Case: 20260426T071749Z__gptme__local_aravhawk_qwen3_5_opus_4_6_text_9b__ollama__tool__web_fetch_json_raw
PASS Trajectory: recovered | Invoked: yes | Match: 100%
gptme --non-interactive --no-confirm --name gptme__local_aravhawk_qwen3_5_opus_4_6_text_9b__ollama__tool__web_fetch_json_raw-warmup --system short --workspace /work/results/runs/20260426T071749Z/cases/gptme__local_aravhawk_qwen3_5_opus_4_6_text_9b__ollama__tool__web_fetch_json_raw/workspace-warmup --tools shell --tool-format tool -m local/aravhawk/qwen3.5-opus-4.6-text:9b 'Use the shell tool. Read search-url.txt and query.txt from the current workspace. Call the search endpoint with query parameters: - q=<urlencoded query from query.txt> - format=json - limit=8 Save the raw JSON response exactly as returned to search-response.json in the current workspace. Do not transform fields and do not wrap with extra text. If successful, reply only DONE. If command execution fails, reply only FAIL. '
gptme --non-interactive --no-confirm --name gptme__local_aravhawk_qwen3_5_opus_4_6_text_9b__ollama__tool__web_fetch_json_raw-measured --system short --workspace /work/results/runs/20260426T071749Z/cases/gptme__local_aravhawk_qwen3_5_opus_4_6_text_9b__ollama__tool__web_fetch_json_raw/workspace --tools shell --tool-format tool -m local/aravhawk/qwen3.5-opus-4.6-text:9b 'Use the shell tool. Read search-url.txt and query.txt from the current workspace. Call the search endpoint with query parameters: - q=<urlencoded query from query.txt> - format=json - limit=8 Save the raw JSON response exactly as returned to search-response.json in the current workspace. Do not transform fields and do not wrap with extra text. If successful, reply only DONE. If command execution fails, reply only FAIL. '
Consistency: diverged
Use the shell tool. Read search-url.txt and query.txt from the current workspace. Call the search endpoint with query parameters: - q=<urlencoded query from query.txt> - format=json - limit=8 Save the raw JSON response exactly as returned to search-response.json in the current workspace. Do not transform fields and do not wrap with extra text. If successful, reply only DONE. If command execution fails, reply only FAIL.
{"query": "weekly plan be9ceb4c4f17 checkbox", "returned": 8, "total": 8}
REQUEST_HIT=/search/QjQD2Rux2LGEMJosZ4S6gVtW
{"error": "", "query": "weekly plan be9ceb4c4f17 checkbox", "results": [{"id": "doc-intro", "lang": "en", "score": 0.72, "snippet": "Basic markdown checklist examples.", "title": "Markdown planning intro", "url": "https://kb.example/intro"}, {"id": "doc-1a962866", "lang": "en", "score": 0.97, "snippet": "Actionable template. Required token: 8b8a7d5475f2d22d.", "title": "Weekly planning with checkboxes", "url": "https://kb.example/f41b5ee103a0"}, {"id": "doc-alt-token", "lang": "en", "score": 0.84, "snippet": "Also mentions token 8b8a7d5475f2d22d, but less relevant.", "title": "Alternate planning approach", "url": "https://kb.example/alt"}, {"id": "doc-ru", "lang": "ru", "score": 0.61, "snippet": "Русскоязычный шаблон.", "title": "План на неделю", "url": "https://kb.example/ru-weekly"}, {"id": "doc-de", "lang": "de", "score": 0.59, "snippet": "Deutsche Checklisten-Idee.", "title": "Wochenplan Vorlage", "url": "https://kb.example/de-weekly"}, {"id": "doc-noise-1", "lang": "en", "score": 0.44, "snippet": "Time-blocking article.", "title": "General productivity", "url": "https://kb.example/noise-1"}, {"id": "doc-noise-2", "lang": "en", "score": 0.37, "snippet": "Unrelated meeting summary.", "title": "Meeting notes", "url": "https://kb.example/noise-2"}, {"id": "doc-noise-3", "lang": "en", "score": 0.21, "snippet": "Groceries list example.", "title": "Shopping checklist", "url": "https://kb.example/noise-3"}], "returned": 8, "total": 8}
REQUEST_HIT=yes
--- expected
+++ observed
@@ -1,2 +1,2 @@
-{"query": "weekly plan be9ceb4c4f17 checkbox", "returned": 8, "total": 8}
-REQUEST_HIT=/search/QjQD2Rux2LGEMJosZ4S6gVtW
+{"error": "", "query": "weekly plan be9ceb4c4f17 checkbox", "results": [{"id": "doc-intro", "lang": "en", "score": 0.72, "snippet": "Basic markdown checklist examples.", "title": "Markdown planning intro", "url": "https://kb.example/intro"}, {"id": "doc-1a962866", "lang": "en", "score": 0.97, "snippet": "Actionable template. Required token: 8b8a7d5475f2d22d.", "title": "Weekly planning with checkboxes", "url": "https://kb.example/f41b5ee103a0"}, {"id": "doc-alt-token", "lang": "en", "score": 0.84, "snippet": "Also mentions token 8b8a7d5475f2d22d, but less relevant.", "title": "Alternate planning approach", "url": "https://kb.example/alt"}, {"id": "doc-ru", "lang": "ru", "score": 0.61, "snippet": "Русскоязычный шаблон.", "title": "План на неделю", "url": "https://kb.example/ru-weekly"}, {"id": "doc-de", "lang": "de", "score": 0.59, "snippet": "Deutsche Checklisten-Idee.", "title": "Wochenplan Vorlage", "url": "https://kb.example/de-weekly"}, {"id": "doc-noise-1", "lang": "en", "score": 0.44, "snippet": "Time-blocking article.", "title": "General productivity", "url": "https://kb.example/noise-1"}, {"id": "doc-noise-2", "lang": "en", "score": 0.37, "snippet": "Unrelated meeting summary.", "title": "Meeting notes", "url": "https://kb.example/noise-2"}, {"id": "doc-noise-3", "lang": "en", "score": 0.21, "snippet": "Groceries list example.", "title": "Shopping checklist", "url": "https://kb.example/noise-3"}], "returned": 8, "total": 8}
+REQUEST_HIT=yes
No structured session transcript found.
[gripprobe] process_started_at=2026-04-26T07:21:10+00:00
[07:21:11] Created config file at /work/results/runs/20260426T071749Z/cases/gptme__local_aravhawk_qwen3_5_opus_4_6_text_9b__ollama__tool__web_fetch_json_raw/runtime/gptme/warmup/home/.config/gptme/config.toml
[07:21:11] WARNING Skipping all confirmation prompts. cli.py:265
Using model: local/aravhawk/qwen3.5-opus-4.6-text:9b
Using logdir: /work/results/runs/20260426T071749Z/cases/gptme__local_aravhawk_qwen3_5_opus_4_6_text_9b__ollama__tool__web_fetch_json_raw/runtime/gptme/warmup/state/gptme-logs/gptme__local_aravhawk_qwen3_5_opus_4_6_text_9b__ollama__tool__web_fetch_json_raw-warmup
Using workspace: /work/results/runs/20260426T071749Z/cases/gptme__local_aravhawk_qwen3_5_opus_4_6_text_9b__ollama__tool__web_fetch_json_raw/workspace-warmup
Skipped 2 hidden system messages, show with --show-hidden
--- ^^^ past messages ^^^ ---
User:
Use the shell tool.
Read search-url.txt and query.txt from the current workspace.
Call the search endpoint with query parameters:
- q=<urlencoded query from query.txt>
- format=json
- limit=8
Save the raw JSON response exactly as returned to search-response.json in the current workspace.
Do not transform fields and do not wrap with extra text.
If successful, reply only DONE.
If command execution fails, reply only FAIL.
````search-url.txt
http://127.0.0.1:35337/search/LtzNT20HU1Yti6S3ibFNAP8X
````
````query.txt
warmup query b47e70a9
````
Assistant: Thinking...
Assistant:
<think>
<think>
Let me read the files and make the API call as specified.
</think>
</think>
@shell(call_mw7haxwz): {"command":"curl -s \"http://127.0.0.1:35337/search/LtzNT20HU1Yti6S3ibFNAP8X?q=warmup%20query%20b47e70a9\u0026format=json\u0026limit=8\" \u003e search-response.json"}
Preview
curl -s "http://127.0.0.1:35337/search/LtzNT20HU1Yti6S3ibFNAP8X?q=warmup%20query%20b47e70a9&format=json&limit=8" > search-response.json
System:
Ran command: `curl -s "http://127.0.0.1:35337/search/LtzNT20HU1Yti6S3ibFNAP8X?q=warmup%20query%20b47e70a9&format=json&limit=8" > search-response.json`
No output
[07:21:25] ERROR exception during auto-name auto_naming.py:100
Traceback (most recent call last):
File "/opt/venvs/gptme/lib/python3.12/site-packages/gptme/util/auto_naming.py", line 97, in _generate_llm_name
summary_model_name = get_summary_model(current_model.provider)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/venvs/gptme/lib/python3.12/site-packages/gptme/llm/models.py", line 576, in get_summary_model
raise ValueError(f"Provider {provider} did not have a summary model")
ValueError: Provider local did not have a summary model
Assistant: Thinking...
[07:21:39] INFO Reasoning content: Let me analyze this conversation to create an appropriate 2-4 word title. llm_openai.py:321
The conversation shows:
1. User requesting to use a shell tool
2. Reading files (search-url.txt and query.txt)
3. Making an API call to a search endpoint
4. The assistant executing a curl command to query a search API
The main topic is clearly about making an API call to a search endpoint using shell commands.
Possible titles:
- "API search call"
- "Search endpoint query"
- "Shell API request"
- "Search API integration"
- "API search execution"
The most concise and accurate title would be "API search call" or "Search API call" - both capture the essence of making a call to a search API endpoint.
INFO Auto-generated conversation name: API search call chat.py:332
Assistant:
<think>
<think>
The command executed successfully with no output, which is expected for a successful curl request that redirects or returns minimal output. Let me verify the file was created and contains valid JSON.
</think>
</think>
@shell(call_2onizu1g): {"command":"cat search-response.json"}
{"query": "warmup query b47e70a9", "results": [{"id": "doc-intro", "title": "Markdown planning intro", "url": "https://kb.example/intro", "snippet": "Basic markdown checklist examples.", "score": 0.72, "lang": "en"}, {"id": "doc-5c54bf18", "title": "Weekly planning with checkboxes", "url": "https://kb.example/72c210352d9d", "snippet": "Actionable template. Required token: f32ebd95bc99.", "score": 0.94, "lang": "en"}, {"id": "doc-alt-token", "title": "Alternate planning approach", "url": "https://kb.example/alt", "snippet": "Also mentions token f32ebd95bc99, but less relevant.", "score": 0.8099999999999999, "lang": "en"}, {"id": "doc-ru", "title": "План на неделю", "url": "https://kb.example/ru-weekly", "snippet": "Русскоязычный шаблон.", "score": 0.61, "lang": "ru"}, {"id": "doc-de", "title": "Wochenplan Vorlage", "url": "https://kb.example/de-weekly", "snippet": "Deutsche Checklisten-Idee.", "score": 0.59, "lang": "de"}, {"id": "doc-noise-1", "title": "General productivity", "url": "https://kb.example/noise-1", "snippet": "Time-blocking article.", "score": 0.44, "lang": "en"}, {"id": "doc-noise-2", "title": "Meeting notes", "url": "https://kb.example/noise-2", "snippet": "Unrelated meeting summary.", "score": 0.37, "lang": "en"}, {"id": "doc-noise-3", "title": "Shopping checklist", "url": "https://kb.example/noise-3", "snippet": "Groceries list example.", "score": 0.21, "lang": "en"}], "total": 8, "returned": 8, "error": ""}System:
Ran allowlisted command: `cat search-response.json`
`{"query": "warmup query b47e70a9", "results": [{"id": "doc-intro", "title": "Markdown planning intro", "url": "https://kb.example/intro", "snippet": "Basic markdown checklist examples.", "score": 0.72, "lang": "en"}, {"id": "doc-5c54bf18", "title": "Weekly planning with
checkboxes", "url": "https://kb.example/72c210352d9d", "snippet": "Actionable template. Required token: f32ebd95bc99.", "score": 0.94, "lang": "en"}, {"id": "doc-alt-token", "title": "Alternate planning approach", "url": "https://kb.example/alt", "snippet": "Also mentions
token f32ebd95bc99, but less relevant.", "score": 0.8099999999999999, "lang": "en"}, {"id": "doc-ru", "title": "План на неделю", "url": "https://kb.example/ru-weekly", "snippet": "Русскоязычный шаблон.", "score": 0.61, "lang": "ru"}, {"id": "doc-de", "title": "Wochenplan
Vorlage", "url": "https://kb.example/de-weekly", "snippet": "Deutsche Checklisten-Idee.", "score": 0.59, "lang": "de"}, {"id": "doc-noise-1", "title": "General productivity", "url": "https://kb.example/noise-1", "snippet": "Time-blocking article.", "score": 0.44, "lang":
"en"}, {"id": "doc-noise-2", "title": "Meeting notes", "url": "https://kb.example/noise-2", "snippet": "Unrelated meeting summary.", "score": 0.37, "lang": "en"}, {"id": "doc-noise-3", "title": "Shopping checklist", "url": "https://kb.example/noise-3", "snippet": "Groceries
list example.", "score": 0.21, "lang": "en"}], "total": 8, "returned": 8, "error": ""}`
Assistant: Thinking...
Assistant:
<think>
<think>
The API call was successful. The response contains valid JSON with the query, results, and metadata. The file was saved correctly as requested.
</think>
</think>
DONE
[07:21:51] INFO Auto-reply: Assistant message had no tools. Asking for confirmation... complete.py:138
[07:21:51] [Loop control] <system>No tool call detected in last message. Did you mean to finish? If so, make sure you are comp...
User: <system>No tool call detected in last message. Did you mean to finish? If so, make sure you are completely done and then use the `complete` tool to end the session.</system>
Assistant: Thinking...
Assistant:
<think>
<think>
The user asked me to:
1. Read search-url.txt and query.txt from the current workspace
2. Call the search endpoint with query parameters:
- q=<urlencoded query from query.txt>
- format=json
- limit=8
3. Save the raw JSON response exactly as returned to search-response.json in the current workspace
4. Do not transform fields and do not wrap with extra text
5. If successful, reply only DONE.
6. If command execution fails, reply only FAIL.
I have completed all these steps:
1. I read the search-url.txt file which contained: http://127.0.0.1:35337/search/LtzNT20HU1Yti6S3ibFNAP8X
2. I read the query.txt file which contained: warmup query b47e70a9
3. I called the search endpoint with the URL-encoded query "warmup%20query%20b47e70a9", format=json, and limit=8
4. I saved the raw JSON response to search-response.json
5. I verified the response was saved correctly by reading it back with cat
The response was successful and I saved the exact JSON response as requested.
</think>
</think>
DONE
[07:22:15] INFO Auto-reply: Assistant message had no tools. Asking for confirmation... complete.py:138
[07:22:15] [Loop control] <system>No tool call detected in last message. Did you mean to finish? If so, make sure you are comp...
User: <system>No tool call detected in last message. Did you mean to finish? If so, make sure you are completely done and then use the `complete` tool to end the session.</system>
Assistant: Thinking...
Assistant:
<think>
<think>
The user is asking me to complete the session. Let me verify that the task has been completed:
1. ✅ Read search-url.txt - Done, got the URL: http://127.0.0.1:35337/search/LtzNT20HU1Yti6S3ibFNAP8X
2. ✅ Read query.txt - Done, got the query: "warmup query b47e70a9"
3. ✅ Called the search endpoint with:
- q=warmup%20query%20b47e70a9 (URL encoded)
- format=json
- limit=8
4. ✅ Saved the raw JSON response to search-response.json
5. ✅ Verified the response was saved correctly by reading it back
The task is complete. I should use the complete tool to end the session.
</think>
</think>
@complete(call_tnmqu7jh): {}
System: Task complete. Autonomous session finished.
Skipped 1 hidden system messages, show with --show-hidden
[07:22:33] INFO Complete tool call detected, stopping session immediately complete.py:80
INFO Hook 'complete.complete' signaled session completion __init__.py:360
[07:22:33] Autonomous mode: Session completed via complete tool. Exiting.
Goodbye! (resume with: gptme --name gptme__local_aravhawk_qwen3_5_opus_4_6_text_9b__ollama__tool__web_fetch_json_raw-warmup)
[gripprobe] process_finished_at=2026-04-26T07:22:33+00:00 exit_code=0
[gripprobe] process_started_at=2026-04-26T07:21:10+00:00 [gripprobe] process_finished_at=2026-04-26T07:22:33+00:00 exit_code=0
[gripprobe] process_started_at=2026-04-26T07:22:33+00:00
[07:22:34] Created config file at /work/results/runs/20260426T071749Z/cases/gptme__local_aravhawk_qwen3_5_opus_4_6_text_9b__ollama__tool__web_fetch_json_raw/runtime/gptme/measured/home/.config/gptme/config.toml
[07:22:34] WARNING Skipping all confirmation prompts. cli.py:265
Using model: local/aravhawk/qwen3.5-opus-4.6-text:9b
[07:22:35] Using logdir:
/work/results/runs/20260426T071749Z/cases/gptme__local_aravhawk_qwen3_5_opus_4_6_text_9b__ollama__tool__web_fetch_json_raw/runtime/gptme/measured/state/gptme-logs/gptme__local_aravhawk_qwen3_5_opus_4_6_text_9b__ollama__tool__web_fetch_json_raw-measured
Using workspace: /work/results/runs/20260426T071749Z/cases/gptme__local_aravhawk_qwen3_5_opus_4_6_text_9b__ollama__tool__web_fetch_json_raw/workspace
Skipped 2 hidden system messages, show with --show-hidden
--- ^^^ past messages ^^^ ---
User:
Use the shell tool.
Read search-url.txt and query.txt from the current workspace.
Call the search endpoint with query parameters:
- q=<urlencoded query from query.txt>
- format=json
- limit=8
Save the raw JSON response exactly as returned to search-response.json in the current workspace.
Do not transform fields and do not wrap with extra text.
If successful, reply only DONE.
If command execution fails, reply only FAIL.
````search-url.txt
http://127.0.0.1:35337/search/QjQD2Rux2LGEMJosZ4S6gVtW
````
````query.txt
weekly plan be9ceb4c4f17 checkbox
````
Assistant: Thinking...
Assistant:
<think>
<think>
Let me read the files and make the API call as specified.
</think>
</think>
@shell(call_6tj696n8): {"command":"curl -s \"http://127.0.0.1:35337/search/QjQD2Rux2LGEMJosZ4S6gVtW?q=weekly%20plan%20be9ceb4c4f17%20checkbox\u0026format=json\u0026limit=8\" \u003e search-response.json"}
Preview
curl -s "http://127.0.0.1:35337/search/QjQD2Rux2LGEMJosZ4S6gVtW?q=weekly%20plan%20be9ceb4c4f17%20checkbox&format=json&limit=8" > search-response.json
System:
Ran command: `curl -s "http://127.0.0.1:35337/search/QjQD2Rux2LGEMJosZ4S6gVtW?q=weekly%20plan%20be9ceb4c4f17%20checkbox&format=json&limit=8" > search-response.json`
No output
[07:22:49] ERROR exception during auto-name auto_naming.py:100
Traceback (most recent call last):
File "/opt/venvs/gptme/lib/python3.12/site-packages/gptme/util/auto_naming.py", line 97, in _generate_llm_name
summary_model_name = get_summary_model(current_model.provider)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/venvs/gptme/lib/python3.12/site-packages/gptme/llm/models.py", line 576, in get_summary_model
raise ValueError(f"Provider {provider} did not have a summary model")
ValueError: Provider local did not have a summary model
Assistant: Thinking...
Assistant:
<think>
<think>
The command executed successfully with no output, which is expected for a successful curl request that redirects or returns minimal output. The response has been saved to search-response.json.
</think>
</think>
DONE
[07:22:54] INFO Auto-reply: Assistant message had no tools. Asking for confirmation... complete.py:138
[07:22:54] [Loop control] <system>No tool call detected in last message. Did you mean to finish? If so, make sure you are comp...
User: <system>No tool call detected in last message. Did you mean to finish? If so, make sure you are completely done and then use the `complete` tool to end the session.</system>
Assistant: Thinking...
[07:23:08] INFO Reasoning content: Let me analyze this conversation to create an appropriate title. llm_openai.py:321
The conversation involves:
1. A user requesting to use a shell tool
2. Reading files (search-url.txt and query.txt)
3. Making an API call to a search endpoint
4. The assistant executing a curl command to query a search API
The main topic is about making an API call to a search endpoint with specific parameters.
Possible titles:
- "API search call"
- "Search endpoint query"
- "API integration task"
- "Search API request"
- "Shell API call"
The most concise and accurate title would be "API search call" or "Search API request" - both capture the essence of making a call to a search API endpoint.
Let me go with "API search call" as it's clear and concise.
INFO Auto-generated conversation name: API search call chat.py:332
Assistant:
<think>
<think>
The user asked me to:
1. Read search-url.txt and query.txt from the current workspace
2. Call the search endpoint with query parameters:
- q=<urlencoded query from query.txt>
- format=json
- limit=8
3. Save the raw JSON response exactly as returned to search-response.json in the current workspace
4. Do not transform fields and do not wrap with extra text
5. If successful, reply only DONE.
6. If command execution fails, reply only FAIL.
I did exactly that:
1. I read the contents of search-url.txt and query.txt
2. I made a curl request to the search endpoint with the proper parameters
3. I saved the response to search-response.json
4. I replied only "DONE" as instructed
The task is complete.
</think>
</think>
DONE
[07:23:24] INFO Auto-reply: Assistant message had no tools. Asking for confirmation... complete.py:138
[07:23:24] [Loop control] <system>No tool call detected in last message. Did you mean to finish? If so, make sure you are comp...
User: <system>No tool call detected in last message. Did you mean to finish? If so, make sure you are completely done and then use the `complete` tool to end the session.</system>
Assistant: Thinking...
Assistant:
<think>
<think>
The user asked me to:
1. Read search-url.txt and query.txt from the current workspace
2. Call the search endpoint with query parameters:
- q=<urlencoded query from query.txt>
- format=json
- limit=8
3. Save the raw JSON response exactly as returned to search-response.json in the current workspace
4. Do not transform fields and do not wrap with extra text
5. If successful, reply only DONE.
6. If command execution fails, reply only FAIL.
I did this by running:
curl -s "http://127.0.0.1:35337/search/QjQD2Rux2LGEMJosZ4S6gVtW?q=weekly%20plan%20be9ceb4c4f17%20checkbox&format=json&limit=8" > search-response.json
The command executed successfully (no error output), and the response was saved to search-response.json.
The user then asked me to use the complete tool to end the session.
</think>
</think>
I have completed the task:
1. Read the search URL from `search-url.txt`: `http://127.0.0.1:35337/search/QjQD2Rux2LGEMJosZ4S6gVtW`
2. Read the query from `query.txt`: `weekly plan be9ceb4c4f17 checkbox`
3. Made the API call with parameters:
- `q=weekly%20plan%20be9ceb4c4f17%20checkbox` (URL-encoded query)
- `format=json`
- `limit=8`
4. Saved the raw JSON response to `search-response.json`
The command executed successfully and the response was saved as requested.
@complete(call_ivvkzrei): {}
System: Task complete. Autonomous session finished.
Skipped 1 hidden system messages, show with --show-hidden
[07:23:58] INFO Complete tool call detected, stopping session immediately complete.py:80
INFO Hook 'complete.complete' signaled session completion __init__.py:360
[07:23:58] Autonomous mode: Session completed via complete tool. Exiting.
Goodbye! (resume with: gptme --name gptme__local_aravhawk_qwen3_5_opus_4_6_text_9b__ollama__tool__web_fetch_json_raw-measured)
[gripprobe] process_finished_at=2026-04-26T07:23:58+00:00 exit_code=0
[gripprobe] process_started_at=2026-04-26T07:22:33+00:00 [gripprobe] process_finished_at=2026-04-26T07:23:58+00:00 exit_code=0
# Modelfile generated by "ollama show"
# To build a new Modelfile based on this, replace FROM with:
# FROM aravhawk/qwen3.5-opus-4.6-text:9b
FROM /usr/share/ollama/.ollama/models/blobs/sha256-d0ecd80b0e45b0d9e49c8cd1527b7f7d52d8d3bde2c569ab36aac59bb78f53f7
TEMPLATE {{ .Prompt }}
RENDERER qwen3.5
PARSER qwen3.5
PARAMETER num_ctx 32768
PARAMETER presence_penalty 1.5
PARAMETER stop <|im_end|>
PARAMETER stop <|im_start|>
PARAMETER temperature 1
PARAMETER top_k 20
PARAMETER top_p 0.95