mirror of
https://github.com/hanzoai/engine.git
synced 2026-11-20 14:17:52 +00:00
* feat(models): implement the gemma4 family * Some fixes to run * Faster * Handle think tags * Handle think tags * Further refactor * Fix bugs * Moe works * Fix bos * Fixes for vision * Fix corner case * Remove debugging * Cleanup * Further refinements * Cleanup * Cleanup rotating cache * Fix cache * Fix cache * Fix mask and cache bug * Fix prealloc bug * Fix fa bug * Fix small corner case * Fix audios index * MoE refactor * More indexed moe quants * Format * Enable FA fallback * Add paged attn support * Fixes * Fixes * Audio works * Audio works * Audio fixes * Fix default for reasoning * Format * Fixes for parity * Fixes * Fixes * Format * No isq for vision * Fixes * Remove vision isq * Fix loading * Fixes for vision moe * Allowe looser case * Allow default sampling params * Fixes * Fix * Further fix * Fix effective_sliding_window * Fix bidirectional case * Fix bidirectional FA * Fix buffer zeroing * Fix some nans * Update * Update rmsnorm * Update cli * Minor fixes * Fix loading * Add tool call support * Fix tanh * Update reasoning parser * Update routing * Update routing * Attempt fix * Attempt fix * Attempt fix * Fix search * Cleanup * candle 0.10.0 * Fix block table bug * Remove unnecessary part * Remove unnecessary part * Remove unnecessary part * Fixes * Fixes * Fixes * vision -> multimodal * Add video support * Update docs * Video fixes * Video fixes * Fix mask * Add oneshot mode * Add oneshot mode * Fixes * Update for full sdpa fix * Rename thinking * Better loading * Add ffmpeg installation * Dont re expand * Fixes * Fixes * Minor tweaks * Only image tokens get bidirectional * Fix video prefix cache * Better video handling * Bidirectional on both * Fix uqffs * Allow auth for uqff * Improve readme * Fix uqff gen * Update readme * Fix uqff * Fix uqff * Disable paged * Fix afq cuda * Readme * Readme * Model card link * Allow shorthand * Bump versions * Bump versions * Bump versions * Examples * Update * Docs * Bump version * Fix expand logic * Bump cehck * Bump cehck * Bump
73 lines
1.7 KiB
JSON
73 lines
1.7 KiB
JSON
[
|
|
{
|
|
"model_id": "llama3-3b-instruct",
|
|
"model": {
|
|
"Plain": {
|
|
"model_id": "meta-llama/Llama-3.2-3B-Instruct"
|
|
}
|
|
},
|
|
"in_situ_quant": "4"
|
|
},
|
|
{
|
|
"model_id": "qwen3-4b",
|
|
"model": {
|
|
"Plain": {
|
|
"model_id": "Qwen/Qwen3-4B"
|
|
}
|
|
},
|
|
"num_device_layers": ["8"],
|
|
"in_situ_quant": "4"
|
|
},
|
|
{
|
|
"model_id": "qwen2-vl",
|
|
"model": {
|
|
"MultimodalPlain": {
|
|
"model_id": "Qwen/Qwen2-VL-2B-Instruct"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"model_id": "gemma4-E4B-multimodal",
|
|
"model": {
|
|
"MultimodalPlain": {
|
|
"model_id": "google/gemma-4-E4B-it"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"model_id": "phi3-multimodal",
|
|
"model": {
|
|
"MultimodalPlain": {
|
|
"model_id": "microsoft/Phi-3-vision-128k-instruct"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"model_id": "llama-gguf-q4",
|
|
"model": {
|
|
"Gguf": {
|
|
"tok_model_id": null,
|
|
"quantized_model_id": "TheBloke/Llama-2-7b-Chat-GGUF",
|
|
"quantized_filename": "llama-2-7b-chat.Q4_K_M.gguf"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"model_id": "deepseek-coder",
|
|
"model": {
|
|
"Plain": {
|
|
"model_id": "deepseek-ai/deepseek-coder-1.3b-instruct"
|
|
}
|
|
},
|
|
"chat_template": "{%- if messages[0]['role'] == 'system' -%}{{ messages[0]['content'] }}\n{%- endif -%}{%- for message in messages -%}{%- if message['role'] == 'user' -%}### Instruction:\n{{ message['content'] }}\n\n### Response:\n{%- elif message['role'] == 'assistant' -%}{{ message['content'] }}\n{%- endif -%}{%- endfor -%}"
|
|
},
|
|
{
|
|
"model_id": "flux-schnell",
|
|
"model": {
|
|
"DiffusionPlain": {
|
|
"model_id": "black-forest-labs/FLUX.1-schnell",
|
|
"dtype": "bf16"
|
|
}
|
|
}
|
|
}
|
|
] |