Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Instructions to use ryanmarten/OpenThinker-7B-Unverified with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ryanmarten/OpenThinker-7B-Unverified with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ryanmarten/OpenThinker-7B-Unverified") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("ryanmarten/OpenThinker-7B-Unverified") model = AutoModelForCausalLM.from_pretrained("ryanmarten/OpenThinker-7B-Unverified", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use ryanmarten/OpenThinker-7B-Unverified with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ryanmarten/OpenThinker-7B-Unverified" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ryanmarten/OpenThinker-7B-Unverified", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/ryanmarten/OpenThinker-7B-Unverified
- SGLang
How to use ryanmarten/OpenThinker-7B-Unverified 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 "ryanmarten/OpenThinker-7B-Unverified" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ryanmarten/OpenThinker-7B-Unverified", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "ryanmarten/OpenThinker-7B-Unverified" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ryanmarten/OpenThinker-7B-Unverified", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use ryanmarten/OpenThinker-7B-Unverified with Docker Model Runner:
docker model run hf.co/ryanmarten/OpenThinker-7B-Unverified
Update README.md
Browse files
README.md
CHANGED
|
@@ -11,24 +11,31 @@ model-index:
|
|
| 11 |
results: []
|
| 12 |
---
|
| 13 |
|
| 14 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
-
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
|
| 17 |
-
|
|
|
|
|
|
|
| 18 |
|
| 19 |
-
|
| 20 |
|
| 21 |
-
|
|
|
|
| 22 |
|
| 23 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
|
| 25 |
-
## Intended uses & limitations
|
| 26 |
|
| 27 |
-
More information needed
|
| 28 |
|
| 29 |
-
##
|
|
|
|
|
|
|
| 30 |
|
| 31 |
-
More information needed
|
| 32 |
|
| 33 |
## Training procedure
|
| 34 |
|
|
@@ -49,8 +56,6 @@ The following hyperparameters were used during training:
|
|
| 49 |
- lr_scheduler_warmup_ratio: 0.1
|
| 50 |
- num_epochs: 3.0
|
| 51 |
|
| 52 |
-
### Training results
|
| 53 |
-
|
| 54 |
|
| 55 |
|
| 56 |
### Framework versions
|
|
|
|
| 11 |
results: []
|
| 12 |
---
|
| 13 |
|
|
|
|
|
|
|
| 14 |
|
| 15 |
+
<p align="center">
|
| 16 |
+
<img src="https://huggingface.co/datasets/open-thoughts/open-thoughts-114k/resolve/main/open_thoughts.png" width="50%">
|
| 17 |
+
</p>
|
| 18 |
|
| 19 |
+
# OpenThinker-7B-Unverified
|
| 20 |
|
| 21 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the
|
| 22 |
+
[OpenThoughts-Unverified-173k](https://huggingface.co/datasets/open-thoughts/OpenThoughts-Unverified-173k) dataset.
|
| 23 |
|
| 24 |
+
Please see [OpenThinker-7B](https://huggingface.co/open-thoughts/OpenThinker-7B) for more information.
|
| 25 |
+
|
| 26 |
+
|Model Name|Dataset size|AIME24 I/II|AIME25 I|MATH500|GPQA Diamond|LCBv2|
|
| 27 |
+
|---|---|---|---|---|---|---|
|
| 28 |
+
|[OpenThinker-7B](https://huggingface.co/open-thoughts/OpenThinker-7B)|114k|31.3|30.7|84.4|38.9|41.8|
|
| 29 |
+
|[OpenThinker-7B-Unverified](https://huggingface.co/open-thoughts/OpenThinker-7B-Unverified)|173k|34|29.33|83|39.4|43.8|
|
| 30 |
+
|[OpenThinker-32B](https://huggingface.co/open-thoughts/OpenThinker-32B)|114k|66.7|53.3|90.6|61.6|68.9|
|
| 31 |
+
|[OpenThinker-32B-Unverified](https://huggingface.co/open-thoughts/OpenThinker-32B-Unverified)|173k|60.7|44|90|60.6|69.2|
|
| 32 |
|
|
|
|
| 33 |
|
|
|
|
| 34 |
|
| 35 |
+
## Intended uses & limitations
|
| 36 |
+
|
| 37 |
+
Apache 2.0
|
| 38 |
|
|
|
|
| 39 |
|
| 40 |
## Training procedure
|
| 41 |
|
|
|
|
| 56 |
- lr_scheduler_warmup_ratio: 0.1
|
| 57 |
- num_epochs: 3.0
|
| 58 |
|
|
|
|
|
|
|
| 59 |
|
| 60 |
|
| 61 |
### Framework versions
|