Downloads · 30 days
323
64% of all-time downloads
quant-mind/Spark-X2.5-4B-W4A16-AutoRound
Spark-X2.5-4B-W4A16-AutoRound is a text generation model from quant-mind. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
Quantização em W4A16 (INT4) de alta precisão do modelo XHToken/Spark-X2.5-4B usando Intel AutoRound.
Downloads · 30 days
323
64% of all-time downloads
All-time downloads
508
Public
Parameters
4.1B
2.6 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors2.6 GB · 100%
How the weights are stored.
I323.8B · 92%
From the Hugging Face model README
Quantização em W4A16 (INT4) de alta precisão do modelo XHToken/Spark-X2.5-4B usando Intel AutoRound.
auto_gptq (compatível com kernel Marlin, vLLM e SGLang)iters): 200nsamples): 128seqlen): 2048enable_minmax_tuning=True, enable_norm_bias_tuning=Truelm_head e embeddings preservados em BF16from vllm import LLM, SamplingParams
llm = LLM(
model="quant-mind/Spark-X2.5-4B-W4A16-AutoRound",
quantization="gptq_marlin",
trust_remote_code=True,
max_model_len=4096
)
prompts = ["Olá! Como você pode me ajudar hoje?"]
params = SamplingParams(temperature=0.7, max_tokens=200)
outputs = llm.generate(prompts, params)
print(outputs[0].outputs[0].text)
Quantizado por quant-mind.