Downloads · 30 days
147
4% of all-time downloads
RichardErkhov/ehristoforu_-_llama-3-12b-instruct-gguf
ehristoforu_-_llama-3-12b-instruct-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
147
4% of all-time downloads
All-time downloads
3.4K
Public
Repo size
137 GB
Likes
0
Public
Click a slice to open those files.
.gguf159 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
llama-3-12b-instruct - GGUF
| Name | Quant method | Size |
|---|---|---|
| llama-3-12b-instruct.Q2_K.gguf | Q2_K | 4.31GB |
| llama-3-12b-instruct.IQ3_XS.gguf | IQ3_XS | 4.77GB |
| llama-3-12b-instruct.IQ3_S.gguf | IQ3_S | 5.01GB |
| llama-3-12b-instruct.Q3_K_S.gguf | Q3_K_S | 4.98GB |
| llama-3-12b-instruct.IQ3_M.gguf | IQ3_M | 5.16GB |
| llama-3-12b-instruct.Q3_K.gguf | Q3_K | 5.5GB |
| llama-3-12b-instruct.Q3_K_M.gguf | Q3_K_M | 5.5GB |
| llama-3-12b-instruct.Q3_K_L.gguf | Q3_K_L | 5.94GB |
| llama-3-12b-instruct.IQ4_XS.gguf | IQ4_XS | 6.15GB |
| llama-3-12b-instruct.Q4_0.gguf | Q4_0 | 6.4GB |
| llama-3-12b-instruct.IQ4_NL.gguf | IQ4_NL | 6.46GB |
| llama-3-12b-instruct.Q4_K_S.gguf | Q4_K_S | 6.44GB |
| llama-3-12b-instruct.Q4_K.gguf | Q4_K | 6.78GB |
| llama-3-12b-instruct.Q4_K_M.gguf | Q4_K_M | 6.78GB |
| llama-3-12b-instruct.Q4_1.gguf | Q4_1 | 7.06GB |
| llama-3-12b-instruct.Q5_0.gguf | Q5_0 | 7.73GB |
| llama-3-12b-instruct.Q5_K_S.gguf | Q5_K_S | 7.73GB |
| llama-3-12b-instruct.Q5_K.gguf | Q5_K | 7.92GB |
| llama-3-12b-instruct.Q5_K_M.gguf | Q5_K_M | 7.92GB |
| llama-3-12b-instruct.Q5_1.gguf | Q5_1 | 8.39GB |
| llama-3-12b-instruct.Q6_K.gguf | Q6_K | 9.14GB |
| llama-3-12b-instruct.Q8_0.gguf | Q8_0 | 11.84GB |
base_model:

We created a model from other cool models to combine everything into one cool model.
Use the code below to get started with the model.
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
model_id = "ehristoforu/llama-3-12b-instruct"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
device_map="auto",
)
messages = [
{"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
{"role": "user", "content": "Who are you?"},
]
input_ids = tokenizer.apply_chat_template(
messages,
add_generation_prompt=True,
return_tensors="pt"
).to(model.device)
terminators = [
tokenizer.eos_token_id,
tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
outputs = model.generate(
input_ids,
max_new_tokens=256,
eos_token_id=terminators,
do_sample=True,
temperature=0.6,
top_p=0.9,
)
response = outputs[0][input_ids.shape[-1]:]
print(tokenizer.decode(response, skip_special_tokens=True))
Base model: Meta-Llama-3-8B-Instruct
Merge models:
Merge datasets: