Upload PhiForCausalLM
Browse files- config.json +43 -0
- generation_config.json +4 -0
- model.safetensors +3 -0
config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/phi-1_5",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"PhiForCausalLM"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.0,
|
8 |
+
"auto_map": {
|
9 |
+
"AutoConfig": "microsoft/phi-1_5--configuration_phi.PhiConfig",
|
10 |
+
"AutoModelForCausalLM": "microsoft/phi-1_5--modeling_phi.PhiForCausalLM"
|
11 |
+
},
|
12 |
+
"embd_pdrop": 0.0,
|
13 |
+
"flash_attn": false,
|
14 |
+
"flash_rotary": false,
|
15 |
+
"fused_dense": false,
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"layer_norm_epsilon": 1e-05,
|
18 |
+
"model_type": "phi",
|
19 |
+
"n_embd": 2048,
|
20 |
+
"n_head": 32,
|
21 |
+
"n_head_kv": null,
|
22 |
+
"n_inner": null,
|
23 |
+
"n_layer": 24,
|
24 |
+
"n_positions": 2048,
|
25 |
+
"quantization_config": {
|
26 |
+
"bnb_4bit_compute_dtype": "float32",
|
27 |
+
"bnb_4bit_quant_type": "fp4",
|
28 |
+
"bnb_4bit_use_double_quant": false,
|
29 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
30 |
+
"llm_int8_has_fp16_weight": false,
|
31 |
+
"llm_int8_skip_modules": null,
|
32 |
+
"llm_int8_threshold": 6.0,
|
33 |
+
"load_in_4bit": false,
|
34 |
+
"load_in_8bit": true,
|
35 |
+
"quant_method": "bitsandbytes"
|
36 |
+
},
|
37 |
+
"resid_pdrop": 0.0,
|
38 |
+
"rotary_dim": 32,
|
39 |
+
"tie_word_embeddings": false,
|
40 |
+
"torch_dtype": "float16",
|
41 |
+
"transformers_version": "4.35.2",
|
42 |
+
"vocab_size": 51200
|
43 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"transformers_version": "4.35.2"
|
4 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c15094506975acc018201b41d6bef6556baa0bce9c863e49db1e6ab051223bf
|
3 |
+
size 1649273760
|