Downloads · 30 days
8
12% of all-time downloads
YMRohit/rohit-portfolio-lfm25-350m-onnx
rohit-portfolio-lfm25-350m-onnx is a text generation model from YMRohit. Use it when you need the model to write or continue text. It is set up for transformers.js. The card lists the license as other.
Q4 ONNX export of a browser-local portfolio agent fine-tuned from LiquidAI/LFM2.5-350M.
Downloads · 30 days
8
12% of all-time downloads
All-time downloads
67
Public
Repo size
289 MB
Likes
0
Public
Click a slice to open those files.
.onnx_data289 MB · 98%
From the Hugging Face model README
Q4 ONNX export of a browser-local portfolio agent fine-tuned from LiquidAI/LFM2.5-350M.
The model is trained to return strict JSON packets for a static website agent:
{"title":"...","say":"...","actions":[{"name":"openProject","args":{"id":"..."}}],"citations":["..."]}
It is designed for client-side execution with Transformers.js/WebGPU and a separate browser-side action validator. The training data uses curated public portfolio summaries and synthetic interaction examples; it is not intended to expose raw CV/PDF text, private records, schemas, patient data, supplier data, or customer data.
onnx/model_q4.onnxonnx/model_q4.onnx_datastrict_eval_q4_500.jsonThe exported Q4 ONNX artifact passed the held-out strict browser-agent eval:
full_json: 1.0json_object: 1.0strict_valid: 1.0action_exact: 1.0citation_exact: 1.0import { AutoModelForCausalLM, AutoTokenizer } from "@huggingface/transformers";
const modelId = "YMRohit/rohit-portfolio-lfm25-350m-onnx";
const tokenizer = await AutoTokenizer.from_pretrained(modelId);
const model = await AutoModelForCausalLM.from_pretrained(modelId, {
device: "webgpu",
dtype: "q4",
});