mannix/llama3.1-storm

mannix/ llama3.1-storm

573 Downloads Updated 1 year ago

Llama-3.1-Storm-8B outperforms both Llama-3.1-8B-Instruct and Hermes-3-Llama-3.1-8B!

tools

ollama run mannix/llama3.1-storm

curl http://localhost:11434/api/chat \
  -d '{
    "model": "mannix/llama3.1-storm",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='mannix/llama3.1-storm',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'mannix/llama3.1-storm',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code

Claude Code ollama launch claude --model mannix/llama3.1-storm

Codex

Codex ollama launch codex --model mannix/llama3.1-storm

OpenCode

OpenCode ollama launch opencode --model mannix/llama3.1-storm

OpenClaw

OpenClaw ollama launch openclaw --model mannix/llama3.1-storm

Models

Name

13 models

Size

Context

Input

llama3.1-storm:latest

4.7GB · 128K context window · Text · 1 year ago

llama3.1-storm:latest

4.7GB

128K

Text

llama3.1-storm:q2_k

3.2GB · 128K context window · Text · 1 year ago

llama3.1-storm:q2_k

3.2GB

128K

Text

llama3.1-storm:q3_k_s

3.7GB · 128K context window · Text · 1 year ago

llama3.1-storm:q3_k_s

3.7GB

128K

Text

llama3.1-storm:q3_k_l

4.3GB · 128K context window · Text · 1 year ago

llama3.1-storm:q3_k_l

4.3GB

128K

Text

llama3.1-storm:q4_0

4.7GB · 128K context window · Text · 1 year ago

llama3.1-storm:q4_0

4.7GB

128K

Text

llama3.1-storm:q5_0

5.6GB · 128K context window · Text · 1 year ago

llama3.1-storm:q5_0

5.6GB

128K

Text

llama3.1-storm:q5_1

6.1GB · 128K context window · Text · 1 year ago

llama3.1-storm:q5_1

6.1GB

128K

Text

llama3.1-storm:q5_k_s

5.6GB · 128K context window · Text · 1 year ago

llama3.1-storm:q5_k_s

5.6GB

128K

Text

llama3.1-storm:q5_k_m

5.7GB · 128K context window · Text · 1 year ago

llama3.1-storm:q5_k_m

5.7GB

128K

Text

llama3.1-storm:q6_k

6.6GB · 128K context window · Text · 1 year ago

llama3.1-storm:q6_k

6.6GB

128K

Text

llama3.1-storm:q8_0

8.5GB · 128K context window · Text · 1 year ago

llama3.1-storm:q8_0

8.5GB

128K

Text

llama3.1-storm:iq3_xxs

3.3GB · 128K context window · Text · 1 year ago

llama3.1-storm:iq3_xxs

3.3GB

128K

Text

llama3.1-storm:fp16

16GB · 128K context window · Text · 1 year ago

llama3.1-storm:fp16

16GB

128K

Text

Readme

Quantization from fp32
Using i-matrix calibration_datav3.txt

🤗 Announcement Blog: https://huggingface.co/blog/akjindal53244/llama31-storm8b

Llama-3.1-Storm-8B: Improved SLM with Self-Curation + Model Merging