Added Eagle training support for Kimi-K2

[xuhaojie-2025]

add support for Kimi-K2 eagle train

• add target model for Kimi-K2 in specforge/modeling/target/kimi_k2.py

• add Kimi-K2 config in configs/kimi-k2-eagle3.json

• fix chat template in specforge/data/template.py

• When generating the hidden layer, the special dialogue template of Kimi-K2 has been adapted in specforge/data/preprocessing.py

• The tokenizer of the Kimi-K2 model cannot automatically use the fasttokenizer. A script is used to generate tokenizer.json, enabling it to use the fasttokenizer interface.

[gemini-code-assist[bot]]

[!WARNING] Gemini is unable to generate a summary due to a potential policy violation.

[sleepcoo]

Can you fix the conflict?

[xuhaojie-2025]

Can you fix the conflict?

[xuhaojie-2025]

Can you fix the conflict?

I have resolved the conflict based on upstream/main and re - submitted the code.

[jondurbin]

@xuhaojie-2025 Trying to use this for kimi-k2-0905 but having a bit of a time getting it working. Library issues, some stray bad lines, not using trust_remote_code in various places, outdated kimi_k2.py with bad refs to qk_head_dim, etc. I can struggle through but I'm wondering if perhaps you have an updated or functional branch/commit somewhere I can look at?