Skip to content

Add falcon-e support #268

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
tsong-ms merged 6 commits into from
May 21, 2025
+31 −2
Merged

Add falcon-e support #268

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
de371b7
add falcon-e support
younesbelkada May 14, 2025
0015ad5
Update README.md
younesbelkada May 15, 2025
9e95756
Merge branch 'microsoft:main' into add-falcon-e-final
younesbelkada May 20, 2025
f314d18
feat: add also base models
younesbelkada May 21, 2025
765741d
update submodule
younesbelkada May 21, 2025
5c12850
Merge branch 'add-falcon-e-final' of github.com:younesbelkada/BitNet …
younesbelkada May 21, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion 3rdparty/llama.cpp
Open in desktop
Submodule llama.cpp updated 3 files
+1 −0 include/llama.h
+7 −0 src/llama-vocab.cpp
+12 −0 src/llama.cpp
14 changes: 14 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -137,6 +137,20 @@ This project is based on the [llama.cpp](https://github.com/ggerganov/llama.cpp)
<td>&#9989;</td>
<td>&#10060;</td>
</tr>
<tr>
<td rowspan="2"><a href="https://huggingface.co/collections/tiiuae/falcon-edge-series-6804fd13344d6d8a8fa71130">Falcon-E Family</a></td>
<td rowspan="2">1B-3B</td>
<td>x86</td>
<td>&#9989;</td>
<td>&#10060;</td>
<td>&#9989;</td>
</tr>
<tr>
<td>ARM</td>
<td>&#9989;</td>
<td>&#9989;</td>
<td>&#10060;</td>
</tr>
</table>


Expand Down
14 changes: 13 additions & 1 deletion setup_env.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,6 +44,18 @@
"microsoft/BitNet-b1.58-2B-4T": {
"model_name": "BitNet-b1.58-2B-4T",
},
"tiiuae/Falcon-E-3B-Instruct": {
"model_name": "Falcon-E-3B-Instruct",
},
"tiiuae/Falcon-E-1B-Instruct": {
"model_name": "Falcon-E-1B-Instruct",
},
"tiiuae/Falcon-E-3B-Base": {
"model_name": "Falcon-E-3B-Base",
},
"tiiuae/Falcon-E-1B-Base": {
"model_name": "Falcon-E-1B-Base",
},
}

SUPPORTED_QUANT_TYPES = {
Expand Down Expand Up @@ -144,7 +156,7 @@ def setup_gguf():
def gen_code():
_, arch = system_info()

llama3_f3_models = set([model['model_name'] for model in SUPPORTED_HF_MODELS.values() if model['model_name'].startswith("Falcon3") or model['model_name'].startswith("Llama")])
llama3_f3_models = set([model['model_name'] for model in SUPPORTED_HF_MODELS.values() if model['model_name'].startswith("Falcon") or model['model_name'].startswith("Llama")])

if arch == "arm64":
if args.use_pretuned:
Expand Down
3 changes: 3 additions & 0 deletions utils/convert-hf-to-gguf-bitnet.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -319,6 +319,9 @@ def get_vocab_base_pre(self, tokenizer) -> str:
if chkhsh == "8aeee3860c56296a157a1fe2fad249ec40aa59b1bb5709f4ade11c4e6fe652ed":
# ref: https://huggingface.co/tiiuae/falcon-7b
res = "falcon"
if chkhsh == "a6b57017d60e6edb4d88ecc2845188e0eb333a70357e45dcc9b53964a73bbae6":
# ref: https://huggingface.co/tiiuae/Falcon-E-3B-Instruct
res = "falcon_e"
if chkhsh == "0876d13b50744004aa9aeae05e7b0647eac9d801b5ba4668afc01e709c15e19f":
# ref: https://huggingface.co/BAAI/bge-small-en-v1.5
res = "bert-bge"
Expand Down