Training in progress, step 1500
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +12 -0
- LLaMA-Factory/README.md +1 -0
- LLaMA-Factory/assets/wechat.jpg +2 -2
- LLaMA-Factory/assets/wechat_npu.jpg +2 -2
- LLaMA-Factory/src/llamafactory.egg-info/PKG-INFO +1 -0
- LLaMA-Factory/src/llamafactory/__pycache__/__init__.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/data/__pycache__/__init__.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/data/__pycache__/collator.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/data/__pycache__/converter.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/data/__pycache__/data_utils.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/data/__pycache__/formatter.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/data/__pycache__/loader.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/data/__pycache__/mm_plugin.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/data/__pycache__/parser.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/data/__pycache__/template.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/data/__pycache__/tool_utils.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/data/processor/__pycache__/__init__.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/data/processor/__pycache__/feedback.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/data/processor/__pycache__/pairwise.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/data/processor/__pycache__/pretrain.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/data/processor/__pycache__/processor_utils.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/data/processor/__pycache__/supervised.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/data/processor/__pycache__/unsupervised.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/data/template.py +13 -0
- LLaMA-Factory/src/llamafactory/extras/__pycache__/__init__.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/extras/__pycache__/constants.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/extras/__pycache__/env.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/extras/__pycache__/logging.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/extras/__pycache__/misc.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/extras/__pycache__/packages.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/extras/__pycache__/ploting.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/extras/constants.py +55 -0
- LLaMA-Factory/src/llamafactory/hparams/__pycache__/__init__.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/hparams/__pycache__/data_args.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/hparams/__pycache__/evaluation_args.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/hparams/__pycache__/finetuning_args.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/hparams/__pycache__/generating_args.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/hparams/__pycache__/model_args.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/hparams/__pycache__/parser.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/hparams/__pycache__/training_args.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/model/__pycache__/__init__.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/model/__pycache__/adapter.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/model/__pycache__/loader.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/model/__pycache__/patcher.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/model/model_utils/__pycache__/__init__.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/model/model_utils/__pycache__/attention.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/model/model_utils/__pycache__/checkpointing.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/model/model_utils/__pycache__/embedding.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/model/model_utils/__pycache__/kv_cache.cpython-311.pyc +0 -0
- LLaMA-Factory/src/llamafactory/model/model_utils/__pycache__/liger_kernel.cpython-311.pyc +0 -0
.gitattributes
CHANGED
@@ -54,3 +54,15 @@ Model/last-checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
54 |
Model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
55 |
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
56 |
last-checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
54 |
Model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
55 |
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
56 |
last-checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
57 |
+
LLaMA-Factory/wandb/run-20250620_021722-rdrftts8/run-rdrftts8.wandb filter=lfs diff=lfs merge=lfs -text
|
58 |
+
Model/LLaMA-Factory/wandb/run-20250618_020445-o5waoqcx/run-o5waoqcx.wandb filter=lfs diff=lfs merge=lfs -text
|
59 |
+
Model/Model/LLaMA-Factory/assets/wechat.jpg filter=lfs diff=lfs merge=lfs -text
|
60 |
+
Model/Model/LLaMA-Factory/assets/wechat_alaya.png filter=lfs diff=lfs merge=lfs -text
|
61 |
+
Model/Model/LLaMA-Factory/assets/wechat_npu.jpg filter=lfs diff=lfs merge=lfs -text
|
62 |
+
Model/Model/LLaMA-Factory/data/mllm_demo_data/1.mp3 filter=lfs diff=lfs merge=lfs -text
|
63 |
+
Model/Model/LLaMA-Factory/data/mllm_demo_data/1.mp4 filter=lfs diff=lfs merge=lfs -text
|
64 |
+
Model/Model/LLaMA-Factory/data/mllm_demo_data/2.avi filter=lfs diff=lfs merge=lfs -text
|
65 |
+
Model/Model/LLaMA-Factory/data/mllm_demo_data/3.flac filter=lfs diff=lfs merge=lfs -text
|
66 |
+
Model/Model/LLaMA-Factory/data/mllm_demo_data/3.mp4 filter=lfs diff=lfs merge=lfs -text
|
67 |
+
Model/Model/last-checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
68 |
+
Model/Model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
LLaMA-Factory/README.md
CHANGED
@@ -262,6 +262,7 @@ Choose your path:
|
|
262 |
| [DeepSeek 2.5/3](https://huggingface.co/deepseek-ai) | 236B/671B | deepseek3 |
|
263 |
| [DeepSeek R1 (Distill)](https://huggingface.co/deepseek-ai) | 1.5B/7B/8B/14B/32B/70B/671B | deepseekr1 |
|
264 |
| [Falcon](https://huggingface.co/tiiuae) | 7B/11B/40B/180B | falcon |
|
|
|
265 |
| [Gemma/Gemma 2/CodeGemma](https://huggingface.co/google) | 2B/7B/9B/27B | gemma |
|
266 |
| [Gemma 3](https://huggingface.co/google) | 1B/4B/12B/27B | gemma3/gemma (1B) |
|
267 |
| [GLM-4/GLM-4-0414/GLM-Z1](https://huggingface.co/THUDM) | 9B/32B | glm4/glmz1 |
|
|
|
262 |
| [DeepSeek 2.5/3](https://huggingface.co/deepseek-ai) | 236B/671B | deepseek3 |
|
263 |
| [DeepSeek R1 (Distill)](https://huggingface.co/deepseek-ai) | 1.5B/7B/8B/14B/32B/70B/671B | deepseekr1 |
|
264 |
| [Falcon](https://huggingface.co/tiiuae) | 7B/11B/40B/180B | falcon |
|
265 |
+
| [Falcon-H1](https://huggingface.co/tiiuae) | 0.5B/1.5B/3B/7B/34B | falcon_h1 |
|
266 |
| [Gemma/Gemma 2/CodeGemma](https://huggingface.co/google) | 2B/7B/9B/27B | gemma |
|
267 |
| [Gemma 3](https://huggingface.co/google) | 1B/4B/12B/27B | gemma3/gemma (1B) |
|
268 |
| [GLM-4/GLM-4-0414/GLM-Z1](https://huggingface.co/THUDM) | 9B/32B | glm4/glmz1 |
|
LLaMA-Factory/assets/wechat.jpg
CHANGED
![]() |
Git LFS Details
|
![]() |
Git LFS Details
|
LLaMA-Factory/assets/wechat_npu.jpg
CHANGED
![]() |
Git LFS Details
|
![]() |
Git LFS Details
|
LLaMA-Factory/src/llamafactory.egg-info/PKG-INFO
CHANGED
@@ -386,6 +386,7 @@ Choose your path:
|
|
386 |
| [DeepSeek 2.5/3](https://huggingface.co/deepseek-ai) | 236B/671B | deepseek3 |
|
387 |
| [DeepSeek R1 (Distill)](https://huggingface.co/deepseek-ai) | 1.5B/7B/8B/14B/32B/70B/671B | deepseekr1 |
|
388 |
| [Falcon](https://huggingface.co/tiiuae) | 7B/11B/40B/180B | falcon |
|
|
|
389 |
| [Gemma/Gemma 2/CodeGemma](https://huggingface.co/google) | 2B/7B/9B/27B | gemma |
|
390 |
| [Gemma 3](https://huggingface.co/google) | 1B/4B/12B/27B | gemma3/gemma (1B) |
|
391 |
| [GLM-4/GLM-4-0414/GLM-Z1](https://huggingface.co/THUDM) | 9B/32B | glm4/glmz1 |
|
|
|
386 |
| [DeepSeek 2.5/3](https://huggingface.co/deepseek-ai) | 236B/671B | deepseek3 |
|
387 |
| [DeepSeek R1 (Distill)](https://huggingface.co/deepseek-ai) | 1.5B/7B/8B/14B/32B/70B/671B | deepseekr1 |
|
388 |
| [Falcon](https://huggingface.co/tiiuae) | 7B/11B/40B/180B | falcon |
|
389 |
+
| [Falcon-H1](https://huggingface.co/tiiuae) | 0.5B/1.5B/3B/7B/34B | falcon_h1 |
|
390 |
| [Gemma/Gemma 2/CodeGemma](https://huggingface.co/google) | 2B/7B/9B/27B | gemma |
|
391 |
| [Gemma 3](https://huggingface.co/google) | 1B/4B/12B/27B | gemma3/gemma (1B) |
|
392 |
| [GLM-4/GLM-4-0414/GLM-Z1](https://huggingface.co/THUDM) | 9B/32B | glm4/glmz1 |
|
LLaMA-Factory/src/llamafactory/__pycache__/__init__.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/__pycache__/__init__.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/__pycache__/__init__.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/data/__pycache__/__init__.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/data/__pycache__/__init__.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/data/__pycache__/__init__.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/data/__pycache__/collator.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/data/__pycache__/collator.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/data/__pycache__/collator.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/data/__pycache__/converter.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/data/__pycache__/converter.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/data/__pycache__/converter.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/data/__pycache__/data_utils.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/data/__pycache__/data_utils.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/data/__pycache__/data_utils.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/data/__pycache__/formatter.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/data/__pycache__/formatter.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/data/__pycache__/formatter.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/data/__pycache__/loader.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/data/__pycache__/loader.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/data/__pycache__/loader.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/data/__pycache__/mm_plugin.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/data/__pycache__/mm_plugin.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/data/__pycache__/mm_plugin.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/data/__pycache__/parser.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/data/__pycache__/parser.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/data/__pycache__/parser.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/data/__pycache__/template.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/data/__pycache__/template.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/data/__pycache__/template.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/data/__pycache__/tool_utils.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/data/__pycache__/tool_utils.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/data/__pycache__/tool_utils.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/data/processor/__pycache__/__init__.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/data/processor/__pycache__/__init__.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/data/processor/__pycache__/__init__.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/data/processor/__pycache__/feedback.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/data/processor/__pycache__/feedback.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/data/processor/__pycache__/feedback.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/data/processor/__pycache__/pairwise.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/data/processor/__pycache__/pairwise.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/data/processor/__pycache__/pairwise.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/data/processor/__pycache__/pretrain.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/data/processor/__pycache__/pretrain.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/data/processor/__pycache__/pretrain.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/data/processor/__pycache__/processor_utils.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/data/processor/__pycache__/processor_utils.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/data/processor/__pycache__/processor_utils.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/data/processor/__pycache__/supervised.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/data/processor/__pycache__/supervised.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/data/processor/__pycache__/supervised.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/data/processor/__pycache__/unsupervised.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/data/processor/__pycache__/unsupervised.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/data/processor/__pycache__/unsupervised.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/data/template.py
CHANGED
@@ -916,6 +916,19 @@ register_template(
|
|
916 |
)
|
917 |
|
918 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
919 |
register_template(
|
920 |
name="fewshot",
|
921 |
format_assistant=StringFormatter(slots=["{{content}}\n\n"]),
|
|
|
916 |
)
|
917 |
|
918 |
|
919 |
+
register_template(
|
920 |
+
name="falcon_h1",
|
921 |
+
format_user=StringFormatter(slots=["<|im_start|>user\n{{content}}<|im_end|>\n"]),
|
922 |
+
format_assistant=StringFormatter(slots=["{{content}}<|im_end|>\n"]),
|
923 |
+
format_system=StringFormatter(slots=["<|im_start|>system\n{{content}}<|im_end|>\n"]),
|
924 |
+
format_function=FunctionFormatter(slots=["{{content}}<|im_end|>\n"], tool_format="default"),
|
925 |
+
format_observation=StringFormatter(slots=["<|im_start|>tool\n{{content}}<|im_end|>\n"]),
|
926 |
+
format_tools=ToolFormatter(tool_format="default"),
|
927 |
+
format_prefix=EmptyFormatter(slots=[{"bos_token"}]),
|
928 |
+
stop_words=["<|im_end|>", "<|end_of_text|>"],
|
929 |
+
)
|
930 |
+
|
931 |
+
|
932 |
register_template(
|
933 |
name="fewshot",
|
934 |
format_assistant=StringFormatter(slots=["{{content}}\n\n"]),
|
LLaMA-Factory/src/llamafactory/extras/__pycache__/__init__.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/extras/__pycache__/__init__.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/extras/__pycache__/__init__.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/extras/__pycache__/constants.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/extras/__pycache__/constants.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/extras/__pycache__/constants.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/extras/__pycache__/env.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/extras/__pycache__/env.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/extras/__pycache__/env.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/extras/__pycache__/logging.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/extras/__pycache__/logging.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/extras/__pycache__/logging.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/extras/__pycache__/misc.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/extras/__pycache__/misc.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/extras/__pycache__/misc.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/extras/__pycache__/packages.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/extras/__pycache__/packages.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/extras/__pycache__/packages.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/extras/__pycache__/ploting.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/extras/__pycache__/ploting.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/extras/__pycache__/ploting.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/extras/constants.py
CHANGED
@@ -633,6 +633,61 @@ register_model_group(
|
|
633 |
template="falcon",
|
634 |
)
|
635 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
636 |
|
637 |
register_model_group(
|
638 |
models={
|
|
|
633 |
template="falcon",
|
634 |
)
|
635 |
|
636 |
+
register_model_group(
|
637 |
+
models={
|
638 |
+
"Falcon-H1-0.5B-Instruct": {
|
639 |
+
DownloadSource.DEFAULT: "tiiuae/Falcon-H1-0.5B-Instruct",
|
640 |
+
DownloadSource.MODELSCOPE: "tiiuae/Falcon-H1-0.5B-Instruct",
|
641 |
+
},
|
642 |
+
"Falcon-H1-0.5B-Base": {
|
643 |
+
DownloadSource.DEFAULT: "tiiuae/Falcon-H1-0.5B-Base",
|
644 |
+
DownloadSource.MODELSCOPE: "tiiuae/Falcon-H1-0.5B-Base",
|
645 |
+
},
|
646 |
+
"Falcon-H1-1.5B-Instruct": {
|
647 |
+
DownloadSource.DEFAULT: "tiiuae/Falcon-H1-1.5B-Instruct",
|
648 |
+
DownloadSource.MODELSCOPE: "tiiuae/Falcon-H1-1.5B-Instruct",
|
649 |
+
},
|
650 |
+
"Falcon-H1-1.5B-Base": {
|
651 |
+
DownloadSource.DEFAULT: "tiiuae/Falcon-H1-1.5B-Base",
|
652 |
+
DownloadSource.MODELSCOPE: "tiiuae/Falcon-H1-1.5B-Base",
|
653 |
+
},
|
654 |
+
"Falcon-H1-1.5B-Deep-Instruct": {
|
655 |
+
DownloadSource.DEFAULT: "tiiuae/Falcon-H1-1.5B-Deep-Instruct",
|
656 |
+
DownloadSource.MODELSCOPE: "tiiuae/Falcon-H1-1.5B-Deep-Instruct",
|
657 |
+
},
|
658 |
+
"Falcon-H1-1.5B-Deep-Base": {
|
659 |
+
DownloadSource.DEFAULT: "tiuae/Falcon-H1-1.5B-Deep-Base",
|
660 |
+
DownloadSource.MODELSCOPE: "tiiuae/Falcon-H1-1.5B-Deep-Base",
|
661 |
+
},
|
662 |
+
"Falcon-H1-3B-Instruct": {
|
663 |
+
DownloadSource.DEFAULT: "tiiuae/Falcon-H1-3B-Instruct",
|
664 |
+
DownloadSource.MODELSCOPE: "tiiuae/Falcon-H1-3B-Instruct",
|
665 |
+
},
|
666 |
+
"Falcon-H1-3B-Base": {
|
667 |
+
DownloadSource.DEFAULT: "tiiuae/Falcon-H1-3B-Base",
|
668 |
+
DownloadSource.MODELSCOPE: "tiiuae/Falcon-H1-3B-Base",
|
669 |
+
},
|
670 |
+
"Falcon-H1-7B-Instruct": {
|
671 |
+
DownloadSource.DEFAULT: "tiiuae/Falcon-H1-7B-Instruct",
|
672 |
+
DownloadSource.MODELSCOPE: "tiiuae/Falcon-H1-7B-Instruct",
|
673 |
+
},
|
674 |
+
"Falcon-H1-7B-Base": {
|
675 |
+
DownloadSource.DEFAULT: "tiiuae/Falcon-H1-7B-Base",
|
676 |
+
DownloadSource.MODELSCOPE: "tiiuae/Falcon-H1-7B-Base",
|
677 |
+
},
|
678 |
+
"Falcon-H1-34B-Instruct": {
|
679 |
+
DownloadSource.DEFAULT: "tiiuae/Falcon-H1-34B-Instruct",
|
680 |
+
DownloadSource.MODELSCOPE: "tiiuae/Falcon-H1-34B-Instruct",
|
681 |
+
},
|
682 |
+
"Falcon-H1-34B-Base": {
|
683 |
+
DownloadSource.DEFAULT: "tiiuae/Falcon-H1-34B-Base",
|
684 |
+
DownloadSource.MODELSCOPE: "tiiuae/Falcon-H1-34B-Base",
|
685 |
+
},
|
686 |
+
|
687 |
+
},
|
688 |
+
template="falcon_h1",
|
689 |
+
)
|
690 |
+
|
691 |
|
692 |
register_model_group(
|
693 |
models={
|
LLaMA-Factory/src/llamafactory/hparams/__pycache__/__init__.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/hparams/__pycache__/__init__.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/hparams/__pycache__/__init__.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/hparams/__pycache__/data_args.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/hparams/__pycache__/data_args.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/hparams/__pycache__/data_args.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/hparams/__pycache__/evaluation_args.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/hparams/__pycache__/evaluation_args.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/hparams/__pycache__/evaluation_args.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/hparams/__pycache__/finetuning_args.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/hparams/__pycache__/finetuning_args.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/hparams/__pycache__/finetuning_args.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/hparams/__pycache__/generating_args.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/hparams/__pycache__/generating_args.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/hparams/__pycache__/generating_args.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/hparams/__pycache__/model_args.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/hparams/__pycache__/model_args.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/hparams/__pycache__/model_args.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/hparams/__pycache__/parser.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/hparams/__pycache__/parser.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/hparams/__pycache__/parser.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/hparams/__pycache__/training_args.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/hparams/__pycache__/training_args.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/hparams/__pycache__/training_args.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/model/__pycache__/__init__.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/model/__pycache__/__init__.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/model/__pycache__/__init__.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/model/__pycache__/adapter.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/model/__pycache__/adapter.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/model/__pycache__/adapter.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/model/__pycache__/loader.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/model/__pycache__/loader.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/model/__pycache__/loader.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/model/__pycache__/patcher.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/model/__pycache__/patcher.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/model/__pycache__/patcher.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/model/model_utils/__pycache__/__init__.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/model/model_utils/__pycache__/__init__.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/model/model_utils/__pycache__/__init__.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/model/model_utils/__pycache__/attention.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/model/model_utils/__pycache__/attention.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/model/model_utils/__pycache__/attention.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/model/model_utils/__pycache__/checkpointing.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/model/model_utils/__pycache__/checkpointing.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/model/model_utils/__pycache__/checkpointing.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/model/model_utils/__pycache__/embedding.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/model/model_utils/__pycache__/embedding.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/model/model_utils/__pycache__/embedding.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/model/model_utils/__pycache__/kv_cache.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/model/model_utils/__pycache__/kv_cache.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/model/model_utils/__pycache__/kv_cache.cpython-311.pyc differ
|
|
LLaMA-Factory/src/llamafactory/model/model_utils/__pycache__/liger_kernel.cpython-311.pyc
CHANGED
Binary files a/LLaMA-Factory/src/llamafactory/model/model_utils/__pycache__/liger_kernel.cpython-311.pyc and b/LLaMA-Factory/src/llamafactory/model/model_utils/__pycache__/liger_kernel.cpython-311.pyc differ
|
|