Text Generation
MLX
Safetensors
English
small-language-model
from-scratch
conversational
apple-silicon
research
Instructions to use OpenSML/Solstice-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use OpenSML/Solstice-1 with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("OpenSML/Solstice-1") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use OpenSML/Solstice-1 with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "OpenSML/Solstice-1"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "OpenSML/Solstice-1" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "OpenSML/Solstice-1", "messages": [ {"role": "user", "content": "Hello"} ] }' - Atomic Chat
Prepare Solstice-1 175M private release package
Browse filesMerged FP32 checkpoint, frozen tokenizer, native MLX runner, Apache-2.0 license, technical documentation, training provenance and benchmark evidence.
- FILE_MANIFEST.json +2 -2
- README.md +1 -1
- SHA256SUMS +1 -1
FILE_MANIFEST.json
CHANGED
|
@@ -22,8 +22,8 @@
|
|
| 22 |
"sha256": "0e6865f1a81cfd69ca48e6987658854ce0c0d23e91d72ae545393cd5fa032375"
|
| 23 |
},
|
| 24 |
"README.md": {
|
| 25 |
-
"bytes":
|
| 26 |
-
"sha256": "
|
| 27 |
},
|
| 28 |
"REPOSITORIES.json": {
|
| 29 |
"bytes": 716,
|
|
|
|
| 22 |
"sha256": "0e6865f1a81cfd69ca48e6987658854ce0c0d23e91d72ae545393cd5fa032375"
|
| 23 |
},
|
| 24 |
"README.md": {
|
| 25 |
+
"bytes": 7699,
|
| 26 |
+
"sha256": "900df54a78e604f4245328633b77eb3cb606e8c213dc1ca71b41549905ced58e"
|
| 27 |
},
|
| 28 |
"REPOSITORIES.json": {
|
| 29 |
"bytes": 716,
|
README.md
CHANGED
|
@@ -123,6 +123,6 @@ Only updates through 128 of the final 256-update experiment are inherited. Earli
|
|
| 123 |
|
| 124 |
## Repository contents and licensing
|
| 125 |
|
| 126 |
-
The weights and author-controlled code are released under [Apache-2.0](LICENSE). Upstream datasets and third-party code retain their own terms; the model license does not relicense those materials. [Source notice](SOURCE_NOTICE.md) 路 [Third-party notices](THIRD_PARTY_NOTICES.md).
|
| 127 |
|
| 128 |
Technical details, data provenance, exact selected training prefixes, source snapshots, and reproduction prerequisites are included. Full raw corpora, optimizer binaries, and all ancestor weights are not distributed. The historical training archive is not a verified one-command retraining package. [Training and reproducibility](TRAINING_AND_REPRODUCIBILITY.md).
|
|
|
|
| 123 |
|
| 124 |
## Repository contents and licensing
|
| 125 |
|
| 126 |
+
The weights and author-controlled code are released under [Apache-2.0](https://huggingface.co/OpenSML/Solstice-1/blob/main/LICENSE). Upstream datasets and third-party code retain their own terms; the model license does not relicense those materials. [Source notice](SOURCE_NOTICE.md) 路 [Third-party notices](THIRD_PARTY_NOTICES.md).
|
| 127 |
|
| 128 |
Technical details, data provenance, exact selected training prefixes, source snapshots, and reproduction prerequisites are included. Full raw corpora, optimizer binaries, and all ancestor weights are not distributed. The historical training archive is not a verified one-command retraining package. [Training and reproducibility](TRAINING_AND_REPRODUCIBILITY.md).
|
SHA256SUMS
CHANGED
|
@@ -3,7 +3,7 @@ f09ed498cc42b482dae88d9fb5026bf74e1d8b9187f9ea301aeda0db76d6c859 BACKUP_AND_CLE
|
|
| 3 |
af646a190d135ec25a6ee2c76d1594c3f9ba8005cd3ca6df908606a15023273e CITATION.cff
|
| 4 |
cfc7749b96f63bd31c3c42b5c471bf756814053e847c10f3eb003417bc523d30 LICENSE
|
| 5 |
0e6865f1a81cfd69ca48e6987658854ce0c0d23e91d72ae545393cd5fa032375 PACKAGING_VERIFICATION.json
|
| 6 |
-
|
| 7 |
152a87d0098752350d54fdd3cde3861a77eb497c53dc973ee1a8370d12a13ff6 REPOSITORIES.json
|
| 8 |
fd05e1595bcdc52942e9425b6efb2c7e89553e6b0ad7d5f93d9075969cd75dba RUN_GUIDE.md
|
| 9 |
87fa33719fe1182d467a05ab417be2a362f50eea59f0ac6496d40e677544e27c SOURCE_NOTICE.md
|
|
|
|
| 3 |
af646a190d135ec25a6ee2c76d1594c3f9ba8005cd3ca6df908606a15023273e CITATION.cff
|
| 4 |
cfc7749b96f63bd31c3c42b5c471bf756814053e847c10f3eb003417bc523d30 LICENSE
|
| 5 |
0e6865f1a81cfd69ca48e6987658854ce0c0d23e91d72ae545393cd5fa032375 PACKAGING_VERIFICATION.json
|
| 6 |
+
900df54a78e604f4245328633b77eb3cb606e8c213dc1ca71b41549905ced58e README.md
|
| 7 |
152a87d0098752350d54fdd3cde3861a77eb497c53dc973ee1a8370d12a13ff6 REPOSITORIES.json
|
| 8 |
fd05e1595bcdc52942e9425b6efb2c7e89553e6b0ad7d5f93d9075969cd75dba RUN_GUIDE.md
|
| 9 |
87fa33719fe1182d467a05ab417be2a362f50eea59f0ac6496d40e677544e27c SOURCE_NOTICE.md
|