Sharpener9290 commited on
Commit
ed81d61
·
verified ·
1 Parent(s): a13acc9

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Model Card for HCUP LLM Humanizer Adapter
2
+
3
+ ## Model Details
4
+ - **Base Model:** mistralai/Mistral-7B-v0.3
5
+ - **Adapter Type:** LoRA (QLoRA 4-bit)
6
+ - **Training:** DPO on clinical writing humanization pairs
7
+
8
+ ## Purpose
9
+ Trained to produce humanized, non-AI-sounding clinical manuscripts using HCUP administrative data patterns.
10
+
11
+ ## Usage
12
+ Load base model + adapter for inference.
13
+
14
+ ## Training Data
15
+ 400 instruction pairs from HCUP corpus (nis, neds, trinetx, hcup_general).
16
+ 50 preference pairs for DPO humanization style transfer.
adapter_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "/home/george/huggingface_models/Mistral-7B-v0.3",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 32,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.05,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 16,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "q_proj",
34
+ "v_proj"
35
+ ],
36
+ "target_parameters": null,
37
+ "task_type": "CAUSAL_LM",
38
+ "trainable_token_indices": null,
39
+ "use_bdlora": null,
40
+ "use_dora": false,
41
+ "use_qalora": false,
42
+ "use_rslora": false
43
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:702fcbc9c9417e6d1671422108b1bb619e322b21454f00e1ecc056da835c508a
3
+ size 27280152
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<s>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "</s>",
7
+ "is_local": true,
8
+ "local_files_only": false,
9
+ "model_max_length": 1000000000000000019884624838656,
10
+ "pad_token": null,
11
+ "sp_model_kwargs": {},
12
+ "spaces_between_special_tokens": false,
13
+ "tokenizer_class": "LlamaTokenizer",
14
+ "unk_token": "<unk>",
15
+ "use_default_system_prompt": false
16
+ }