YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co/docs/hub/model-cards#model-card-metadata)
Quantization made by Richard Erkhov.
expansion-train2 - GGUF
- Model creator: https://huggingface.co/ehristoforu/
- Original model: https://huggingface.co/ehristoforu/expansion-train2/
Name | Quant method | Size |
---|---|---|
expansion-train2.Q2_K.gguf | Q2_K | 0.08GB |
expansion-train2.IQ3_XS.gguf | IQ3_XS | 0.08GB |
expansion-train2.IQ3_S.gguf | IQ3_S | 0.08GB |
expansion-train2.Q3_K_S.gguf | Q3_K_S | 0.08GB |
expansion-train2.IQ3_M.gguf | IQ3_M | 0.09GB |
expansion-train2.Q3_K.gguf | Q3_K | 0.09GB |
expansion-train2.Q3_K_M.gguf | Q3_K_M | 0.09GB |
expansion-train2.Q3_K_L.gguf | Q3_K_L | 0.1GB |
expansion-train2.IQ4_XS.gguf | IQ4_XS | 0.1GB |
expansion-train2.Q4_0.gguf | Q4_0 | 0.1GB |
expansion-train2.IQ4_NL.gguf | IQ4_NL | 0.1GB |
expansion-train2.Q4_K_S.gguf | Q4_K_S | 0.1GB |
expansion-train2.Q4_K.gguf | Q4_K | 0.11GB |
expansion-train2.Q4_K_M.gguf | Q4_K_M | 0.11GB |
expansion-train2.Q4_1.gguf | Q4_1 | 0.11GB |
expansion-train2.Q5_0.gguf | Q5_0 | 0.11GB |
expansion-train2.Q5_K_S.gguf | Q5_K_S | 0.11GB |
expansion-train2.Q5_K.gguf | Q5_K | 0.12GB |
expansion-train2.Q5_K_M.gguf | Q5_K_M | 0.12GB |
expansion-train2.Q5_1.gguf | Q5_1 | 0.12GB |
expansion-train2.Q6_K.gguf | Q6_K | 0.13GB |
expansion-train2.Q8_0.gguf | Q8_0 | 0.17GB |
Original model description:
tags: - autotrain - text-generation-inference - text-generation library_name: transformers base_model: ehristoforu/expansion-train1 widget: - messages: - role: user content: What is your favorite condiment? license: other datasets: - MohamedRashad/midjourney-detailed-prompts
Model Trained Using AutoTrain
This model was trained using AutoTrain. For more information, please visit AutoTrain.
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model_path = "PATH_TO_THIS_REPO"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(
model_path,
device_map="auto",
torch_dtype='auto'
).eval()
# Prompt content: "hi"
messages = [
{"role": "user", "content": "hi"}
]
input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
output_ids = model.generate(input_ids.to('cuda'))
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
# Model response: "Hello! How can I assist you today?"
print(response)
- Downloads last month
- 3