mirror of
https://github.com/zenlm/engine.git
synced 2026-10-30 15:00:05 +00:00
Eric BuehlerandGitHub
272f7ee1b5
* Refactor MistralRs * Working multi-model! * Add mutli-model docs initially * Update mistralrs-pyo3, mistralrs-bench, mistralrs * Update apis for consistency * API tweaks * Logging tweaks * Add examples, tweak cli * Clearer pipeline id * Fix config key semantics * Format and clippy * Tweak logging, fix example * Clippy refactor * Update examples * Remove unused multi model docs * Replace 'ignore' with 'default' * Update docs
28 lines
625 B
JSON
28 lines
625 B
JSON
{
|
|
"llama3-3b-text": {
|
|
"Plain": {
|
|
"model_id": "meta-llama/Llama-3.2-3B-Instruct"
|
|
},
|
|
"in_situ_quant": "8"
|
|
},
|
|
"gemma3-4b-vision": {
|
|
"VisionPlain": {
|
|
"model_id": "google/gemma-3-4b-it"
|
|
},
|
|
"in_situ_quant": "4"
|
|
},
|
|
"qwen3-4b-fast": {
|
|
"Plain": {
|
|
"model_id": "Qwen/Qwen3-4B"
|
|
},
|
|
"in_situ_quant": "4",
|
|
"num_device_layers": ["8"]
|
|
},
|
|
"llama3-gguf": {
|
|
"Gguf": {
|
|
"tok_model_id": "meta-llama/Llama-3.2-3B-Instruct",
|
|
"quantized_model_id": "bartowski/Llama-3.2-3B-Instruct-GGUF",
|
|
"quantized_filename": "Llama-3.2-3B-Instruct-Q4_K_M.gguf"
|
|
}
|
|
}
|
|
} |