Upload Phi3ForCausalLM
Browse files- config.json +23 -16
- generation_config.json +8 -6
- model.safetensors +3 -0
config.json
CHANGED
@@ -1,29 +1,34 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
"attention_bias": false,
|
7 |
"attention_dropout": 0.0,
|
8 |
-
"
|
9 |
-
|
|
|
|
|
|
|
|
|
|
|
10 |
"hidden_act": "silu",
|
11 |
-
"hidden_size":
|
12 |
"initializer_range": 0.02,
|
13 |
-
"intermediate_size":
|
14 |
-
"max_position_embeddings":
|
15 |
-
"
|
16 |
-
"model_type": "llama",
|
17 |
"num_attention_heads": 32,
|
18 |
"num_hidden_layers": 32,
|
19 |
-
"num_key_value_heads":
|
20 |
-
"
|
|
|
21 |
"quantization_config": {
|
22 |
"_load_in_4bit": true,
|
23 |
"_load_in_8bit": false,
|
24 |
-
"bnb_4bit_compute_dtype": "
|
25 |
"bnb_4bit_quant_storage": "uint8",
|
26 |
-
"bnb_4bit_quant_type": "
|
27 |
"bnb_4bit_use_double_quant": false,
|
28 |
"llm_int8_enable_fp32_cpu_offload": false,
|
29 |
"llm_int8_has_fp16_weight": false,
|
@@ -33,12 +38,14 @@
|
|
33 |
"load_in_8bit": false,
|
34 |
"quant_method": "bitsandbytes"
|
35 |
},
|
|
|
36 |
"rms_norm_eps": 1e-05,
|
37 |
"rope_scaling": null,
|
38 |
-
"rope_theta":
|
|
|
39 |
"tie_word_embeddings": false,
|
40 |
"torch_dtype": "float32",
|
41 |
"transformers_version": "4.41.2",
|
42 |
-
"use_cache":
|
43 |
-
"vocab_size":
|
44 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
|
3 |
"architectures": [
|
4 |
+
"Phi3ForCausalLM"
|
5 |
],
|
6 |
"attention_bias": false,
|
7 |
"attention_dropout": 0.0,
|
8 |
+
"auto_map": {
|
9 |
+
"AutoConfig": "microsoft/Phi-3-mini-4k-instruct--configuration_phi3.Phi3Config",
|
10 |
+
"AutoModelForCausalLM": "microsoft/Phi-3-mini-4k-instruct--modeling_phi3.Phi3ForCausalLM"
|
11 |
+
},
|
12 |
+
"bos_token_id": 1,
|
13 |
+
"embd_pdrop": 0.0,
|
14 |
+
"eos_token_id": 32000,
|
15 |
"hidden_act": "silu",
|
16 |
+
"hidden_size": 3072,
|
17 |
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 8192,
|
19 |
+
"max_position_embeddings": 4096,
|
20 |
+
"model_type": "phi3",
|
|
|
21 |
"num_attention_heads": 32,
|
22 |
"num_hidden_layers": 32,
|
23 |
+
"num_key_value_heads": 32,
|
24 |
+
"original_max_position_embeddings": 4096,
|
25 |
+
"pad_token_id": 32000,
|
26 |
"quantization_config": {
|
27 |
"_load_in_4bit": true,
|
28 |
"_load_in_8bit": false,
|
29 |
+
"bnb_4bit_compute_dtype": "float32",
|
30 |
"bnb_4bit_quant_storage": "uint8",
|
31 |
+
"bnb_4bit_quant_type": "fp4",
|
32 |
"bnb_4bit_use_double_quant": false,
|
33 |
"llm_int8_enable_fp32_cpu_offload": false,
|
34 |
"llm_int8_has_fp16_weight": false,
|
|
|
38 |
"load_in_8bit": false,
|
39 |
"quant_method": "bitsandbytes"
|
40 |
},
|
41 |
+
"resid_pdrop": 0.0,
|
42 |
"rms_norm_eps": 1e-05,
|
43 |
"rope_scaling": null,
|
44 |
+
"rope_theta": 10000.0,
|
45 |
+
"sliding_window": 2047,
|
46 |
"tie_word_embeddings": false,
|
47 |
"torch_dtype": "float32",
|
48 |
"transformers_version": "4.41.2",
|
49 |
+
"use_cache": true,
|
50 |
+
"vocab_size": 32064
|
51 |
}
|
generation_config.json
CHANGED
@@ -1,9 +1,11 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
-
"eos_token_id":
|
5 |
-
|
6 |
-
|
7 |
-
|
|
|
|
|
8 |
"transformers_version": "4.41.2"
|
9 |
}
|
|
|
1 |
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": [
|
5 |
+
32000,
|
6 |
+
32001,
|
7 |
+
32007
|
8 |
+
],
|
9 |
+
"pad_token_id": 32000,
|
10 |
"transformers_version": "4.41.2"
|
11 |
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab5426c1ad1d14ae1dfb0f4261c018e5f3e0e818ade37f80c804d04b2ac63e8e
|
3 |
+
size 2827324312
|