Update README.md
Browse files
README.md
CHANGED
|
@@ -149,7 +149,7 @@ ilab model download --repository docker://registry.redhat.io/rhelai1/mistral-sma
|
|
| 149 |
|
| 150 |
```bash
|
| 151 |
# Serve model via ilab
|
| 152 |
-
ilab model serve --model-path ~/.cache/instructlab/models/mistral-small-24b-instruct-2501
|
| 153 |
|
| 154 |
# Chat with model
|
| 155 |
ilab model chat --model ~/.cache/instructlab/models/mistral-small-24b-instruct-2501
|
|
@@ -216,6 +216,17 @@ spec:
|
|
| 216 |
maxReplicas: 1
|
| 217 |
minReplicas: 1
|
| 218 |
model:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 219 |
modelFormat:
|
| 220 |
name: vLLM
|
| 221 |
name: ''
|
|
|
|
| 149 |
|
| 150 |
```bash
|
| 151 |
# Serve model via ilab
|
| 152 |
+
ilab model serve --model-path ~/.cache/instructlab/models/mistral-small-24b-instruct-2501 --gpu 1 -- --tokenizer-mode "mistral" --config-format "mistral" --load-format "mistral" --tool-call-parser "mistral" --enable-auto-tool-choice --limit-mm-per-prompt "image=10" --max-model-len 16384 --uvicorn-log-level "debug" --trust-remote-code
|
| 153 |
|
| 154 |
# Chat with model
|
| 155 |
ilab model chat --model ~/.cache/instructlab/models/mistral-small-24b-instruct-2501
|
|
|
|
| 216 |
maxReplicas: 1
|
| 217 |
minReplicas: 1
|
| 218 |
model:
|
| 219 |
+
args:
|
| 220 |
+
- "--tokenizer-mode=mistral"
|
| 221 |
+
- "--config-format=mistral"
|
| 222 |
+
- "--load-format=mistral"
|
| 223 |
+
- "--tool-call-parser=mistral"
|
| 224 |
+
- "--enable-auto-tool-choice"
|
| 225 |
+
- "--limit-mm-per-prompt=image=10"
|
| 226 |
+
- "--max-model-len=16384"
|
| 227 |
+
- "--uvicorn-log-level=debug"
|
| 228 |
+
- "--trust-remote-code"
|
| 229 |
+
|
| 230 |
modelFormat:
|
| 231 |
name: vLLM
|
| 232 |
name: ''
|