from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("glogwa68/olmo-3-DISTILL-glm-4.7-think")
tokenizer = AutoTokenizer.from_pretrained("glogwa68/olmo-3-DISTILL-glm-4.7-think")

messages = [{"role": "user", "content": "Hello, how are you?"}]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True)
outputs = model.generate(inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Ollama (GGUF)

Base Model: unsloth/Olmo-3-7B-Think
Fine-tuning Dataset: TeichAI/glm-4.7-2000x
Context Length: 1048576 tokens
Special Feature: Thinking/Reasoning with &lt;think&gt; tags

ollama run hf.co/glogwa68/olmo-3-DISTILL-glm-4.7-think-GGUF:Q4_K_M

llama.cpp

llama-cli --hf-repo glogwa68/olmo-3-DISTILL-glm-4.7-think-GGUF --hf-file olmo-3-distill-glm-4.7-think-q4_k_m.gguf -p "Hello"

Training Details

Epochs: 2
Learning Rate: 2e-5
Batch Size: 8 (with gradient accumulation)
Precision: FP16
Hardware: Multi-GPU with DeepSpeed ZeRO-3

License

Apache 2.0