Parth commited on
Commit
c29f96b
1 Parent(s): af258e8

Upload PhiForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +30 -18
  2. generation_config.json +0 -2
  3. model.safetensors +3 -0
config.json CHANGED
@@ -1,34 +1,46 @@
1
  {
2
  "_name_or_path": "microsoft/phi-2",
 
3
  "architectures": [
4
  "PhiForCausalLM"
5
  ],
6
- "attention_dropout": 0.0,
7
  "auto_map": {
8
  "AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig",
9
  "AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM"
10
  },
11
- "bos_token_id": 50256,
12
  "embd_pdrop": 0.0,
13
- "eos_token_id": 50256,
14
- "hidden_act": "gelu_new",
15
- "hidden_size": 2560,
 
16
  "initializer_range": 0.02,
17
- "intermediate_size": 10240,
18
- "layer_norm_eps": 1e-05,
19
- "max_position_embeddings": 2048,
20
- "model_type": "phi",
21
- "num_attention_heads": 32,
22
- "num_hidden_layers": 32,
23
- "num_key_value_heads": 32,
24
- "partial_rotary_factor": 0.4,
25
- "qk_layernorm": false,
 
 
 
 
 
 
 
 
 
 
 
 
26
  "resid_pdrop": 0.1,
27
- "rope_scaling": null,
28
- "rope_theta": 10000.0,
29
  "tie_word_embeddings": false,
30
- "torch_dtype": "float16",
31
  "transformers_version": "4.37.2",
32
- "use_cache": true,
33
  "vocab_size": 51200
34
  }
 
1
  {
2
  "_name_or_path": "microsoft/phi-2",
3
+ "activation_function": "gelu_new",
4
  "architectures": [
5
  "PhiForCausalLM"
6
  ],
7
+ "attn_pdrop": 0.0,
8
  "auto_map": {
9
  "AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig",
10
  "AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM"
11
  },
 
12
  "embd_pdrop": 0.0,
13
+ "flash_attn": true,
14
+ "flash_rotary": true,
15
+ "fused_dense": true,
16
+ "img_processor": null,
17
  "initializer_range": 0.02,
18
+ "layer_norm_epsilon": 1e-05,
19
+ "model_type": "phi-msft",
20
+ "n_embd": 2560,
21
+ "n_head": 32,
22
+ "n_head_kv": null,
23
+ "n_inner": null,
24
+ "n_layer": 32,
25
+ "n_positions": 2048,
26
+ "pretraining_tp": 1,
27
+ "quantization_config": {
28
+ "bnb_4bit_compute_dtype": "float16",
29
+ "bnb_4bit_quant_type": "nf4",
30
+ "bnb_4bit_use_double_quant": false,
31
+ "llm_int8_enable_fp32_cpu_offload": false,
32
+ "llm_int8_has_fp16_weight": false,
33
+ "llm_int8_skip_modules": null,
34
+ "llm_int8_threshold": 6.0,
35
+ "load_in_4bit": true,
36
+ "load_in_8bit": false,
37
+ "quant_method": "bitsandbytes"
38
+ },
39
  "resid_pdrop": 0.1,
40
+ "rotary_dim": 32,
 
41
  "tie_word_embeddings": false,
42
+ "torch_dtype": "float32",
43
  "transformers_version": "4.37.2",
44
+ "use_cache": false,
45
  "vocab_size": 51200
46
  }
generation_config.json CHANGED
@@ -1,6 +1,4 @@
1
  {
2
  "_from_model_config": true,
3
- "bos_token_id": 50256,
4
- "eos_token_id": 50256,
5
  "transformers_version": "4.37.2"
6
  }
 
1
  {
2
  "_from_model_config": true,
 
 
3
  "transformers_version": "4.37.2"
4
  }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcaec593f72c793a7540b32bde02fc11058b4267768de94d9a32107b6d784124
3
+ size 2468082680