[toml]: urllib package removed

[abukhoy]

The following models have been successfully tested without using model cache:

• TinyLlama/TinyLlama-1.1B-Chat-v1.0
• gpt2
• Salesforce/codegen-350M-mono
• microsoft/Phi-3-mini-4k-instruct
• tiiuae/falcon-7b
• Qwen/Qwen2-0.5B
• Qwen/Qwen3-0.6B
• bigcode/starcoder2-3b
• Felladrin/Minueza-32M-Base
• wtang06/mpt-125m-c4
• hakurei/gpt-j-random-tinier
• meta-llama/Llama-3.2-1B
• unsloth/gemma-2b
• unsloth/gemma-2-2b
• TheBloke/TinyLlama-1.1B-Chat-v0.3-AWQ (AWQ model)
• neuralmagic/Llama-3.2-3B-Instruct-FP8 (float quantized compressed-tensor per tensor for weights and activations)
• neuralmagic/Qwen2-0.5B-Instruct-FP8 (FP8 quant method, static, LM head ignored)
• ibm-granite/granite-3.1-2b-instruct
• ibm-granite/granite-guardian-3.1-2b
• allenai/OLMo-2-0425-1B