Text Generation
Transformers
Hindi
English
india
hindi
code-assistant
chat-assistant
instruction-tuned
Eval Results (legacy)
Instructions to use Harshsfd/Bot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Harshsfd/Bot with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Harshsfd/Bot")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Harshsfd/Bot", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Harshsfd/Bot with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Harshsfd/Bot" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Harshsfd/Bot", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Harshsfd/Bot
- SGLang
How to use Harshsfd/Bot 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 "Harshsfd/Bot" \ --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": "Harshsfd/Bot", "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 "Harshsfd/Bot" \ --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": "Harshsfd/Bot", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Harshsfd/Bot with Docker Model Runner:
docker model run hf.co/Harshsfd/Bot
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- hi
|
| 5 |
+
- en
|
| 6 |
+
library_name: transformers
|
| 7 |
+
pipeline_tag: text-generation
|
| 8 |
+
base_model:
|
| 9 |
+
- mistralai/Mistral-7B-Instruct-v0.3
|
| 10 |
+
# You can swap this with any compatible instruct model you have rights to use
|
| 11 |
+
metrics:
|
| 12 |
+
- perplexity
|
| 13 |
+
- mt-bench
|
| 14 |
+
- bleu
|
| 15 |
+
datasets:
|
| 16 |
+
- openhermes
|
| 17 |
+
- hindi_qa_custom
|
| 18 |
+
# replace with your actual datasets
|
| 19 |
+
tags:
|
| 20 |
+
- india
|
| 21 |
+
- hindi
|
| 22 |
+
- code-assistant
|
| 23 |
+
- chat-assistant
|
| 24 |
+
- instruction-tuned
|
| 25 |
+
model-index:
|
| 26 |
+
- name: Harshsfd/Bot
|
| 27 |
+
results:
|
| 28 |
+
- task:
|
| 29 |
+
name: Text Generation
|
| 30 |
+
type: text-generation
|
| 31 |
+
dataset:
|
| 32 |
+
name: OpenHermes (subset)
|
| 33 |
+
type: openhermes
|
| 34 |
+
metrics:
|
| 35 |
+
- name: Perplexity
|
| 36 |
+
type: perplexity
|
| 37 |
+
value: 11.8
|
| 38 |
+
std: 0.4
|
| 39 |
+
verified: false
|
| 40 |
+
- name: MT-Bench (instruct)
|
| 41 |
+
type: mt-bench
|
| 42 |
+
value: 7.2
|
| 43 |
+
std: 0.2
|
| 44 |
+
verified: false
|
| 45 |
+
---
|