Instructions to use caphe/Affine-3000 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use caphe/Affine-3000 with Transformers:

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

pipe = pipeline("text-generation", model="caphe/Affine-3000")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("caphe/Affine-3000")
model = AutoModelForCausalLM.from_pretrained("caphe/Affine-3000", device_map="auto")
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 caphe/Affine-3000 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "caphe/Affine-3000"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "caphe/Affine-3000",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/caphe/Affine-3000

SGLang

How to use caphe/Affine-3000 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 "caphe/Affine-3000" \
    --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": "caphe/Affine-3000",
		"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 "caphe/Affine-3000" \
        --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": "caphe/Affine-3000",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use caphe/Affine-3000 with Docker Model Runner:
```
docker model run hf.co/caphe/Affine-3000
```

caphe commited on Jan 1

Commit

b3a8a4c

verified ·

1 Parent(s): 40dbf0f

Upload Qwen3ForCausalLM

Browse files

Files changed (5) hide show

config.json +2 -2
generation_config.json +2 -1
model-00001-of-00002.safetensors +2 -2
model-00002-of-00002.safetensors +1 -1
model.safetensors.index.json +2 -2

config.json CHANGED Viewed

@@ -62,7 +62,7 @@
   "sliding_window": null,
   "tie_word_embeddings": true,
   "transformers_version": "4.57.3",
-  "use_cache": true,
   "use_sliding_window": false,
-  "vocab_size": 151936
 }

   "sliding_window": null,
   "tie_word_embeddings": true,
   "transformers_version": "4.57.3",
+  "use_cache": false,
   "use_sliding_window": false,
+  "vocab_size": 151669
 }

generation_config.json CHANGED Viewed

@@ -2,5 +2,6 @@
   "_from_model_config": true,
   "bos_token_id": 151643,
   "eos_token_id": 151645,
-  "transformers_version": "4.57.3"
 }

   "_from_model_config": true,
   "bos_token_id": 151643,
   "eos_token_id": 151645,
+  "transformers_version": "4.57.3",
+  "use_cache": false
 }

model-00001-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71ce96f67f541b508489a6875d2172d32140ccdf94cb90e81d32fd8dfa2350b2
-size 4967215360

 version https://git-lfs.github.com/spec/v1
+oid sha256:edd81314f81e479821ef440407a258ba887390b538394208fe6963dc6524c96a
+size 4965848320

model-00002-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7fe899467d14e125b99eac9c0e81513f07ca19ee75cb0ef062d5f444579014f
 size 3077766632

 version https://git-lfs.github.com/spec/v1
+oid sha256:bb5e2ab68b988fa386446ad2fcda08b4a463b17421555f62957337575a3eab14
 size 3077766632

model.safetensors.index.json CHANGED Viewed

@@ -1,7 +1,7 @@
 {
   "metadata": {
-    "total_parameters": 4022468096,
-    "total_size": 8044936192
   },
   "weight_map": {
     "model.embed_tokens.weight": "model-00001-of-00002.safetensors",

 {
   "metadata": {
+    "total_parameters": 4021784576,
+    "total_size": 8043569152
   },
   "weight_map": {
     "model.embed_tokens.weight": "model-00001-of-00002.safetensors",