CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-02 09:12:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

clean

Browse Source
This commit is contained in:
ibrahimkhadraoui
2025-07-08 11:00:30 +04:00
parent 4bc9e0ca89
commit 2834a4ac10
1 changed files with 0 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
convert_hf_to_gguf.py
View File

@@ -6669,14 +6669,6 @@ class FalconH1Model(Mamba2Model):
## Validation ##
assert self.hparams.get("hidden_act") in [None, "silu"], "Only SILU activation supported"
assert self.d_inner % d_head == 0, f"SSM inner size {self.d_inner} not a multiple of head dim {d_head}"
# Add Falcon Mamba2 specific configuration
self.gguf_writer.add_ssm_head_dim(self.hparams["mamba_d_head"])
self.gguf_writer.add_ssm_inner_size(self.hparams["mamba_d_ssm"])
self.gguf_writer.add_head_count(self.find_hparam(["num_attention_heads"]))
self.gguf_writer.add_key_length(self.hparams["head_dim"])
self.gguf_writer.add_value_length(self.hparams["head_dim"])
self.gguf_writer.add_head_count_kv(self.find_hparam(["num_key_value_heads"], optional=True) or
self.find_hparam(["num_attention_heads"]))