Instructions to use raydelossantos/OmniCoder-9B-GPTQ-Int8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Local Apps Settings

How to use raydelossantos/OmniCoder-9B-GPTQ-Int8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "raydelossantos/OmniCoder-9B-GPTQ-Int8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "raydelossantos/OmniCoder-9B-GPTQ-Int8",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/raydelossantos/OmniCoder-9B-GPTQ-Int8

SGLang

How to use raydelossantos/OmniCoder-9B-GPTQ-Int8 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "raydelossantos/OmniCoder-9B-GPTQ-Int8" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "raydelossantos/OmniCoder-9B-GPTQ-Int8",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "raydelossantos/OmniCoder-9B-GPTQ-Int8" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "raydelossantos/OmniCoder-9B-GPTQ-Int8",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use raydelossantos/OmniCoder-9B-GPTQ-Int8 with Docker Model Runner:
```
docker model run hf.co/raydelossantos/OmniCoder-9B-GPTQ-Int8
```

raydelossantos commited on Mar 22

Commit

cd328b1

verified ·

1 Parent(s): 9fcb455

Fix config.json: use VLM structure (model_type=qwen3_5, Qwen3_5ForConditionalGeneration) with quantization_config

Browse files

Files changed (1) hide show

config.json +27 -19

config.json CHANGED Viewed

@@ -2,7 +2,9 @@
   "architectures": [
     "Qwen3_5ForConditionalGeneration"
   ],
   "model_type": "qwen3_5",
   "text_config": {
     "attention_bias": false,
     "attention_dropout": 0.0,
@@ -63,7 +65,7 @@
     "num_attention_heads": 16,
     "num_hidden_layers": 32,
     "num_key_value_heads": 4,
-    "pad_token_id": 248044,
     "partial_rotary_factor": 0.25,
     "rms_norm_eps": 1e-06,
     "rope_parameters": {
@@ -78,10 +80,32 @@
       "rope_type": "default"
     },
     "tie_word_embeddings": false,
-    "transformers_version": "5.3.0.dev0",
     "use_cache": true,
-    "vocab_size": 248320
   },
   "quantization_config": {
     "bits": 8,
     "checkpoint_format": "gptq",
@@ -130,21 +154,5 @@
     "pack_dtype": "int32",
     "quant_method": "gptq",
     "sym": true
-  },
-  "vision_config": {
-    "deepstack_visual_indexes": [],
-    "depth": 27,
-    "hidden_act": "gelu_pytorch_tanh",
-    "hidden_size": 1152,
-    "in_channels": 3,
-    "initializer_range": 0.02,
-    "intermediate_size": 4304,
-    "model_type": "qwen3_5",
-    "num_heads": 16,
-    "num_position_embeddings": 2304,
-    "out_hidden_size": 4096,
-    "patch_size": 16,
-    "spatial_merge_size": 2,
-    "temporal_patch_size": 2
   }
 }

   "architectures": [
     "Qwen3_5ForConditionalGeneration"
   ],
+  "image_token_id": 248056,
   "model_type": "qwen3_5",
+  "pad_token_id": 248055,
   "text_config": {
     "attention_bias": false,
     "attention_dropout": 0.0,
     "num_attention_heads": 16,
     "num_hidden_layers": 32,
     "num_key_value_heads": 4,
+    "pad_token_id": null,
     "partial_rotary_factor": 0.25,
     "rms_norm_eps": 1e-06,
     "rope_parameters": {
       "rope_type": "default"
     },
     "tie_word_embeddings": false,
     "use_cache": true,
+    "vocab_size": 248320,
+    "model_type": "qwen3_5_text"
   },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.3.0.dev0",
+  "unsloth_fixed": true,
+  "video_token_id": 248057,
+  "vision_config": {
+    "deepstack_visual_indexes": [],
+    "depth": 27,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "model_type": "qwen3_5",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 4096,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 248054,
+  "vision_start_token_id": 248053,
   "quantization_config": {
     "bits": 8,
     "checkpoint_format": "gptq",
     "pack_dtype": "int32",
     "quant_method": "gptq",
     "sym": true
   }
 }