Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
tchbcb
/
samai-4b
Like
1
Safetensors
Chinese
English
samai_4b
pondernet
mixture-of-experts
adaptive-computation
rent-math
custom_code
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
samai-4b
8.49 GB
Ctrl+K
Ctrl+K
1 contributor
History:
12 commits
tchbcb
200k ctx (rope_scaling hook) + openai-compatible api (key 1234) + bootstrap v2 (chat 7861 / api 7862) + model card
a49846b
verified
9 days ago
sft_adapter
sft adapter (lora r16 + router/ponder_head, loss 0.611)
9 days ago
.gitattributes
Safe
1.52 kB
initial commit
9 days ago
README.md
3.82 kB
200k ctx (rope_scaling hook) + openai-compatible api (key 1234) + bootstrap v2 (chat 7861 / api 7862) + model card
9 days ago
bootstrap.py
4.79 kB
200k ctx (rope_scaling hook) + openai-compatible api (key 1234) + bootstrap v2 (chat 7861 / api 7862) + model card
9 days ago
chat_server.py
14.4 kB
chat server (flask, port 7861, force_think+antiloop+votes)
9 days ago
chat_template.jinja
Safe
4.65 kB
samai-4b: spark-x2.5-4b backbone + pondernet/dmoe conversion
9 days ago
config.json
2.57 kB
200k ctx (rope_scaling hook) + openai-compatible api (key 1234) + bootstrap v2 (chat 7861 / api 7862) + model card
9 days ago
control_server.py
2.16 kB
200k ctx (rope_scaling hook) + openai-compatible api (key 1234) + bootstrap v2 (chat 7861 / api 7862) + model card
9 days ago
eval_report.json
12.6 kB
post-SFT eval report (math 8/9, original rent 3/3)
9 days ago
generation_config.json
197 Bytes
samai-4b SFT merged full weights (rent-math sft, 831 rows x2ep)
9 days ago
merges.txt
Safe
1.57 MB
samai-4b: spark-x2.5-4b backbone + pondernet/dmoe conversion
9 days ago
model-00001-of-00003.safetensors
4 GB
xet
samai-4b SFT merged full weights (rent-math sft, 831 rows x2ep)
9 days ago
model-00002-of-00003.safetensors
3.99 GB
xet
samai-4b SFT merged full weights (rent-math sft, 831 rows x2ep)
9 days ago
model-00003-of-00003.safetensors
320 MB
xet
samai-4b SFT merged full weights (rent-math sft, 831 rows x2ep)
9 days ago
model.safetensors.index.json
41.4 kB
samai-4b SFT merged full weights (rent-math sft, 831 rows x2ep)
9 days ago
modeling_samai_4b.py
61.5 kB
200k ctx (rope_scaling hook) + openai-compatible api (key 1234) + bootstrap v2 (chat 7861 / api 7862) + model card
9 days ago
openai_api.py
10.6 kB
200k ctx (rope_scaling hook) + openai-compatible api (key 1234) + bootstrap v2 (chat 7861 / api 7862) + model card
9 days ago
special_tokens_map.json
Safe
156 Bytes
samai-4b: spark-x2.5-4b backbone + pondernet/dmoe conversion
9 days ago
tokenizer.json
Safe
10.1 MB
samai-4b SFT merged full weights (rent-math sft, 831 rows x2ep)
9 days ago
tokenizer_config.json
Safe
389 Bytes
samai-4b SFT merged full weights (rent-math sft, 831 rows x2ep)
9 days ago
vocab.json
Safe
3.03 MB
samai-4b: spark-x2.5-4b backbone + pondernet/dmoe conversion
9 days ago