Text Generation
Transformers
Safetensors
qwen3
GRPO
Reasoning-Course
trl
sft
text-generation-inference
Instructions to use halxj/Devjalx-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use halxj/Devjalx-4b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="halxj/Devjalx-4b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("halxj/Devjalx-4b") model = AutoModelForCausalLM.from_pretrained("halxj/Devjalx-4b") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use halxj/Devjalx-4b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "halxj/Devjalx-4b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "halxj/Devjalx-4b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/halxj/Devjalx-4b
- SGLang
How to use halxj/Devjalx-4b 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 "halxj/Devjalx-4b" \ --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": "halxj/Devjalx-4b", "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 "halxj/Devjalx-4b" \ --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": "halxj/Devjalx-4b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use halxj/Devjalx-4b with Docker Model Runner:
docker model run hf.co/halxj/Devjalx-4b
Upload Qwen3ForCausalLM
Browse files- config.json +1 -1
- generation_config.json +1 -1
- model.safetensors +1 -1
config.json
CHANGED
|
@@ -64,7 +64,7 @@
|
|
| 64 |
},
|
| 65 |
"sliding_window": null,
|
| 66 |
"tie_word_embeddings": true,
|
| 67 |
-
"transformers_version": "5.
|
| 68 |
"use_cache": true,
|
| 69 |
"use_sliding_window": false,
|
| 70 |
"vocab_size": 151936
|
|
|
|
| 64 |
},
|
| 65 |
"sliding_window": null,
|
| 66 |
"tie_word_embeddings": true,
|
| 67 |
+
"transformers_version": "5.5.0",
|
| 68 |
"use_cache": true,
|
| 69 |
"use_sliding_window": false,
|
| 70 |
"vocab_size": 151936
|
generation_config.json
CHANGED
|
@@ -9,5 +9,5 @@
|
|
| 9 |
"temperature": 0.7,
|
| 10 |
"top_k": 20,
|
| 11 |
"top_p": 0.8,
|
| 12 |
-
"transformers_version": "5.
|
| 13 |
}
|
|
|
|
| 9 |
"temperature": 0.7,
|
| 10 |
"top_k": 20,
|
| 11 |
"top_p": 0.8,
|
| 12 |
+
"transformers_version": "5.5.0"
|
| 13 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 8044982080
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3d9905ebc73faa0ab094a4dfc4447a3e0c66a589fbbdd8148119a0fabd96c33
|
| 3 |
size 8044982080
|