Text Generation
Transformers
Safetensors
English
Chinese
qwen3
qwen3-8b
lora
qlora
sft
rag
faiss
dense-retrieval
agent
ppo
rlhf
rule-reward
harness-engineering
um-handbook
question-answering
chatbot
education
tensor-talk
Instructions to use TensorCat/TensorTalk with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TensorCat/TensorTalk with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="TensorCat/TensorTalk")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("TensorCat/TensorTalk", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use TensorCat/TensorTalk with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "TensorCat/TensorTalk" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "TensorCat/TensorTalk", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/TensorCat/TensorTalk
- SGLang
How to use TensorCat/TensorTalk 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 "TensorCat/TensorTalk" \ --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": "TensorCat/TensorTalk", "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 "TensorCat/TensorTalk" \ --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": "TensorCat/TensorTalk", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use TensorCat/TensorTalk with Docker Model Runner:
docker model run hf.co/TensorCat/TensorTalk
Update README.md
Browse files
README.md
CHANGED
|
@@ -27,34 +27,6 @@ tags:
|
|
| 27 |
- education
|
| 28 |
- tensor-talk
|
| 29 |
---
|
| 30 |
-
---
|
| 31 |
-
license: other
|
| 32 |
-
language:
|
| 33 |
-
- en
|
| 34 |
-
- zh
|
| 35 |
-
tags:
|
| 36 |
-
- qwen3
|
| 37 |
-
- qwen3-8b
|
| 38 |
-
- lora
|
| 39 |
-
- qlora
|
| 40 |
-
- sft
|
| 41 |
-
- rag
|
| 42 |
-
- faiss
|
| 43 |
-
- dense-retrieval
|
| 44 |
-
- agent
|
| 45 |
-
- ppo
|
| 46 |
-
- rlhf
|
| 47 |
-
- rule-reward
|
| 48 |
-
- harness-engineering
|
| 49 |
-
- um-handbook
|
| 50 |
-
- question-answering
|
| 51 |
-
- chatbot
|
| 52 |
-
- education
|
| 53 |
-
- tensor-talk
|
| 54 |
-
pipeline_tag: text-generation
|
| 55 |
-
base_model: Qwen/Qwen3-8B
|
| 56 |
-
library_name: transformers
|
| 57 |
-
---
|
| 58 |
|
| 59 |
# TensorTalk: UM Handbook Qwen3-8B SFT + RAG + Agent + PPO + Harness Engineering
|
| 60 |
|
|
|
|
| 27 |
- education
|
| 28 |
- tensor-talk
|
| 29 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
|
| 31 |
# TensorTalk: UM Handbook Qwen3-8B SFT + RAG + Agent + PPO + Harness Engineering
|
| 32 |
|