README.md

---
tags:
  - medical
  - loRA
  - 4bit
  - conversational
pipeline_tag: text-generation
---

# DeepSeek-V2-medical

This repository contains a 4-bit LoRA adapter fine-tuned on top of [deepseek-ai/DeepSeek-V2-Lite](https://huggingface.co/deepseek-ai/DeepSeek-V2-Lite) for **medical treatment planning**.

- **Base model**: `deepseek-ai/DeepSeek-V2-Lite` (4-bit quantized)  
- **Adapter**: LoRA, trained on clinical vignette → treatment plan pairs  
- **Tokenizer**: same as base, with `pad_token` set to `eos`

## Usage

```python
from transformers import AutoTokenizer, BitsAndBytesConfig
from peft         import PeftModel
import torch

# 1) Load tokenizer + adapter
tokenizer = AutoTokenizer.from_pretrained(
    "CodCodingCode/DeepSeek-V2-medical",
    trust_remote_code=True
)
tokenizer.pad_token_id = tokenizer.pad_token_id or tokenizer.eos_token_id

bnb = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.float16,
)

# 2) Reload the base quantized model
from transformers import AutoModelForCausalLM
base = AutoModelForCausalLM.from_pretrained(
    "deepseek-ai/DeepSeek-V2-Lite",
    quantization_config=bnb,
    device_map="auto",
    trust_remote_code=True,
)
base.resize_token_embeddings(len(tokenizer))

# 3) Attach your LoRA adapter
model = PeftModel.from_pretrained(
    base,
    "CodCodingCode/DeepSeek-V2-medical",
    device_map="auto",
    torch_dtype=torch.float16,
    trust_remote_code=True,
)
model.config.use_cache = False  # match your training config

# 4) Generate
prompt = (
    "### Instruction:\n"
    "You are a board-certified clinician ...\n\n"
    "### Input:\n"
    "THINKING: ...\n\n"
    "### Response:\n"
)
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(
    **inputs,
    max_new_tokens=256,
    do_sample=True,
    temperature=0.2,
    top_p=0.95,
    pad_token_id=tokenizer.pad_token_id,
    eos_token_id=tokenizer.eos_token_id,
)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

This repository contains a 4-bit LoRA fine-tuned adapter on top of [deepseek-ai/DeepSeek-V2-Lite](https://huggingface.co/deepseek-ai/DeepSeek-V2-Lite) for medical treatment planning.

## Model Card

- **Base model:** `deepseek-ai/DeepSeek-V2-Lite` (4-bit quantized)  
- **Adapter:** LoRA, trained on clinical vignette→treatment pairs  
- **Tokenizer:** same as base, with pad_token set to eos  

## Usage

```python
from transformers import AutoTokenizer, BitsAndBytesConfig
from peft        import PeftModel
import torch

# 1) Load tokenizer + adapter
tokenizer = AutoTokenizer.from_pretrained(
    "CodCodingCode/DeepSeek-V2-medical", trust_remote_code=True
)
tokenizer.pad_token_id = tokenizer.pad_token_id or tokenizer.eos_token_id

# 2) Reload quantized base
bnb = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.float16,
)
base = AutoModelForCausalLM.from_pretrained(
    "deepseek-ai/DeepSeek-V2-Lite",
    quantization_config=bnb,
    device_map="auto",
    trust_remote_code=True,
)
base.resize_token_embeddings(len(tokenizer))

# 3) Attach LoRA adapter
model = PeftModel.from_pretrained(
    base,
    "CodCodingCode/DeepSeek-V2-medical",
    device_map="auto",
    trust_remote_code=True,
)
model.config.use_cache = False

# 4) Generate text
prompt = (
    "### Instruction:\n"
    "You are a board-certified clinician. Based on the following patient vignette, "
    "suggest a concise treatment plan:\n\n"
    "### Input:\n"
    "A 65-year-old presents with chronic shortness of breath and persistent cough...\n\n"
    "### Response:\n"
)
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

outputs = model.generate(
    **inputs,
    max_new_tokens=128,
    do_sample=True,
    top_p=0.9,
    temperature=0.8,
    pad_token_id=tokenizer.pad_token_id,
    eos_token_id=tokenizer.eos_token_id,
)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))

# Model Card for Model ID

<!-- Provide a quick summary of what the model is/does. -->




## Model Details

### Model Description

<!-- Provide a longer summary of what this model is. -->



- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]

### Model Sources [optional]

<!-- Provide the basic links for the model. -->

- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]

## Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

### Direct Use

<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->

[More Information Needed]

### Downstream Use [optional]

<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->

[More Information Needed]

### Out-of-Scope Use

<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->

[More Information Needed]

## Bias, Risks, and Limitations

<!-- This section is meant to convey both technical and sociotechnical limitations. -->

[More Information Needed]

### Recommendations

<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

## How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

## Training Details

### Training Data

<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->

[More Information Needed]

### Training Procedure

<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->

#### Preprocessing [optional]

[More Information Needed]


#### Training Hyperparameters

- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->

#### Speeds, Sizes, Times [optional]

<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->

[More Information Needed]

## Evaluation

<!-- This section describes the evaluation protocols and provides the results. -->

### Testing Data, Factors & Metrics

#### Testing Data

<!-- This should link to a Dataset Card if possible. -->

[More Information Needed]

#### Factors

<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->

[More Information Needed]

#### Metrics

<!-- These are the evaluation metrics being used, ideally with a description of why. -->

[More Information Needed]

### Results

[More Information Needed]

#### Summary



## Model Examination [optional]

<!-- Relevant interpretability work for the model goes here -->

[More Information Needed]

## Environmental Impact

<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->

Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).

- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]

## Technical Specifications [optional]

### Model Architecture and Objective

[More Information Needed]

### Compute Infrastructure

[More Information Needed]

#### Hardware

[More Information Needed]

#### Software

[More Information Needed]

## Citation [optional]

<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->

**BibTeX:**

[More Information Needed]

**APA:**

[More Information Needed]

## Glossary [optional]

<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->

[More Information Needed]

## More Information [optional]

[More Information Needed]

## Model Card Authors [optional]

[More Information Needed]

## Model Card Contact

[More Information Needed]
### Framework versions

- PEFT 0.15.2