upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-07-23 11:10:55 -05:00
Code Issues Packages Projects Releases Wiki Activity

model : add support for talkie-1930-13b (#22596)

Browse Source 
* initial talkie support, coherent

* reorder to follow convention

* absorb inverse rope

* stop folding scalars to improve quantization

* use broadcasting instead of duplication

* style cleanup

* add scaling support to LoraTorchTensor; use that path in conversion

* use layer_out_scale instead of embd_skip_scale
This commit is contained in:
Niklas Sheth
2026-05-26 00:57:38 -04:00
committed by GitHub
parent 1506d39e76
commit c9d98295a3
14 changed files with 263 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
convert_hf_to_gguf_update.py
View File

@@ -156,6 +156,7 @@ models = [
{"name": "kanana2", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/kakaocorp/kanana-2-30b-a3b-instruct-2601", },
{"name": "f2llmv2", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/codefuse-ai/F2LLM-v2-4B", },
{"name": "sarvam-moe", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/sarvamai/sarvam-30b", },
{"name": "talkie", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/lewtun/talkie-1930-13b-it-hf", },
]
# some models are known to be broken upstream, so we will skip them as exceptions