Switch model source to gdubicki/Qwen3-Coder-Next-NVFP4-GB10

README.md

@@ -1,6 +1,6 @@
-# saricles/Qwen3-Coder-Next-NVFP4-GB10 on DGX Spark (GB10)
+# gdubicki/Qwen3-Coder-Next-NVFP4-GB10 on DGX Spark (GB10)
 
-Runs [`saricles/Qwen3-Coder-Next-NVFP4-GB10`](https://huggingface.co/saricles/Qwen3-Coder-Next-NVFP4-GB10) via vLLM with an OpenAI-compatible API endpoint.
+Runs [`gdubicki/Qwen3-Coder-Next-NVFP4-GB10`](https://huggingface.co/gdubicki/Qwen3-Coder-Next-NVFP4-GB10) (quantized by [saricles](https://huggingface.co/saricles/Qwen3-Coder-Next-NVFP4-GB10)) via vLLM with an OpenAI-compatible API endpoint.
 Tested on DGX Spark (GB10 Blackwell, SM12.1, 128 GB unified LPDDR5X).
 
 ## Model overview
@@ -51,7 +51,7 @@ Qwen3-Coder-Next is 80B total but 3B active — same throughput as Nemotron-3-Na
 ## Quick start
 
 ```bash
-# Required — model is gated on Hugging Face (accept license at saricles/Qwen3-Coder-Next-NVFP4-GB10 first):
+# Required — model is gated on Hugging Face (accept license at gdubicki/Qwen3-Coder-Next-NVFP4-GB10 first):
 export HF_TOKEN=hf_xxxx
 
 bash start-qwen3-coder-next.sh
@@ -78,12 +78,12 @@ Reasoning is **ON by default**. Toggle per request:
 # Reasoning OFF
 curl -s -X POST http://localhost:8000/v1/chat/completions \
   -H "Content-Type: application/json" \
-  -d '{"model":"saricles/Qwen3-Coder-Next-NVFP4-GB10","messages":[{"role":"user","content":"What is the capital of France?"}],"max_tokens":60,"chat_template_kwargs":{"enable_thinking":false}}'
+  -d '{"model":"gdubicki/Qwen3-Coder-Next-NVFP4-GB10","messages":[{"role":"user","content":"What is the capital of France?"}],"max_tokens":60,"chat_template_kwargs":{"enable_thinking":false}}'
 
 # Reasoning ON (default)
 curl -s -X POST http://localhost:8000/v1/chat/completions \
   -H "Content-Type: application/json" \
-  -d '{"model":"saricles/Qwen3-Coder-Next-NVFP4-GB10","messages":[{"role":"user","content":"Write a binary search implementation in Python."}],"max_tokens":2000,"chat_template_kwargs":{"enable_thinking":true}}'
+  -d '{"model":"gdubicki/Qwen3-Coder-Next-NVFP4-GB10","messages":[{"role":"user","content":"Write a binary search implementation in Python."}],"max_tokens":2000,"chat_template_kwargs":{"enable_thinking":true}}'
 ```
 
 ## Cline configuration
@@ -95,7 +95,7 @@ curl -s -X POST http://localhost:8000/v1/chat/completions \
 |-------|-------|
 | Provider | OpenAI Compatible |
 | Base URL | `http://<spark-ip>:8000/v1` |
-| Model ID | `saricles/Qwen3-Coder-Next-NVFP4-GB10` |
+| Model ID | `gdubicki/Qwen3-Coder-Next-NVFP4-GB10` |
 | API Key | `dummy` (any non-empty string) |
 
 ## Files
@@ -147,6 +147,6 @@ vLLM auto-detects quantization from `quantization_config` in `config.json`; no `
 
 - Docker with `nvidia-container-toolkit`
 - Image: `vllm/vllm-openai:cu130-nightly`
-- HF token with access to `saricles/Qwen3-Coder-Next-NVFP4-GB10` (gated — accept license first)
+- HF token with access to `gdubicki/Qwen3-Coder-Next-NVFP4-GB10` (gated — accept license first)
 - Model weights cached locally (auto-downloaded on first run, ~45 GB):
   `~/.cache/huggingface/hub/models--saricles--Qwen3-Coder-Next-NVFP4-GB10/`

docker-run.sh

@@ -27,7 +27,7 @@ docker run \
     -e VLLM_MARLIN_USE_ATOMIC_ADD=1 \
     ${HF_TOKEN:+-e HF_TOKEN="${HF_TOKEN}"} \
     vllm/vllm-openai:cu130-nightly \
-    saricles/Qwen3-Coder-Next-NVFP4-GB10 \
+    gdubicki/Qwen3-Coder-Next-NVFP4-GB10 \
     --dtype auto \
     --gpu-memory-utilization 0.90 \
     --kv-cache-dtype fp8 \

start-qwen3-coder-next.sh

@@ -18,7 +18,7 @@ set -euo pipefail
 # ---------------------------------------------------------------------------
 CONTAINER_NAME="qwen3-coder-next-vllm"
 IMAGE="vllm/vllm-openai:cu130-nightly"
-MODEL="saricles/Qwen3-Coder-Next-NVFP4-GB10"
+MODEL="gdubicki/Qwen3-Coder-Next-NVFP4-GB10"
 PORT=8000
 MAX_MODEL_LEN="${MAX_MODEL_LEN:-262144}"