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)

# pip install -U transformers accelerate
# 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=256)
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
```

Gregory-L commited on 27 days ago

Commit

6a6da4e

verified ·

1 Parent(s): 0d00fc1

the node route, measured: 0.19 tok/s under a 15% CPU cap — it scores, it does not converse

Browse files

Files changed (1) hide show

README.md +15 -2

README.md CHANGED Viewed

@@ -75,7 +75,7 @@ cd mindXtrain39 && ollama create mindXtrain39 -f Modelfile && ollama run mindXtr
 | **mindXhfgradio** [Space](https://huggingface.co/spaces/Gregory-L/mindXhfgradio) | free | the caller's ZeroGPU quota (5 min/day free, 40 PRO; anonymous share a small pool) | Workbench → backend `here`. Sign in with Hugging Face and the minutes are yours |
 | the same Space as an **MCP server** | free | same | add it at [settings/mcp](https://huggingface.co/settings/mcp); `probe` becomes a tool |
 | the same Space by **API** | free | same | `gradio_client` → `/probe`, or its `agents.md` |
-| **mindX's node** | free | the node | served on Ollama as the local responder; reachable from [/huggingface.html](https://mindx.pythai.net/huggingface.html) |
 | Ollama / llama.cpp locally | free | you | `Modelfile` in this repo; the persona's SYSTEM prompt is baked in |
 There is no paid endpoint for this model and none is planned. It is 135M: the cheapest inference is
@@ -100,10 +100,23 @@ Gen 39 is mindX's **local inference responder**: the voice that answers as mindX
 without a provider, a key or a bill. It is deliberately *not* the planner — a 135M model plans nothing.
 Reasoning stays with the cloud/local ladder in `models/*.yaml`; this model answers.
-- served on the node's Ollama (see `GET /insight/hf/models`);
 - the persona's SYSTEM prompt travels with it (`Modelfile`), the same one the Space uses;
 - every exchange is scored and lands in the coach's ledger, so use is also evidence.
 ## 5. How it was trained — `educational.policy`
 [`educational.policy.json`](educational.policy.json) is the reproducible protocol, written from this

 | **mindXhfgradio** [Space](https://huggingface.co/spaces/Gregory-L/mindXhfgradio) | free | the caller's ZeroGPU quota (5 min/day free, 40 PRO; anonymous share a small pool) | Workbench → backend `here`. Sign in with Hugging Face and the minutes are yours |
 | the same Space as an **MCP server** | free | same | add it at [settings/mcp](https://huggingface.co/settings/mcp); `probe` becomes a tool |
 | the same Space by **API** | free | same | `gradio_client` → `/probe`, or its `agents.md` |
+| **mindX's node** | free | the node | served as `mindXtrain39` (alias `mindx-gen39`) — but **measured 0.19 tok/s** (24 tokens in 127 s, plus 85 s cold load) under the node's 15 % CPU cap. It is there for the coach's scoring, not for conversation |
 | Ollama / llama.cpp locally | free | you | `Modelfile` in this repo; the persona's SYSTEM prompt is baked in |
 There is no paid endpoint for this model and none is planned. It is 135M: the cheapest inference is
 without a provider, a key or a bill. It is deliberately *not* the planner — a 135M model plans nothing.
 Reasoning stays with the cloud/local ladder in `models/*.yaml`; this model answers.
+- served on the node's Ollama as `mindXtrain39`, aliased `mindx-gen39` so the coach's convention finds it
+  (`GET /insight/hf/models`), and named in `llm.ollama.local_responder`;
+- **it is the responder, never the planner** — `default_model` stays a larger model, because a 135M model plans nothing;
 - the persona's SYSTEM prompt travels with it (`Modelfile`), the same one the Space uses;
 - every exchange is scored and lands in the coach's ledger, so use is also evidence.
+**Measured on that node, 2026-09-12** (2 vCPU, the service capped at 15 % of the processor):
+| | |
+|---|---|
+| cold load | 85.1 s |
+| prompt eval | 19.8 s |
+| generation | 127.4 s for 24 tokens |
+| **throughput** | **0.19 tokens/second** |
+So the node route is honest but slow: it exists so the coach can score a generation without spending GPU minutes. For anything interactive, run the 135M on your own CPU or use the ZeroGPU Space — both are free and both are faster.
 ## 5. How it was trained — `educational.policy`
 [`educational.policy.json`](educational.policy.json) is the reproducible protocol, written from this