Instructions to use guicybercode/br-sovereign-llm-smoke with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use guicybercode/br-sovereign-llm-smoke with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="guicybercode/br-sovereign-llm-smoke")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("guicybercode/br-sovereign-llm-smoke")
model = AutoModelForCausalLM.from_pretrained("guicybercode/br-sovereign-llm-smoke", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use guicybercode/br-sovereign-llm-smoke with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "guicybercode/br-sovereign-llm-smoke"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "guicybercode/br-sovereign-llm-smoke",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/guicybercode/br-sovereign-llm-smoke

SGLang

How to use guicybercode/br-sovereign-llm-smoke with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "guicybercode/br-sovereign-llm-smoke" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "guicybercode/br-sovereign-llm-smoke",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "guicybercode/br-sovereign-llm-smoke" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "guicybercode/br-sovereign-llm-smoke",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use guicybercode/br-sovereign-llm-smoke with Docker Model Runner:
```
docker model run hf.co/guicybercode/br-sovereign-llm-smoke
```

guicybercode commited on 2 days ago

Commit

be0fc2e

verified ·

1 Parent(s): 47c6a3f

Public candidate v0.1.1 - final private verification

Browse files

Files changed (3) hide show

evidence/g6-tokenizer-quality.json +1 -1
evidence/g7-training-semantics.json +1 -1
release-manifest.json +3 -3

evidence/g6-tokenizer-quality.json CHANGED Viewed

@@ -11,7 +11,7 @@
   },
   "claim_boundary": "The eight-document fixture cannot establish domain coverage, fertility quality, or downstream scientific performance.",
   "gate_id": "G6",
-  "generated_at": "2026-08-26T17:03:08Z",
   "measurements": {
     "bytes_per_token": 2.400815217391304,
     "characters": 1695,

   },
   "claim_boundary": "The eight-document fixture cannot establish domain coverage, fertility quality, or downstream scientific performance.",
   "gate_id": "G6",
+  "generated_at": "2026-08-26T17:05:37Z",
   "measurements": {
     "bytes_per_token": 2.400815217391304,
     "characters": 1695,

evidence/g7-training-semantics.json CHANGED Viewed

@@ -15,7 +15,7 @@
   },
   "claim_boundary": "Pass applies only to the declared engineering smoke artifact. It does not satisfy the full scientific G7 gate or checkpoint-restart H2.",
   "gate_id": "G7",
-  "generated_at": "2026-08-26T17:03:08Z",
   "measurements": {
     "final_resumed_loss": 6.114025115966797,
     "final_uninterrupted_loss": 6.114025115966797,

   },
   "claim_boundary": "Pass applies only to the declared engineering smoke artifact. It does not satisfy the full scientific G7 gate or checkpoint-restart H2.",
   "gate_id": "G7",
+  "generated_at": "2026-08-26T17:05:37Z",
   "measurements": {
     "final_resumed_loss": 6.114025115966797,
     "final_uninterrupted_loss": 6.114025115966797,

release-manifest.json CHANGED Viewed

@@ -38,12 +38,12 @@
     },
     {
       "path": "evidence/g6-tokenizer-quality.json",
-      "sha256": "3a61d87d753f08ac8a48e6fdd9042ffe73340368ca239144294ebef476adbd1c",
       "size_bytes": 1018
     },
     {
       "path": "evidence/g7-training-semantics.json",
-      "sha256": "d0a9980965d42d25a8886b283fecf8a1a22b9181c5544443fe8a8358efb9df7f",
       "size_bytes": 1318
     },
     {
@@ -77,7 +77,7 @@
       "size_bytes": 17469
     }
   ],
-  "manifest_sha256": "cc38b873623c41f92b77cbb96df7aa3edb67de1dd647055b4f1dee86e75d4752",
   "public_approval": {
     "path": "PUBLICATION_REVIEW.md",
     "sha256": "374f3e8a167788334bc6e3f056939d81a2b78ab8d82600733d9f69ec7ce9ab53",

     },
     {
       "path": "evidence/g6-tokenizer-quality.json",
+      "sha256": "cab95f19eae838b634bdc8b81305ef19734bfd22e5dab37bbc653f7d6a18be4b",
       "size_bytes": 1018
     },
     {
       "path": "evidence/g7-training-semantics.json",
+      "sha256": "ce5691f643cb842ddc7e81dd02e75ff8bf109f7160a0d447293873eb631390aa",
       "size_bytes": 1318
     },
     {
       "size_bytes": 17469
     }
   ],
+  "manifest_sha256": "ffe83856af26a3654a14b2adef75e20381e701c243cdb15d4d41fde1b85dc56c",
   "public_approval": {
     "path": "PUBLICATION_REVIEW.md",
     "sha256": "374f3e8a167788334bc6e3f056939d81a2b78ab8d82600733d9f69ec7ce9ab53",