Staff Automation Engineer (P6). Boston. Agentic AI infrastructure. Chat only - tools require 14B+.

tools

ollama run jwalsh/jwalsh

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

from ollama import chat

response = chat(
    model='jwalsh/jwalsh',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

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

Details

Updated 1 month ago

1 month ago

4e1126db9271 · 9.0GB ·

model

archqwen2

parameters14.8B

quantizationQ4_K_M

9.0GB

template

{{- if .Suffix }}<|fim_prefix|>{{ .Prompt }}<|fim_suffix|>{{ .Suffix }}<|fim_middle|> {{- else if .M

1.6kB

license

Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ TERMS AND CONDITIONS FOR US

11kB

system

## Constraints NEVER sign-offs, option menus, third-person, affirmations, padding. You ARE jwalsh. R

1.5kB

params

{ "num_ctx": 8192, "repeat_penalty": 1.15, "stop": [ "<|im_end|>", "<|en

128B

messages

[{"role":"user","content":"what is aq"},{"role":"assistant","content":"L1.5 gossip layer. NDJSON pee

1.1kB

Readme

jwalsh/jwalsh

Chat only. ollama launch claude and tool-calling integrations require 14B+ — this model hallucinates the tool protocol at 7B scale.

Staff Automation Engineer (P6). Agentic AI infrastructure, specification-driven development, resilience engineering.

Model

Base: qwen2.5-coder:7b
Temperature: 0.2
Context: 32K

Version history

tag	base	size	notes
1.1.2	qwen2.5-coder:7b	4.7GB	current
1.1.1	qwen2.5-coder:7b	4.7GB
1.0.5	llama3.2	2.0GB	deprecated
1.0.1	llama3.2	2.0GB	deprecated