Downloads · 30 days
198
8% of all-time downloads
belyakoff_-_SmolLM2-360M-Instruct-FT-gguf
RichardErkhov/belyakoff_-_SmolLM2-360M-Instruct-FT-gguf
belyakoff_-_SmolLM2-360M-Instruct-FT-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.
All-time downloads
2.4K
Public
Repo size
4.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf5.1 GB · 100%
At a glance
- Access
- Public
- Created
- Nov 14, 2024
- Updated
- Nov 14, 2024
- SHA
- ae188686
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
SmolLM2-360M-Instruct-FT - GGUF
- Model creator: https://huggingface.co/belyakoff/
- Original model: https://huggingface.co/belyakoff/SmolLM2-360M-Instruct-FT/
| Name | Quant method | Size |
|---|---|---|
| SmolLM2-360M-Instruct-FT.Q2_K.gguf | Q2_K | 0.2GB |
| SmolLM2-360M-Instruct-FT.Q3_K_S.gguf | Q3_K_S | 0.2GB |
| SmolLM2-360M-Instruct-FT.Q3_K.gguf | Q3_K | 0.22GB |
| SmolLM2-360M-Instruct-FT.Q3_K_M.gguf | Q3_K_M | 0.22GB |
| SmolLM2-360M-Instruct-FT.Q3_K_L.gguf | Q3_K_L | 0.23GB |
| SmolLM2-360M-Instruct-FT.IQ4_XS.gguf | IQ4_XS | 0.21GB |
| SmolLM2-360M-Instruct-FT.Q4_0.gguf | Q4_0 | 0.21GB |
| SmolLM2-360M-Instruct-FT.IQ4_NL.gguf | IQ4_NL | 0.21GB |
| SmolLM2-360M-Instruct-FT.Q4_K_S.gguf | Q4_K_S | 0.24GB |
| SmolLM2-360M-Instruct-FT.Q4_K.gguf | Q4_K | 0.25GB |
| SmolLM2-360M-Instruct-FT.Q4_K_M.gguf | Q4_K_M | 0.25GB |
| SmolLM2-360M-Instruct-FT.Q4_1.gguf | Q4_1 | 0.23GB |
| SmolLM2-360M-Instruct-FT.Q5_0.gguf | Q5_0 | 0.25GB |
| SmolLM2-360M-Instruct-FT.Q5_K_S.gguf | Q5_K_S | 0.26GB |
| SmolLM2-360M-Instruct-FT.Q5_K.gguf | Q5_K | 0.27GB |
| SmolLM2-360M-Instruct-FT.Q5_K_M.gguf | Q5_K_M | 0.27GB |
| SmolLM2-360M-Instruct-FT.Q5_1.gguf | Q5_1 | 0.27GB |
| SmolLM2-360M-Instruct-FT.Q6_K.gguf | Q6_K | 0.34GB |
| SmolLM2-360M-Instruct-FT.Q8_0.gguf | Q8_0 | 0.36GB |
Original model description:
library_name: transformers license: apache-2.0 datasets:
- Vikhrmodels/GrandMaster-PRO-MAX language:
- ru base_model:
- HuggingFaceTB/SmolLM2-360M-Instruct pipeline_tag: text-generation tags:
- rag
Versions
v1: SFT -- 7658aab7702e56d9f5fa3b33bf7adcdae92f536b
Example
from transformers import AutoModelForCausalLM, AutoTokenizer
checkpoint = "belyakoff/SmolLM2-360M-Instruct-FT"
device = "cuda" # for GPU usage or "cpu" for CPU usage
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
# for multiple GPUs install accelerate and do `model = AutoModelForCausalLM.from_pretrained(checkpoint, device_map="auto")`
model = AutoModelForCausalLM.from_pretrained(checkpoint).to(device)
messages = [{"role": "user", "content": "Столица России?"}]
input_text=tokenizer.apply_chat_template(messages, tokenize=False)
print(input_text)
inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)
outputs = model.generate(inputs, max_new_tokens=50, temperature=0.2, top_p=0.9, do_sample=True)
print(tokenizer.decode(outputs[0]))
# Столица России — Москва. Это один из самых известных и культурно значимых городов в мире.
Limitations
Don't change system prompt. Changing system prompt will make the model go crazy.
- Created
- Nov 14, 2024
- Updated
- Nov 14, 2024