phi-2-mental-health
Browse files- README.md +13 -0
- config.json +45 -0
README.md
CHANGED
|
@@ -6,6 +6,7 @@ tags:
|
|
| 6 |
model-index:
|
| 7 |
- name: results
|
| 8 |
results: []
|
|
|
|
| 9 |
---
|
| 10 |
|
| 11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -29,6 +30,17 @@ More information needed
|
|
| 29 |
|
| 30 |
## Training procedure
|
| 31 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
### Training hyperparameters
|
| 33 |
|
| 34 |
The following hyperparameters were used during training:
|
|
@@ -49,6 +61,7 @@ The following hyperparameters were used during training:
|
|
| 49 |
|
| 50 |
### Framework versions
|
| 51 |
|
|
|
|
| 52 |
- Transformers 4.31.0
|
| 53 |
- Pytorch 2.1.0+cu118
|
| 54 |
- Datasets 3.0.1
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: results
|
| 8 |
results: []
|
| 9 |
+
library_name: peft
|
| 10 |
---
|
| 11 |
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 30 |
|
| 31 |
## Training procedure
|
| 32 |
|
| 33 |
+
|
| 34 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 35 |
+
- load_in_8bit: False
|
| 36 |
+
- load_in_4bit: True
|
| 37 |
+
- llm_int8_threshold: 6.0
|
| 38 |
+
- llm_int8_skip_modules: None
|
| 39 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 40 |
+
- llm_int8_has_fp16_weight: False
|
| 41 |
+
- bnb_4bit_quant_type: nf4
|
| 42 |
+
- bnb_4bit_use_double_quant: False
|
| 43 |
+
- bnb_4bit_compute_dtype: float16
|
| 44 |
### Training hyperparameters
|
| 45 |
|
| 46 |
The following hyperparameters were used during training:
|
|
|
|
| 61 |
|
| 62 |
### Framework versions
|
| 63 |
|
| 64 |
+
- PEFT 0.4.0
|
| 65 |
- Transformers 4.31.0
|
| 66 |
- Pytorch 2.1.0+cu118
|
| 67 |
- Datasets 3.0.1
|
config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
},
|
| 38 |
+
"resid_pdrop": 0.1,
|
| 39 |
+
"rotary_dim": 32,
|
| 40 |
+
"tie_word_embeddings": false,
|
| 41 |
+
"torch_dtype": "float16",
|
| 42 |
+
"transformers_version": "4.31.0",
|
| 43 |
+
"use_cache": false,
|
| 44 |
+
"vocab_size": 51200
|
| 45 |
+
}
|