Instructions to use GetSoloTech/GPT-OSS-Code-Reasoning-20B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GetSoloTech/GPT-OSS-Code-Reasoning-20B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="GetSoloTech/GPT-OSS-Code-Reasoning-20B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("GetSoloTech/GPT-OSS-Code-Reasoning-20B")
model = AutoModelForCausalLM.from_pretrained("GetSoloTech/GPT-OSS-Code-Reasoning-20B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use GetSoloTech/GPT-OSS-Code-Reasoning-20B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GetSoloTech/GPT-OSS-Code-Reasoning-20B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GetSoloTech/GPT-OSS-Code-Reasoning-20B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/GetSoloTech/GPT-OSS-Code-Reasoning-20B

SGLang

How to use GetSoloTech/GPT-OSS-Code-Reasoning-20B 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 "GetSoloTech/GPT-OSS-Code-Reasoning-20B" \
    --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": "GetSoloTech/GPT-OSS-Code-Reasoning-20B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "GetSoloTech/GPT-OSS-Code-Reasoning-20B" \
        --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": "GetSoloTech/GPT-OSS-Code-Reasoning-20B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use GetSoloTech/GPT-OSS-Code-Reasoning-20B with Docker Model Runner:
```
docker model run hf.co/GetSoloTech/GPT-OSS-Code-Reasoning-20B
```

zeeshaan-ai commited on Aug 19, 2025

Commit

b26779f

verified ·

1 Parent(s): 6b2b4c9

Upload config.json

Browse files

Files changed (1) hide show

config.json +75 -67

config.json CHANGED Viewed

@@ -1,69 +1,77 @@
 {
-    "architectures": [
-        "GptOssForCausalLM"
     ],
-    "attention_bias": true,
-    "attention_dropout": 0.0,
-    "eos_token_id": 200002,
-    "experts_per_token": 4,
-    "head_dim": 64,
-    "hidden_act": "silu",
-    "hidden_size": 2880,
-    "initial_context_length": 4096,
-    "initializer_range": 0.02,
-    "intermediate_size": 2880,
-    "layer_types": [
-        "sliding_attention",
-        "full_attention",
-        "sliding_attention",
-        "full_attention",
-        "sliding_attention",
-        "full_attention",
-        "sliding_attention",
-        "full_attention",
-        "sliding_attention",
-        "full_attention",
-        "sliding_attention",
-        "full_attention",
-        "sliding_attention",
-        "full_attention",
-        "sliding_attention",
-        "full_attention",
-        "sliding_attention",
-        "full_attention",
-        "sliding_attention",
-        "full_attention",
-        "sliding_attention",
-        "full_attention",
-        "sliding_attention",
-        "full_attention"
-    ],
-    "max_position_embeddings": 131072,
-    "model_type": "gpt_oss",
-    "num_attention_heads": 64,
-    "num_experts_per_tok": 4,
-    "num_hidden_layers": 24,
-    "num_key_value_heads": 8,
-    "num_local_experts": 32,
-    "output_router_logits": false,
-    "pad_token_id": 199999,
-    "rms_norm_eps": 1e-05,
-    "rope_scaling": {
-        "beta_fast": 32.0,
-        "beta_slow": 1.0,
-        "factor": 32.0,
-        "original_max_position_embeddings": 4096,
-        "rope_type": "yarn",
-        "truncate": false
-    },
-    "rope_theta": 150000,
-    "router_aux_loss_coef": 0.9,
-    "sliding_window": 128,
-    "swiglu_limit": 7.0,
-    "tie_word_embeddings": false,
-    "torch_dtype": "bfloat16",
-    "transformers_version": "4.56.0.dev0",
-    "unsloth_version": "2025.8.4",
-    "use_cache": true,
-    "vocab_size": 201088
-}

 {
+  "architectures": [
+    "GptOssForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "eos_token_id": 200002,
+  "experts_per_token": 4,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2880,
+  "initial_context_length": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 2880,
+  "layer_types": [
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 131072,
+  "model_type": "gpt_oss",
+  "num_attention_heads": 64,
+  "num_experts_per_tok": 4,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 8,
+  "num_local_experts": 32,
+  "output_router_logits": false,
+  "pad_token_id": 200017,
+  "quantization_config": {
+    "modules_to_not_convert": [
+      "model.layers.*.self_attn",
+      "model.layers.*.mlp.router",
+      "model.embed_tokens",
+      "lm_head"
     ],
+    "quant_method": "mxfp4"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "beta_fast": 32.0,
+    "beta_slow": 1.0,
+    "factor": 32.0,
+    "original_max_position_embeddings": 4096,
+    "rope_type": "yarn",
+    "truncate": false
+  },
+  "rope_theta": 150000,
+  "router_aux_loss_coef": 0.9,
+  "sliding_window": 128,
+  "swiglu_limit": 7.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.55.0",
+  "unsloth_fixed": true,
+  "use_cache": true,
+  "vocab_size": 201088
+}