Instructions to use mkd-hossain/keural-sft-18k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mkd-hossain/keural-sft-18k with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="mkd-hossain/keural-sft-18k", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("mkd-hossain/keural-sft-18k", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mkd-hossain/keural-sft-18k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mkd-hossain/keural-sft-18k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mkd-hossain/keural-sft-18k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mkd-hossain/keural-sft-18k

SGLang

How to use mkd-hossain/keural-sft-18k 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 "mkd-hossain/keural-sft-18k" \
    --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": "mkd-hossain/keural-sft-18k",
		"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 "mkd-hossain/keural-sft-18k" \
        --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": "mkd-hossain/keural-sft-18k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mkd-hossain/keural-sft-18k with Docker Model Runner:
```
docker model run hf.co/mkd-hossain/keural-sft-18k
```

mkd-hossain commited on May 18

Commit

93eba2f

verified ·

1 Parent(s): 6e0606b

Upload config.json with huggingface_hub

Browse files

Files changed (1) hide show

config.json +28 -0

config.json ADDED Viewed

	@@ -0,0 +1,28 @@

+{
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "model_type": "mixtral",
+  "vocab_size": 131074,
+  "hidden_size": 4096,
+  "intermediate_size": 5632,
+  "num_hidden_layers": 24,
+  "num_attention_heads": 32,
+  "num_key_value_heads": 8,
+  "head_dim": 128,
+  "num_local_experts": 8,
+  "num_experts_per_tok": 2,
+  "max_position_embeddings": 4096,
+  "rope_theta": 500000.0,
+  "rms_norm_eps": 1e-05,
+  "sliding_window": 512,
+  "hidden_act": "silu",
+  "initializer_range": 0.02,
+  "use_cache": true,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0",
+  "output_router_logits": false,
+  "router_aux_loss_coef": 0.001,
+  "keural_step": 18000
+}