Instructions to use rwang220/Yida-Model-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rwang220/Yida-Model-14B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="rwang220/Yida-Model-14B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rwang220/Yida-Model-14B")
model = AutoModelForCausalLM.from_pretrained("rwang220/Yida-Model-14B", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use rwang220/Yida-Model-14B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rwang220/Yida-Model-14B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rwang220/Yida-Model-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rwang220/Yida-Model-14B

SGLang

How to use rwang220/Yida-Model-14B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "rwang220/Yida-Model-14B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rwang220/Yida-Model-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "rwang220/Yida-Model-14B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rwang220/Yida-Model-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rwang220/Yida-Model-14B with Docker Model Runner:
```
docker model run hf.co/rwang220/Yida-Model-14B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Yida-Model-14B

Yida-Model-14B is a merged full-weight checkpoint of Qwen/Qwen3-14B after LoRA supervised fine-tuning on an internal Chinese medical instruction mix. The Hub files are the merged bfloat16 weights (not a PEFT adapter).

This model is for research and engineering evaluation. It is not a medical device and must not be used as the sole basis for clinical decisions.

Model Details

Developed by: rwang220
Model type: Causal language model (Qwen3ForCausalLM)
Parameters: 14.77B (14,768,307,200)
Precision: bfloat16
Architecture: 40 layers, hidden size 5120, GQA 40/8, intermediate size 17408, vocab 151936
Context: max_position_embeddings is 40,960. RoPE is default (no YaRN in this checkpoint). Tokenizer model_max_length is 131,072; SFT used 8,192.
Chat template: Qwen3 thinking / tool-calling Jinja template (chat_template.jinja)
Language(s): Chinese and English (training mix is primarily Chinese medical tasks)
License: Apache 2.0, inherited from Qwen3-14B

Training

Fine-tuned with ms-swift LoRA, then merged into full weights. Training code is not published.

Item	Value
Base model	Qwen/Qwen3-14B
Framework	ms-swift 4.0.2, PEFT 0.18.0, transformers 5.3.0.dev0, torch 2.9.0+cu128
Hardware	4 GPUs, DDP
Run	`all_14b_9.4/v0-20260904-061558`
Start / end	2026-09-04 06:16 → 2026-09-09 19:02
LoRA	rank 16, alpha 32, dropout 0.05, targets `q/k/v/o/gate/up/down_proj`
Optim	fused AdamW, lr `1e-4`, cosine, warmup ratio 0.05, weight decay 0.1
Schedule	4 epochs, 47,384 steps, max length 8192
Batch	per-device 1, grad accum 8 (global batch 32)
Final train loss	0.5922
Final eval loss	0.5709, token acc 0.8124
Last / best ckpt	`checkpoint-47384`
Merge	6 safetensor shards (`max_shard_size=5GB`)

Data

Internal medical SFT mix (merged_scores_v4_three_models_score5 / prefix-optimized CoT). Most categories were capped at 10,000 samples; MedSafety and MedEthics at 30,000. Validation used 10,000 held-out samples.

Included task families (names from the training registry): CMB-Clin-extended, MedAnalysis, MedCare, MedChartQC, MedDiag, MedDiffer, MedEthics, MedExam, MedExplain, MedHC, MedHG, MedInsureCalc, MedInsureCheck, MedLitQA, MedMC, MedOutcome, MedPHM, MedPathQC, MedPopular, MedPrimary, MedPsychCare, MedPsychQA, MedRecordGen, MedRehab, MedReportQC, MedRxCheck, MedRxPlan, MedSafety, MedSpeQA, MedSummary, MedSynonym, MedTeach, MedTerm, MedTreat, SMDoc.

How to Use

Requires a recent transformers with Qwen3 support (the export was written by transformers 5.5.0).

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "rwang220/Yida-Model-14B"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="auto",
)

messages = [{"role": "user", "content": "请用通俗语言解释高血压的常见注意事项。"}]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True,
)
inputs = tokenizer([text], return_tensors="pt").to(model.device)
output = model.generate(**inputs, max_new_tokens=1024, temperature=0.6, top_p=0.95, top_k=20)
print(tokenizer.decode(output[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))

vLLM:

vllm serve rwang220/Yida-Model-14B --reasoning-parser qwen3

Default sampling in generation_config.json: temperature 0.6, top_p 0.95, top_k 20.

Set enable_thinking=False in apply_chat_template for the non-thinking path.

Files

model-00001-of-00006.safetensors … model-00006-of-00006.safetensors
model.safetensors.index.json
config.json, generation_config.json
tokenizer.json, tokenizer_config.json, vocab.json, merges.txt
chat_template.jinja
LICENSE (Apache-2.0)

Total Hub payload is about 27.5 GiB (~29.5 GB): six bf16 shards plus tokenizer and card files.

Intended Use and Limitations

Intended for research on Chinese medical dialogue, chart/report drafting, and related NLP prototypes.

Limitations:

Can hallucinate guidelines, doses, diagnoses, and citations.
Training data is internal and not fully documented here.
Evaluation in this card is training/eval loss only; no public clinical benchmark is claimed.
Outputs may mix thinking traces (<think>…</think>) with the final answer.

Citation

@misc{yida-model-14b,
  title        = {Yida-Model-14B},
  author       = {Wang, Rui},
  year         = {2026},
  howpublished = {\url{https://huggingface.co/rwang220/Yida-Model-14B}},
  note         = {Code and docs: https://github.com/rwang220/yida_model}
}

Also cite Qwen3.

Downloads last month: 432

Safetensors

Model size

15B params

Tensor type

BF16

Model tree for rwang220/Yida-Model-14B

Base model

Qwen/Qwen3-14B-Base

Finetuned

Qwen/Qwen3-14B

Finetuned

(350)

this model

Quantizations

1 model