🌿 Stoner Bud-E (Kartoon93/stoner-bud-e)
Stoner Bud-E is a 7.62B-parameter conversational language model (Qwen2ForCausalLM, bfloat16) tailored for cannabis culture, strain genetics, terpene pharmacology, vaporizer temperature guidance, and responsible edible dosing education.
- 🚀 Live Interactive Space & Sommelier Suite: spaces/Kartoon93/stoner-bud-e
- 🌐 Direct Web App URL: https://kartoon93-stoner-bud-e.static.hf.space/index.html
📊 Model Specifications
| Property | Value |
|---|---|
| Architecture | Qwen2ForCausalLM (Qwen/Qwen2.5-7B-Instruct family) |
| Total Parameters | 7,615,616,512 (7.62B) |
| Tensor Precision | BF16 (safetensors, 4 shards, ~15.24 GB) |
| Context Length | 32,768 tokens |
| Hidden Size / Layers | 3584 hidden dim / 28 transformer layers |
| Attention Heads (GQA) | 28 Query heads / 4 Key-Value heads |
| Vocabulary Size | 152,064 |
💻 Quickstart (transformers)
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
MODEL_ID = "Kartoon93/stoner-bud-e"
tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
model = AutoModelForCausalLM.from_pretrained(
MODEL_ID,
dtype=torch.bfloat16,
attn_implementation="sdpa",
device_map="auto",
).eval()
messages = [
{
"role": "system",
"content": (
"You are Stoner Bud-E, a chill, friendly, and knowledgeable AI budtender "
"and cannabis sommelier."
),
},
{
"role": "user",
"content": "Compare Blue Dream and Gelato — terpene profiles, lineage, and effects.",
},
]
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer([prompt], return_tensors="pt").to(model.device)
with torch.no_grad():
output_ids = model.generate(
**inputs,
max_new_tokens=512,
temperature=0.7,
top_p=0.8,
repetition_penalty=1.05,
)
response = tokenizer.decode(output_ids[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)
print(response)
- Downloads last month
- -