EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

smaller and non gated models for docs (#5378)

Browse Source
This commit is contained in:
simveit
2025-04-21 02:38:25 +02:00
committed by GitHub
parent fac17acf08
commit 8de53da989
6 changed files with 51 additions and 44 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
docs/backend/openai_api_embeddings.ipynb
View File

@@ -40,7 +40,7 @@
"\n",
"embedding_process, port = launch_server_cmd(\n",
" \"\"\"\n",
"python -m sglang.launch_server --model-path Alibaba-NLP/gte-Qwen2-7B-instruct \\\n",
"python3 -m sglang.launch_server --model-path Alibaba-NLP/gte-Qwen2-1.5B-instruct \\\n",
" --host 0.0.0.0 --is-embedding\n",
"\"\"\"\n",
")\n",
@@ -66,7 +66,7 @@
"text = \"Once upon a time\"\n",
"\n",
"curl_text = f\"\"\"curl -s http://localhost:{port}/v1/embeddings \\\n",
" -d '{{\"model\": \"Alibaba-NLP/gte-Qwen2-7B-instruct\", \"input\": \"{text}\"}}'\"\"\"\n",
" -d '{{\"model\": \"Alibaba-NLP/gte-Qwen2-1.5B-instruct\", \"input\": \"{text}\"}}'\"\"\"\n",
"\n",
"text_embedding = json.loads(subprocess.check_output(curl_text, shell=True))[\"data\"][0][\n",
" \"embedding\"\n",
@@ -94,7 +94,7 @@
"\n",
"response = requests.post(\n",
" f\"http://localhost:{port}/v1/embeddings\",\n",
" json={\"model\": \"Alibaba-NLP/gte-Qwen2-7B-instruct\", \"input\": text},\n",
" json={\"model\": \"Alibaba-NLP/gte-Qwen2-1.5B-instruct\", \"input\": text},\n",
")\n",
"\n",
"text_embedding = response.json()[\"data\"][0][\"embedding\"]\n",
@@ -121,7 +121,7 @@
"\n",
"# Text embedding example\n",
"response = client.embeddings.create(\n",
" model=\"Alibaba-NLP/gte-Qwen2-7B-instruct\",\n",
" model=\"Alibaba-NLP/gte-Qwen2-1.5B-instruct\",\n",
" input=text,\n",
")\n",
"\n",
@@ -150,11 +150,11 @@
"\n",
"os.environ[\"TOKENIZERS_PARALLELISM\"] = \"false\"\n",
"\n",
"tokenizer = AutoTokenizer.from_pretrained(\"Alibaba-NLP/gte-Qwen2-7B-instruct\")\n",
"tokenizer = AutoTokenizer.from_pretrained(\"Alibaba-NLP/gte-Qwen2-1.5B-instruct\")\n",
"input_ids = tokenizer.encode(text)\n",
"\n",
"curl_ids = f\"\"\"curl -s http://localhost:{port}/v1/embeddings \\\n",
" -d '{{\"model\": \"Alibaba-NLP/gte-Qwen2-7B-instruct\", \"input\": {json.dumps(input_ids)}}}'\"\"\"\n",
" -d '{{\"model\": \"Alibaba-NLP/gte-Qwen2-1.5B-instruct\", \"input\": {json.dumps(input_ids)}}}'\"\"\"\n",
"\n",
"input_ids_embedding = json.loads(subprocess.check_output(curl_ids, shell=True))[\"data\"][\n",
" 0\n",