
CHANGED
|
@@ -6,5 +6,5 @@
|
|
| 6 |
199999
|
| 7 |
],
|
| 8 |
"pad_token_id": 199999,
|
| 9 |
-
"transformers_version": "4.
|
| 10 |
}
|
|
|
|
| 6 |
199999
|
| 7 |
],
|
| 8 |
"pad_token_id": 199999,
|
| 9 |
+
"transformers_version": "4.53.0.dev0"
|
| 10 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d80b2c8d56ccbc15cf808ead75ba209ca390467538815051185e142e87820d7d
|
| 3 |
+
size 4454508683
|