Hugging Face's logo

Shaleen123
/
phi-2-code

Text Generation
Transformers
Safetensors
phi
custom_code
text-generation-inference
Inference Endpoints
4-bit precision
bitsandbytes
Model card Files Community
Shaleen123 commited on
Commit
d3d3703
•
1 Parent(s): 1743aca

Upload PhiForCausalLM

Browse files
Files changed (2) hide show
  1. config.json +24 -20
  2. model.safetensors +2 -2
config.json CHANGED
@@ -1,29 +1,32 @@
1
  {
2
- "_name_or_path": "/kaggle/input/gemma/transformers/2b/2",
3
  "architectures": [
4
- "GemmaForCausalLM"
5
  ],
6
- "attention_bias": false,
7
  "attention_dropout": 0.0,
8
- "bos_token_id": 2,
9
- "eos_token_id": 1,
10
- "head_dim": 256,
11
- "hidden_act": "gelu",
12
- "hidden_activation": null,
13
- "hidden_size": 2048,
 
 
 
14
  "initializer_range": 0.02,
15
- "intermediate_size": 16384,
16
- "max_position_embeddings": 8192,
17
- "model_type": "gemma",
18
- "num_attention_heads": 8,
19
- "num_hidden_layers": 18,
20
- "num_key_value_heads": 1,
21
- "pad_token_id": 0,
 
 
22
  "quantization_config": {
23
  "_load_in_4bit": true,
24
  "_load_in_8bit": false,
25
  "bnb_4bit_compute_dtype": "float32",
26
- "bnb_4bit_quant_storage": "uint8",
27
  "bnb_4bit_quant_type": "fp4",
28
  "bnb_4bit_use_double_quant": false,
29
  "llm_int8_enable_fp32_cpu_offload": false,
@@ -34,11 +37,12 @@
34
  "load_in_8bit": false,
35
  "quant_method": "bitsandbytes"
36
  },
37
- "rms_norm_eps": 1e-06,
38
  "rope_scaling": null,
39
  "rope_theta": 10000.0,
 
40
  "torch_dtype": "float16",
41
- "transformers_version": "4.39.2",
42
  "use_cache": true,
43
- "vocab_size": 256000
44
  }
 
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
  "quantization_config": {
27
  "_load_in_4bit": true,
28
  "_load_in_8bit": false,
29
  "bnb_4bit_compute_dtype": "float32",
 
30
  "bnb_4bit_quant_type": "fp4",
31
  "bnb_4bit_use_double_quant": false,
32
  "llm_int8_enable_fp32_cpu_offload": false,
 
37
  "load_in_8bit": false,
38
  "quant_method": "bitsandbytes"
39
  },
40
+ "resid_pdrop": 0.1,
41
  "rope_scaling": null,
42
  "rope_theta": 10000.0,
43
+ "tie_word_embeddings": false,
44
  "torch_dtype": "float16",
45
+ "transformers_version": "4.38.2",
46
  "use_cache": true,
47
+ "vocab_size": 51200
48
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f600c06a040311acbe63c114bdc5e40d4c28494b5cdf9e3d5724bed2ee9e18b5
3
- size 2163577968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2538c3e54632bd2851fe0051bd0ccb50e8f8d3ba19c92cb1a1d85d61487a0ba1
3
+ size 1941927016