qwen3-8b-medai-cpt_olddata

Instructions to use CompassioninMachineLearning/qwen3-8b-medai-cpt_olddata with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CompassioninMachineLearning/qwen3-8b-medai-cpt_olddata with Transformers:

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

pipe = pipeline("text-generation", model="CompassioninMachineLearning/qwen3-8b-medai-cpt_olddata")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CompassioninMachineLearning/qwen3-8b-medai-cpt_olddata")
model = AutoModelForCausalLM.from_pretrained("CompassioninMachineLearning/qwen3-8b-medai-cpt_olddata", 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 CompassioninMachineLearning/qwen3-8b-medai-cpt_olddata with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CompassioninMachineLearning/qwen3-8b-medai-cpt_olddata"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CompassioninMachineLearning/qwen3-8b-medai-cpt_olddata",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CompassioninMachineLearning/qwen3-8b-medai-cpt_olddata

SGLang

How to use CompassioninMachineLearning/qwen3-8b-medai-cpt_olddata 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 "CompassioninMachineLearning/qwen3-8b-medai-cpt_olddata" \
    --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": "CompassioninMachineLearning/qwen3-8b-medai-cpt_olddata",
		"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 "CompassioninMachineLearning/qwen3-8b-medai-cpt_olddata" \
        --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": "CompassioninMachineLearning/qwen3-8b-medai-cpt_olddata",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use CompassioninMachineLearning/qwen3-8b-medai-cpt_olddata with Docker Model Runner:
```
docker model run hf.co/CompassioninMachineLearning/qwen3-8b-medai-cpt_olddata
```

qwen3-8b-medai-cpt

Continued pre-training (mid-training) of Qwen/Qwen3-8B-Base on the CaML corpus CompassioninMachineLearning/pretraining_research_documents_medai (revision 06248aa). Standalone BF16 weights; no PEFT adapter is needed to load it.

Training

Unsloth, 4-bit base during training, LoRA on all attention and MLP projections (rsLoRA, rank 128, alpha 64, dropout 0.05); embed_tokens and lm_head fully trained at one tenth of the body learning rate.
Learning rate 5e-5, cosine schedule, 5% warmup, weight decay 0.01, effective batch 32 sequences, max length 8192, up to 5 epochs with early stopping on held-out loss. Seed 3407.
Full settings and package versions: training_manifest.json.
LoRA checkpoints: ganscs/Qwen3-8b-qwen-h100-20260909-CPT-LoRA-checkpoints. This export uses checkpoint 750, the best held-out loss of the run (1.2269).

Export

Merged with Unsloth save_pretrained_merged(save_method="merged_16bit") from checkpoint 750 into the original BF16 base weights (base revision 49e3418), 2026-09-10. An earlier upload of the same checkpoint merged with a hand-written PEFT script (ganscs/Qwen3-8b-qwen-h100-20260909-CPT-merged-step-750) was compared tensor by tensor against this export: identical names, shapes and dtypes; all non-LoRA tensors bit-identical; the LoRA-merged projections agree to within one bf16 rounding step.

Load

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "CompassioninMachineLearning/qwen3-8b-medai-cpt"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, dtype=torch.bfloat16, device_map="auto")

Downloads last month: 148

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for CompassioninMachineLearning/qwen3-8b-medai-cpt_olddata

Base model

Qwen/Qwen3-8B-Base

Finetuned

(557)

this model

qwen3-8b-medai-cpt

Training

Export

Load

Model tree for CompassioninMachineLearning/qwen3-8b-medai-cpt_olddata

Dataset used to train CompassioninMachineLearning/qwen3-8b-medai-cpt_olddata