Text Classification
Transformers
Safetensors
English
qwen3_5_text
text-generation
decision-model
typed-decisions
one-pass
option-probabilities
Instructions to use thegovind/blink-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use thegovind/blink-4b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="thegovind/blink-4b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("thegovind/blink-4b") model = AutoModelForCausalLM.from_pretrained("thegovind/blink-4b", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Card: links to the source code and docs
Browse files
README.md
CHANGED
|
@@ -25,6 +25,8 @@ one forward pass, with no generated text. Long or large multi-question requests
|
|
| 25 |
[blink-4b](https://huggingface.co/thegovind/blink-4b) 路 [blink-27b](https://huggingface.co/thegovind/blink-27b) 路
|
| 26 |
[blink-mimo-9b](https://huggingface.co/thegovind/blink-mimo-9b).
|
| 27 |
|
|
|
|
|
|
|
| 28 |
*Personal research release by thegovind, not an official product of any company. No affiliation with TypeSafe AI,
|
| 29 |
Xiaomi, Alibaba Cloud or the Qwen team. Weights are for non-commercial research; see [Licence](#licence).*
|
| 30 |
|
|
@@ -237,6 +239,8 @@ print(out["answers"]["intent"]["probabilities"])
|
|
| 237 |
JevBench's stock `typesafe` adapter and the Decision Index kit's `http` engine still work unchanged.
|
| 238 |
`GET /healthz` reports startup checks. `v1.2` changes code only; its weights are identical to `v1.0`.
|
| 239 |
|
|
|
|
|
|
|
| 240 |
```sh
|
| 241 |
pip install "torch==2.13.0" "transformers==5.17.0" "flash-linear-attention==0.5.2" "accelerate>=1.1.0" safetensors huggingface_hub
|
| 242 |
hf download thegovind/blink-4b --revision v1.2 --local-dir blink-4b
|
|
|
|
| 25 |
[blink-4b](https://huggingface.co/thegovind/blink-4b) 路 [blink-27b](https://huggingface.co/thegovind/blink-27b) 路
|
| 26 |
[blink-mimo-9b](https://huggingface.co/thegovind/blink-mimo-9b).
|
| 27 |
|
| 28 |
+
[Source code](https://github.com/thegovind/blink) 路 [Docs](https://thegovind.github.io/blink/) 路 [blink-4b docs](https://thegovind.github.io/blink/models/blink-4b/).
|
| 29 |
+
|
| 30 |
*Personal research release by thegovind, not an official product of any company. No affiliation with TypeSafe AI,
|
| 31 |
Xiaomi, Alibaba Cloud or the Qwen team. Weights are for non-commercial research; see [Licence](#licence).*
|
| 32 |
|
|
|
|
| 239 |
JevBench's stock `typesafe` adapter and the Decision Index kit's `http` engine still work unchanged.
|
| 240 |
`GET /healthz` reports startup checks. `v1.2` changes code only; its weights are identical to `v1.0`.
|
| 241 |
|
| 242 |
+
See the [wire-format reference](https://thegovind.github.io/blink/wire-format/) for full API details.
|
| 243 |
+
|
| 244 |
```sh
|
| 245 |
pip install "torch==2.13.0" "transformers==5.17.0" "flash-linear-attention==0.5.2" "accelerate>=1.1.0" safetensors huggingface_hub
|
| 246 |
hf download thegovind/blink-4b --revision v1.2 --local-dir blink-4b
|