38 lines
907 B
YAML
38 lines
907 B
YAML
id: qwen3-4b-instruct-2507
|
|
name: Qwen3 4B Instruct 2507
|
|
type: base-model
|
|
task:
|
|
- text
|
|
- chat
|
|
- summarization
|
|
- code
|
|
- tool-use
|
|
- 1c-rag
|
|
language:
|
|
- ru
|
|
- en
|
|
source: huggingface
|
|
upstream_id: Qwen/Qwen3-4B-Instruct-2507
|
|
upstream_url: https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507
|
|
license: apache-2.0
|
|
status: staging
|
|
created_at: 2026-06-18
|
|
storage_path: /models/base/qwen3-4b-instruct-2507
|
|
format: safetensors
|
|
quantization: none
|
|
context_length: 262144
|
|
deployment_context_length: 32768
|
|
vram_required_gb: null
|
|
parameters: 4B
|
|
base_model: null
|
|
adapter_for: null
|
|
datasets: []
|
|
eval_suites:
|
|
- evals/text/smoke.yaml
|
|
deployment:
|
|
target: docker-gpu.cin.su
|
|
runtime: vllm
|
|
served_model_name: qwen3-4b-instruct
|
|
compose: core/deploy/docker-gpu/vllm/compose.yaml
|
|
notes: "First base text model for local inference. Start with 32K context to reduce OOM risk; increase after GPU VRAM is confirmed."
|