Downloads · 30 days
205
29% of all-time downloads
Blshu/Gemma-4-E2B-Claude-Sonnet-4.6
Gemma-4-E2B-Claude-Sonnet-4.6 is a text generation model from Blshu. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
Gemma-4-E2B-Claude-Sonnet-4.6 is a fine-tuned lightweight language model based on Google's Gemma 4 E2B. It is fine-tuned to capture the structured reasoning, articulate tone, and helpful demeanor inspired by Claude So…
Downloads · 30 days
205
29% of all-time downloads
All-time downloads
710
Public
Repo size
4.8 GB
Likes
0
Public
Click a slice to open those files.
.gguf4.8 GB · 100%
From the Hugging Face model README
Gemma-4-E2B-Claude-Sonnet-4.6 is a fine-tuned lightweight language model based on Google's Gemma 4 E2B. It is fine-tuned to capture the structured reasoning, articulate tone, and helpful demeanor inspired by Claude Sonnet 4.6.
Trained using Unsloth Desktop, this model brings high-quality, nuanced responses to lightweight on-device environments.
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "Blshu/Gemma-4-E2B-Claude-Sonnet-4.6"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.float16,
device_map="auto"
)
messages = [
{"role": "user", "content": "Explain the concept of quantum computing in simple terms."}
]
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(prompt, return_tensors="pt").to("cuda" if torch.cuda.is_available() else "cpu")
outputs = model.generate(
**inputs,
max_new_tokens=256,
temperature=0.7,
top_p=0.9
)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))