CoolFace
Modelpublic

skillsafe-ai/qwen2.5-coder-1.5b-instruct-q4f16

sourceHugging Faceapache-2.0updated 4d agoView on Hugging Face
0likes
Model Card

Qwen2.5-Coder-1.5B-Instruct (q4f16_1, WebLLM)

Browser-ready mlc artifacts for text-generation, produced by SkillSafe's reproducible converter (`models/` in skillsafe.ai) from a pinned upstream source. Every byte here is derivable from that source plus the recipe below; nothing was edited by hand.

Provenance

Upstreamhttps://huggingface.co/mlc-ai/Qwen2.5-Coder-1.5B-Instruct-q4f16_1-MLC/tree/30184a4f713a9aaf6c548ace1290615d0ea041ff
Upstream SHA-256 / commit30184a4f713a9aaf6c548ace1290615d0ea041ff
Reciperecipes/qwen2.5-coder-1.5b-instruct-q4f16.yaml — sha256 856bf330211f9b380a4db453e7bb9210fa8ef12a407f4c7cf4bfc5e69bebdc3d
ToolchainPython 3.12.13, torch 2.10.0, onnx 1.23.0, onnxruntime 1.30.0 on Darwin 25.6.0 arm64
Converted2026-09-22T19:01:36+00:00

Files

fileclasssizeSHA-256
lib/Qwen2-1.5B-Instruct-q4f16_1-ctx4k_cs1k-webgpu.wasmregistry-shared5.13 MB6cd9f132ad258d2017291bb62e955e337f8ae4af74650f4b1ea5a803a7cec538
merges.txtbundle1.59 MB599bab54075088774b1733fde865d5bd747cbcc7a547c5bc12610e874e26f5e3
mlc-chat-config.jsonbundle0.00 MB6d107fd373b38735558d7a8b831549b5e608fe60917c96b496fc44f9cd80e1dd
ndarray-cache.jsonbundle0.12 MB26efc81e694ace258ebce34cba51e26099a62e7d93946f4de12c55f0a5e61ccb
params_shard_0.binregistry111.28 MB3c312ff8880afccbdf3c3e8d8190cf34a8d1c9279f4b28335f1919659c178e66
params_shard_1.binregistry21.30 MBe9746bfae16430c855df30ccdb373216c53ea844be42b22fa13e5e31f64b8cf0
params_shard_10.binregistry25.11 MBc2de8982284a3ecf1d57b521dcdf80a3dfa7ec81024893982780be3e30d4ecda
params_shard_11.binregistry25.11 MBfe3fb13462cb9247d5bc54fda987f7d4f0e3e19e3afc0a5129db214a89012227
params_shard_12.binregistry25.11 MB6e2428c621f859cf6a715315cfaa25236ce06d887bd327e70f494e46ba671dcb
params_shard_13.binregistry25.11 MBc351eb26223c417e13a422910f10d624056a943b004d3d306a5c0a7c567ca476
params_shard_14.binregistry25.11 MB32466b2c68c1b1012ffd7f37a10950fce540db475af71a15268347bb995cb134
params_shard_15.binregistry25.11 MB11fbd058b080ae2692efd55b082807c5df104a45cdee1ae8a44a1f3ad993b5e2
params_shard_16.binregistry25.11 MB88ca4f3c3b5ff8e927b7c1326b4a5225b31a1668b967e23ad72556ff8c9c134b
params_shard_17.binregistry25.11 MB27cb36c5b409ef3b9c59fb2ec13d1e40385321e720b92ad3b7183eb5f7a9f42a
params_shard_18.binregistry25.11 MB4dd21bf71bb109133cd0a9ac12eedf71d6a52953f0ba1bd1362358beb08b9f7d
params_shard_19.binregistry25.11 MB63595695c796f364978c8e8ec4c73a3e9b9f7223d0f50b0619eb92b235d9c4aa
params_shard_2.binregistry25.11 MB7123276d20fc071c8ae9525e7b5889aa770fb1f2c275f2b0ede97838abf52b3a
params_shard_20.binregistry25.11 MBe74ac3965a66228ce39066f7740b41506ae973a7077fcb8bb3570f6bfb35d05b
params_shard_21.binregistry25.11 MB8cdac59722badd047a60273334ff274fe3c4b2061f71a50fe71adbe0d63b19b5
params_shard_22.binregistry25.11 MB7355b4a63af1d4fd215d2f63e96b99212a75ab8f6597dace4b655eeaab980320
params_shard_23.binregistry25.11 MB6880182ff40842b9843b4f510488781837488ad602f24e21c89cbbe630618a68
params_shard_24.binregistry25.11 MB5147a10cfb113a346e9db6a52c15abaeda962aae48f3083431071a7b74d569b3
params_shard_25.binregistry25.11 MBa9f8b1eb8f838ed18efce0062ff310b7ab5b0ccabea58ddc73bf3e6047b7b131
params_shard_26.binregistry25.11 MBbbafb40e746d59bd6f222b8ea9d5c6f269dcb09ddba1195832dca9fd1a1659d9
params_shard_27.binregistry25.11 MB274552455f7ead7f1494c8e995508a0c633f84d2d4d1d28f1111dfcabb3a5e1c
params_shard_28.binregistry25.11 MB84fb8349cac7b45cb6914ae65642df9a6afe9c35cbcce22a7f2077c0c2057777
params_shard_29.binregistry17.73 MBcc09bf175d86320bd3c7721f26eccc497c3b2c544e54f4d7ab1f334f001bd8fc
params_shard_3.binregistry25.11 MB113c72600912d1f34d61782b43a9f630005cf3926c6362eeed4ab3e1f5384672
params_shard_4.binregistry25.11 MB384e14ea7e1fb360e81052ec130919f845b00839a2a801697ca62dcb21280044
params_shard_5.binregistry25.11 MB8830daa29ffc13cd39b7726387773ca4c08745edf1640873365f0d7e06a866b5
params_shard_6.binregistry25.11 MB3693fc3c41037cbc0dad775d95e9461756411625c5da9beac07c6f0173c22ea0
params_shard_7.binregistry25.11 MBae42f18931f0e0aa8e1ac03c3a78abff4fca148ff04cdee55506d74bccff0541
params_shard_8.binregistry25.11 MB408bb892e85d5b306a008b8cbc3e49913802d2c23167de339280015a4c392a84
params_shard_9.binregistry25.11 MB5ce5e702e4b902ccbb61b5a819dc3bf9659ac088034049fc464100d96bdaa741
tensor-cache.jsonbundle0.12 MB26efc81e694ace258ebce34cba51e26099a62e7d93946f4de12c55f0a5e61ccb
tokenizer.jsonbundle6.71 MBc0382117ea329cdf097041132f6d735924b697924d6f6fc3945713e96ce87539
tokenizer_config.jsonbundle0.01 MB006da433cdc0e70f05759008ef5d8d82721e3cbd95bd4831d394f96c54230680
vocab.jsonbundle2.65 MBca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910

registry files are parameter files served from models.skillsafe.ai once vetted; bundle files ship inside an app; registry-shared is a runtime library reused by every model of the same architecture.

Verification

Shard sizes and md5s match ndarray-cache.json; the implied parameter count matches the checkpoint (1,543,714,304 parameters, 4.50 bits/param); the parameter table embedded in the WebGPU model library matches all 311 tensors of these weights.

Use in the browser (WebLLM)

js
import { CreateMLCEngine } from "@mlc-ai/web-llm";
const engine = await CreateMLCEngine("qwen2.5-coder-1.5b-instruct-q4f16", {
  appConfig: { model_list: [{
    model: "https://huggingface.co/skillsafe-ai/qwen2.5-coder-1.5b-instruct-q4f16",
    model_id: "qwen2.5-coder-1.5b-instruct-q4f16",
    model_lib: "https://huggingface.co/skillsafe-ai/qwen2.5-coder-1.5b-instruct-q4f16/resolve/main/lib/Qwen2-1.5B-Instruct-q4f16_1-ctx4k_cs1k-webgpu.wasm",
    overrides: { context_window_size: 4096, prefill_chunk_size: 1024 },
  }] },
});

The model library is compiled for context window 4096 / prefill chunk 1024; mlc-chat-config.json says 32768 / 2048, so set the overrides above.

Licence and attribution

Qwen2.5-Coder-1.5B-Instruct: Copyright 2024 Alibaba Cloud. Apache License 2.0. https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct — q4f161 weights published by MLC (https://huggingface.co/mlc-ai/Qwen2.5-Coder-1.5B-Instruct-q4f161-MLC).

Licence: Apache-2.0 — notice: https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct/blob/2e1fd397ee46e1388853d2af2c993145b0f1098a/LICENSE. The conversion recipe and this model card are part of the SkillSafe repository and carry its licence; the weights remain under the upstream licence above.

The full manifest.json in this repo records the recipe, sources, toolchain (including the uv.lock hash) and per-file verification numbers.