ESHMO-AI-DS-V4-Flash

Instructions to use Artificial-Development-Studios/ESHMO-AI-DS-V4-Flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Artificial-Development-Studios/ESHMO-AI-DS-V4-Flash with Transformers:

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

pipe = pipeline("text-generation", model="Artificial-Development-Studios/ESHMO-AI-DS-V4-Flash")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Artificial-Development-Studios/ESHMO-AI-DS-V4-Flash")
model = AutoModelForCausalLM.from_pretrained("Artificial-Development-Studios/ESHMO-AI-DS-V4-Flash")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Artificial-Development-Studios/ESHMO-AI-DS-V4-Flash with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Artificial-Development-Studios/ESHMO-AI-DS-V4-Flash"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Artificial-Development-Studios/ESHMO-AI-DS-V4-Flash",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Artificial-Development-Studios/ESHMO-AI-DS-V4-Flash

SGLang

How to use Artificial-Development-Studios/ESHMO-AI-DS-V4-Flash 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 "Artificial-Development-Studios/ESHMO-AI-DS-V4-Flash" \
    --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": "Artificial-Development-Studios/ESHMO-AI-DS-V4-Flash",
		"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 "Artificial-Development-Studios/ESHMO-AI-DS-V4-Flash" \
        --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": "Artificial-Development-Studios/ESHMO-AI-DS-V4-Flash",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Artificial-Development-Studios/ESHMO-AI-DS-V4-Flash with Docker Model Runner:
```
docker model run hf.co/Artificial-Development-Studios/ESHMO-AI-DS-V4-Flash
```

ESHMO-AI-DS-V4-Flash

File size: 991 Bytes

5c30e43

{
    "vocab_size": 129280,
    "dim": 4096,
    "moe_inter_dim": 2048,
    "n_layers": 43,
    "n_hash_layers": 3,
    "n_heads": 64,
    "n_routed_experts": 256,
    "n_shared_experts": 1,
    "n_activated_experts": 6,
    "score_func": "sqrtsoftplus",
    "route_scale": 1.5,
    "swiglu_limit": 10.0,
    "q_lora_rank": 1024,
    "head_dim": 512,
    "rope_head_dim": 64,
    "o_groups": 8,
    "o_lora_rank": 1024,
    "window_size": 128,
    "original_seq_len": 65536,
    "rope_theta": 10000,
    "rope_factor": 16,
    "beta_fast": 32,
    "beta_slow": 1,
    "index_n_heads": 64,
    "index_head_dim": 128,
    "index_topk": 512,
    "hc_mult": 4,
    "hc_sinkhorn_iters": 20,
    "dtype": "fp8",
    "scale_fmt": "ue8m0",
    "expert_dtype": "fp4",
    "compress_rope_theta": 160000,
    "compress_ratios": [0, 0, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 0]
}