Instructions to use PYTHAI/mindXtrain39 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PYTHAI/mindXtrain39 with Transformers:

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

pipe = pipeline("text-generation", model="PYTHAI/mindXtrain39")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PYTHAI/mindXtrain39")
model = AutoModelForCausalLM.from_pretrained("PYTHAI/mindXtrain39", 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 PYTHAI/mindXtrain39 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PYTHAI/mindXtrain39"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PYTHAI/mindXtrain39",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/PYTHAI/mindXtrain39

SGLang

How to use PYTHAI/mindXtrain39 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 "PYTHAI/mindXtrain39" \
    --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": "PYTHAI/mindXtrain39",
		"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 "PYTHAI/mindXtrain39" \
        --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": "PYTHAI/mindXtrain39",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use PYTHAI/mindXtrain39 with Docker Model Runner:
```
docker model run hf.co/PYTHAI/mindXtrain39
```

mindXtrain39 / bootcamp.impression.json

Gregory-L

the full card: THOT + iNFT facets, educational.policy, bootcamp.impression / impression.bootcamp, machine-readable card

0d00fc1 verified 11 days ago

Raw

History Blame Contribute Delete

1.19 kB

	{
	"routine": "bootcamp.impression",
	"version": 1,
	"direction": "drill → impression: take a persona and a corpus, and press them into weights",
	"input": {
	"persona": "a mindX .persona (system prompt + voice examples + exchanges)",
	"corpus": "curated machine.dream rows, persona share configurable (15% default, higher in a persona sprint)",
	"regimen": "cpu_percent, wall window, epochs — the host's own profile, not a guess"
	},
	"drill": [
	"build the corpus (corpus.build_curated) with source weights from the last imprint's attribution",
	"train under the recipe (LoRA on attention projections; packing; eval split held out)",
	"probe the frozen base on the battery FIRST — that is 'before'",
	"probe the trained model on the same battery — that is 'after'",
	"impression = after − before, per probe and in the mean"
	],
	"output": {
	"impression": "the measured delta (recall, coherence, identity, task)",
	"verdict": "accepted / proof_rejected — the gate decides, not the operator",
	"artifacts": "adapter + merged weights + train.log + THOT"
	},
	"exemplar": {
	"generation": 39,
	"impression": {
	"delta_recall": 0.1002
	},
	"verdict": "accepted"
	}
	}