github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 17:49:24 -05:00
Code Issues 14.6k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #5890] Assistant doesn't continue from its last message on 0.2.8 #29436

New Issue
Closed
opened 2026-04-22 08:19:12 -05:00 by GiteaMirror · 8 comments
GiteaMirror commented 2026-04-22 08:19:12 -05:00
Owner
Copy Link

Originally created by @josegtmonteiro on GitHub (Jul 23, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5890

Originally assigned to: @jmorganca on GitHub.

What is the issue?

@jmorganca , thanks for the quick fix on the https://github.com/ollama/ollama/issues/5775

However, testing here with 0.2.8. Still not able to continue the message.

With the same example I mentioned before, using the OLLAMA_DEBUG I'm able to see the final prompt on the console, it is:

prompt="<|start_header_id|>system<|end_header_id|>\n\nYou are a helpful assistant.<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nHello, how are you today?<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\nThanks for asking! I'm <|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n"

The messages I'm passing to the chat endpoint are:
history = [ {"role": "system", "content": 'You are a helpful assistant.'}, {"role": "user", "content": "Hello, how are you today?"}, {"role": "assistant", "content": "Thanks for asking! I'm "}, ]

Not sure it has any difference, but I'm testing with "llama3-groq-tool-use:8b-q8_0" model. Was the fix just made for some specific model? or it should be applied to all of them?

Please let me know if more info/tests needed from my side.

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.2.8

Originally created by @josegtmonteiro on GitHub (Jul 23, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5890 Originally assigned to: @jmorganca on GitHub. ### What is the issue? @jmorganca , thanks for the quick fix on the https://github.com/ollama/ollama/issues/5775 However, testing here with 0.2.8. Still not able to continue the message. With the same example I mentioned before, using the OLLAMA_DEBUG I'm able to see the final prompt on the console, it is: prompt="<|start_header_id|>system<|end_header_id|>\n\nYou are a helpful assistant.<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nHello, how are you today?<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\nThanks for asking! I'm <|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n" The messages I'm passing to the chat endpoint are: history = [ {"role": "system", "content": 'You are a helpful assistant.'}, {"role": "user", "content": "Hello, how are you today?"}, {"role": "assistant", "content": "Thanks for asking! I'm "}, ] Not sure it has any difference, but I'm testing with "llama3-groq-tool-use:8b-q8_0" model. Was the fix just made for some specific model? or it should be applied to all of them? Please let me know if more info/tests needed from my side. ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.2.8
GiteaMirror added the bug label 2026-04-22 08:19:12 -05:00
GiteaMirror commented 2026-04-22 08:19:15 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Jul 23, 2024):

Hi @josegtmonteiro thanks for the issue!

It might be the model, here's an example with llama 3

curl http://localhost:11434/api/chat -d '{
    "model": "llama3",
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "Hello, how are you today?"
      },
      {
        "role": "assistant",
        "content": "Thanks for asking! I am "
      }
    ], "stream": false
  }' | jq .message.content
  % Total    % Received % Xferd  Average Speed   Time    Time     Time  Current
                                 Dload  Upload   Total   Spent    Left  Speed
100   918  100   577  100   341    464    274  0:00:01  0:00:01 --:--:--   739
"100% functioning properly and ready to help with any questions or tasks you may have. It's great to chat with you! Is there something specific on your mind that you'd like to discuss, or do you need assistance with a particular topic or problem? I'm all ears (or in this case, all text)!"

I will double check on the model and update it's template if required

<!-- gh-comment-id:2246319387 --> @jmorganca commented on GitHub (Jul 23, 2024): Hi @josegtmonteiro thanks for the issue! It might be the model, here's an example with llama 3 ``` curl http://localhost:11434/api/chat -d '{ "model": "llama3", "messages": [ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Hello, how are you today?" }, { "role": "assistant", "content": "Thanks for asking! I am " } ], "stream": false }' | jq .message.content % Total % Received % Xferd Average Speed Time Time Time Current Dload Upload Total Spent Left Speed 100 918 100 577 100 341 464 274 0:00:01 0:00:01 --:--:-- 739 "100% functioning properly and ready to help with any questions or tasks you may have. It's great to chat with you! Is there something specific on your mind that you'd like to discuss, or do you need assistance with a particular topic or problem? I'm all ears (or in this case, all text)!" ``` I will double check on the model and update it's template if required
GiteaMirror commented 2026-04-22 08:19:15 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Jul 23, 2024):

May I ask how you're using the API? There is no history field in the API, so it could be the tool you're using to call the Ollama API. Happy to help dig in more

<!-- gh-comment-id:2246322790 --> @jmorganca commented on GitHub (Jul 23, 2024): May I ask how you're using the API? There is no `history` field in the API, so it could be the tool you're using to call the Ollama API. Happy to help dig in more
GiteaMirror commented 2026-04-22 08:19:16 -05:00
Author
Owner
Copy Link

@josegtmonteiro commented on GitHub (Jul 23, 2024):

Sorry for that @jmorganca, I'm calling ollama API from a python function, history was just the name of the varible I'm passing to the function.

Here is a test with curl to make it easier:

0.2.1:
curl http://localhost:11434/api/chat -d "{\"model\":\"llama3-groq-tool-use:8b-q8_0\",\"messages\":[{\"role\":\"system\",\"content\":\"You are a helpful assistant.\"},{\"role\":\"user\",\"content\":\"Hello, how are you today?\"},{\"role\":\"assistant\",\"content\":\"Thanks for asking! I am \"}],\"stream\":false}"

{"model":"llama3-groq-tool-use:8b-q8_0","created_at":"2024-07-23T21:20:51.2802235Z","message":{"role":"assistant","content":"100% here to help with any questions or tasks you have. What do you need assistance with today?"},"done_reason":"stop","done":true,"total_duration":2204791900,"load_duration":15954000,"prompt_eval_count":36,"prompt_eval_duration":549710000,"eval_count":22,"eval_duration":1636985000}

0.2.8:
curl http://localhost:11434/api/chat -d "{\"model\":\"llama3-groq-tool-use:8b-q8_0\",\"messages\":[{\"role\":\"system\",\"content\":\"You are a helpful assistant.\"},{\"role\":\"user\",\"content\":\"Hello, how are you today?\"},{\"role\":\"assistant\",\"content\":\"Thanks for asking! I am \"}],\"stream\":false}"

{"model":"llama3-groq-tool-use:8b-q8_0","created_at":"2024-07-23T21:24:08.1458456Z","message":{"role":"assistant","content":"What can I assist you with today?"},"done_reason":"stop","done":true,"total_duration":17892179100,"load_duration":16749627300,"prompt_eval_count":40,"prompt_eval_duration":459699000,"eval_count":9,"eval_duration":670384000}

<!-- gh-comment-id:2246345213 --> @josegtmonteiro commented on GitHub (Jul 23, 2024): Sorry for that @jmorganca, I'm calling ollama API from a python function, `history` was just the name of the varible I'm passing to the function. Here is a test with curl to make it easier: 0.2.1: `curl http://localhost:11434/api/chat -d "{\"model\":\"llama3-groq-tool-use:8b-q8_0\",\"messages\":[{\"role\":\"system\",\"content\":\"You are a helpful assistant.\"},{\"role\":\"user\",\"content\":\"Hello, how are you today?\"},{\"role\":\"assistant\",\"content\":\"Thanks for asking! I am \"}],\"stream\":false}"` `{"model":"llama3-groq-tool-use:8b-q8_0","created_at":"2024-07-23T21:20:51.2802235Z","message":{"role":"assistant","content":"100% here to help with any questions or tasks you have. What do you need assistance with today?"},"done_reason":"stop","done":true,"total_duration":2204791900,"load_duration":15954000,"prompt_eval_count":36,"prompt_eval_duration":549710000,"eval_count":22,"eval_duration":1636985000}` 0.2.8: `curl http://localhost:11434/api/chat -d "{\"model\":\"llama3-groq-tool-use:8b-q8_0\",\"messages\":[{\"role\":\"system\",\"content\":\"You are a helpful assistant.\"},{\"role\":\"user\",\"content\":\"Hello, how are you today?\"},{\"role\":\"assistant\",\"content\":\"Thanks for asking! I am \"}],\"stream\":false}" ` `{"model":"llama3-groq-tool-use:8b-q8_0","created_at":"2024-07-23T21:24:08.1458456Z","message":{"role":"assistant","content":"What can I assist you with today?"},"done_reason":"stop","done":true,"total_duration":17892179100,"load_duration":16749627300,"prompt_eval_count":40,"prompt_eval_duration":459699000,"eval_count":9,"eval_duration":670384000}`
GiteaMirror commented 2026-04-22 08:19:16 -05:00
Author
Owner
Copy Link

@josegtmonteiro commented on GitHub (Jul 23, 2024):

Another example here with llama3.1:8b-instruct-q8_0, have the same issue.

curl http://localhost:11434/api/chat -d "{\"model\":\"llama3.1:8b-instruct-q8_0\",\"messages\":[{\"role\":\"system\",\"content\":\"You are a helpful assistant.\"},{\"role\":\"user\",\"content\":\"Hello, how are you today?\"},{\"role\":\"assistant\",\"content\":\"Thanks for asking! I am \"}],\"stream\":false}"

{"model":"llama3.1:8b-instruct-q8_0","created_at":"2024-07-23T21:32:34.0023863Z","message":{"role":"assistant","content":"I'm just a language model, so I don't have feelings or emotions like humans do, but I'm functioning properly and ready to help with any questions or tasks you may have. How can I assist you today?"},"done_reason":"stop","done":true,"total_duration":11222101900,"load_duration":6797393300,"prompt_eval_count":50,"prompt_eval_duration":382119000,"eval_count":45,"eval_duration":4038738000}

<!-- gh-comment-id:2246356379 --> @josegtmonteiro commented on GitHub (Jul 23, 2024): Another example here with `llama3.1:8b-instruct-q8_0`, have the same issue. `curl http://localhost:11434/api/chat -d "{\"model\":\"llama3.1:8b-instruct-q8_0\",\"messages\":[{\"role\":\"system\",\"content\":\"You are a helpful assistant.\"},{\"role\":\"user\",\"content\":\"Hello, how are you today?\"},{\"role\":\"assistant\",\"content\":\"Thanks for asking! I am \"}],\"stream\":false}" ` `{"model":"llama3.1:8b-instruct-q8_0","created_at":"2024-07-23T21:32:34.0023863Z","message":{"role":"assistant","content":"I'm just a language model, so I don't have feelings or emotions like humans do, but I'm functioning properly and ready to help with any questions or tasks you may have. How can I assist you today?"},"done_reason":"stop","done":true,"total_duration":11222101900,"load_duration":6797393300,"prompt_eval_count":50,"prompt_eval_duration":382119000,"eval_count":45,"eval_duration":4038738000}`
GiteaMirror commented 2026-04-22 08:19:17 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Jul 23, 2024):

Thanks! @josegtmonteiro. Are you sure you're running Ollama 0.2.8? Would it be possible to run ollama -v

<!-- gh-comment-id:2246431123 --> @jmorganca commented on GitHub (Jul 23, 2024): Thanks! @josegtmonteiro. Are you sure you're running Ollama 0.2.8? Would it be possible to run `ollama -v`
GiteaMirror commented 2026-04-22 08:19:18 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Jul 23, 2024):

Here's what I get from that prompt, for example:

% curl http://localhost:11434/api/chat -d "{\"model\":\"llama3.1:8b-instruct-q8_0\",\"messages\":[{\"role\":\"system\",\"content\":\"You are a helpful assistant.\"},{\"role\":\"user\",\"content\":\"Hello, how are you today?\"},{\"role\":\"assistant\",\"content\":\"Thanks for asking! I am \"}],\"stream\":false}"
{"model":"llama3.1:8b-instruct-q8_0","created_at":"2024-07-23T22:47:08.077302Z","message":{"role":"assistant","content":"100% digital, so I don't have feelings like humans do, but I'm functioning properly and ready to help with any questions or tasks you may have! How about you? How's your day going so far?"},"done_reason":"stop","done":true,"total_duration":2066221042,"load_duration":788808833,"prompt_eval_count":34,"prompt_eval_duration":113163000,"eval_count":45,"eval_duration":1157882000
<!-- gh-comment-id:2246432382 --> @jmorganca commented on GitHub (Jul 23, 2024): Here's what I get from that prompt, for example: ``` % curl http://localhost:11434/api/chat -d "{\"model\":\"llama3.1:8b-instruct-q8_0\",\"messages\":[{\"role\":\"system\",\"content\":\"You are a helpful assistant.\"},{\"role\":\"user\",\"content\":\"Hello, how are you today?\"},{\"role\":\"assistant\",\"content\":\"Thanks for asking! I am \"}],\"stream\":false}" {"model":"llama3.1:8b-instruct-q8_0","created_at":"2024-07-23T22:47:08.077302Z","message":{"role":"assistant","content":"100% digital, so I don't have feelings like humans do, but I'm functioning properly and ready to help with any questions or tasks you may have! How about you? How's your day going so far?"},"done_reason":"stop","done":true,"total_duration":2066221042,"load_duration":788808833,"prompt_eval_count":34,"prompt_eval_duration":113163000,"eval_count":45,"eval_duration":1157882000 ```
GiteaMirror commented 2026-04-22 08:19:18 -05:00
Author
Owner
Copy Link

@josegtmonteiro commented on GitHub (Jul 23, 2024):

@jmorganca , in fact I was on 0.2.8-rc1.

However, look at this:

0.2.8-rc1 test:

curl http://localhost:11434/api/chat -d "{\"model\":\"llama3.1:8b-instruct-q8_0\",\"messages\":[{\"role\":\"system\",\"content\":\"You are a helpful assistant.\"},{\"role\":\"user\",\"content\":\"Hello, how are you today?\"},{\"role\":\"assistant\",\"content\":\"Thanks for asking! I am \"}],\"stream\":false}"

{"model":"llama3.1:8b-instruct-q8_0","created_at":"2024-07-23T23:39:38.9715264Z","message":{"role":"assistant","content":"doing well, thanks for checking in! How about you, is there anything I can help with or would you like to chat?"},"done_reason":"stop","done":true,"total_duration":12370306400,"load_duration":9781381000,"prompt_eval_count":50,"prompt_eval_duration":305007000,"eval_count":27,"eval_duration":2269103000}

ollama -v
ollama version is 0.2.8-rc1

curl http://localhost:11434/api/chat -d "{\"model\":\"llama3-groq-tool-use:8b-q8_0\",\"messages\":[{\"role\":\"system\",\"content\":\"You are a helpful assistant.\"},{\"role\":\"user\",\"content\":\"Hello, how are you today?\"},{\"role\":\"assistant\",\"content\":\"Thanks for asking! I am \"}],\"stream\":false}"

{"model":"llama3-groq-tool-use:8b-q8_0","created_at":"2024-07-23T23:40:27.0570595Z","message":{"role":"assistant","content":"doing well and here to help you with anything you need. How can I assist you today?"},"done_reason":"stop","done":true,"total_duration":9054546600,"load_duration":7113248600,"prompt_eval_count":40,"prompt_eval_duration":270677000,"eval_count":20,"eval_duration":1657589000}

ollama -v
ollama version is 0.2.8-rc1

Updated to 0.2.8

ollama -v
ollama version is 0.2.8

curl http://localhost:11434/api/chat -d "{\"model\":\"llama3.1:8b-instruct-q8_0\",\"messages\":[{\"role\":\"system\",\"content\":\"You are a helpful assistant.\"},{\"role\":\"user\",\"content\":\"Hello, how are you today?\"},{\"role\":\"assistant\",\"content\":\"Thanks for asking! I am \"}],\"stream\":false}"

{"model":"llama3.1:8b-instruct-q8_0","created_at":"2024-07-23T23:42:14.5390654Z","message":{"role":"assistant","content":"I'm functioning properly and ready to assist you with any questions or tasks you may have. How about you? How's your day going so far?"},"done_reason":"stop","done":true,"total_duration":12412734900,"load_duration":9339561300,"prompt_eval_count":50,"prompt_eval_duration":371648000,"eval_count":31,"eval_duration":2694835000}

curl http://localhost:11434/api/chat -d "{\"model\":\"llama3-groq-tool-use:8b-q8_0\",\"messages\":[{\"role\":\"system\",\"content\":\"You are a helpful assistant.\"},{\"role\":\"user\",\"content\":\"Hello, how are you today?\"},{\"role\":\"assistant\",\"content\":\"Thanks for asking! I am \"}],\"stream\":false}"

{"model":"llama3-groq-tool-use:8b-q8_0","created_at":"2024-07-23T23:42:36.5827607Z","message":{"role":"assistant","content":"Great! What can I assist you with today?"},"done_reason":"stop","done":true,"total_duration":8349428700,"load_duration":7211502800,"prompt_eval_count":40,"prompt_eval_duration":267179000,"eval_count":11,"eval_duration":865629000}

So, started to repeat the same request to see if something changes:

curl http://localhost:11434/api/chat -d "{\"model\":\"llama3-groq-tool-use:8b-q8_0\",\"messages\":[{\"role\":\"system\",\"content\":\"You are a helpful assistant.\"},{\"role\":\"user\",\"content\":\"Hello, how are you today?\"},{\"role\":\"assistant\",\"content\":\"Thanks for asking! I am \"}],\"stream\":false}"

{"model":"llama3-groq-tool-use:8b-q8_0","created_at":"2024-07-23T23:47:19.8793515Z","message":{"role":"assistant","content":"I'm here to help with any questions or tasks you have. What's on your mind today?"},"done_reason":"stop","done":true,"total_duration":2478095500,"load_duration":16654200,"prompt_eval_count":40,"prompt_eval_duration":454376000,"eval_count":21,"eval_duration":2005076000}

curl http://localhost:11434/api/chat -d "{\"model\":\"llama3-groq-tool-use:8b-q8_0\",\"messages\":[{\"role\":\"system\",\"content\":\"You are a helpful assistant.\"},{\"role\":\"user\",\"content\":\"Hello, how are you today?\"},{\"role\":\"assistant\",\"content\":\"Thanks for asking! I am \"}],\"stream\":false}"

{"model":"llama3-groq-tool-use:8b-q8_0","created_at":"2024-07-23T23:47:30.7754623Z","message":{"role":"assistant","content":"Doing well, thanks. How can I assist you today?"},"done_reason":"stop","done":true,"total_duration":1656656700,"load_duration":22224900,"prompt_eval_count":40,"prompt_eval_duration":341294000,"eval_count":13,"eval_duration":1290546000}

curl http://localhost:11434/api/chat -d "{\"model\":\"llama3-groq-tool-use:8b-q8_0\",\"messages\":[{\"role\":\"system\",\"content\":\"You are a helpful assistant.\"},{\"role\":\"user\",\"content\":\"Hello, how are you today?\"},{\"role\":\"assistant\",\"content\":\"Thanks for asking! I am \"}],\"stream\":false}"

{"model":"llama3-groq-tool-use:8b-q8_0","created_at":"2024-07-23T23:47:35.2650314Z","message":{"role":"assistant","content":"Do you need any help with something specific today?"},"done_reason":"stop","done":true,"total_duration":1140066400,"load_duration":12952200,"prompt_eval_count":40,"prompt_eval_duration":119064000,"eval_count":11,"eval_duration":1004321000}

curl http://localhost:11434/api/chat -d "{\"model\":\"llama3-groq-tool-use:8b-q8_0\",\"messages\":[{\"role\":\"system\",\"content\":\"You are a helpful assistant.\"},{\"role\":\"user\",\"content\":\"Hello, how are you today?\"},{\"role\":\"assistant\",\"content\":\"Thanks for asking! I am \"}],\"stream\":false}"

{"model":"llama3-groq-tool-use:8b-q8_0","created_at":"2024-07-23T23:47:40.6509125Z","message":{"role":"assistant","content":"doing well and here to help. How can I assist you today?"},"done_reason":"stop","done":true,"total_duration":1574673700,"load_duration":12541900,"prompt_eval_count":40,"prompt_eval_duration":202849000,"eval_count":15,"eval_duration":1356576000}

<!-- gh-comment-id:2246550082 --> @josegtmonteiro commented on GitHub (Jul 23, 2024): @jmorganca , in fact I was on 0.2.8-rc1. However, look at this: **0.2.8-rc1 test:** `curl http://localhost:11434/api/chat -d "{\"model\":\"llama3.1:8b-instruct-q8_0\",\"messages\":[{\"role\":\"system\",\"content\":\"You are a helpful assistant.\"},{\"role\":\"user\",\"content\":\"Hello, how are you today?\"},{\"role\":\"assistant\",\"content\":\"Thanks for asking! I am \"}],\"stream\":false}"` `{"model":"llama3.1:8b-instruct-q8_0","created_at":"2024-07-23T23:39:38.9715264Z","message":{"role":"assistant","content":"doing well, thanks for checking in! How about you, is there anything I can help with or would you like to chat?"},"done_reason":"stop","done":true,"total_duration":12370306400,"load_duration":9781381000,"prompt_eval_count":50,"prompt_eval_duration":305007000,"eval_count":27,"eval_duration":2269103000}` `ollama -v` ollama version is 0.2.8-rc1 `curl http://localhost:11434/api/chat -d "{\"model\":\"llama3-groq-tool-use:8b-q8_0\",\"messages\":[{\"role\":\"system\",\"content\":\"You are a helpful assistant.\"},{\"role\":\"user\",\"content\":\"Hello, how are you today?\"},{\"role\":\"assistant\",\"content\":\"Thanks for asking! I am \"}],\"stream\":false}"` `{"model":"llama3-groq-tool-use:8b-q8_0","created_at":"2024-07-23T23:40:27.0570595Z","message":{"role":"assistant","content":"doing well and here to help you with anything you need. How can I assist you today?"},"done_reason":"stop","done":true,"total_duration":9054546600,"load_duration":7113248600,"prompt_eval_count":40,"prompt_eval_duration":270677000,"eval_count":20,"eval_duration":1657589000}` `ollama -v` ollama version is 0.2.8-rc1 **Updated to 0.2.8** `ollama -v` ollama version is 0.2.8 `curl http://localhost:11434/api/chat -d "{\"model\":\"llama3.1:8b-instruct-q8_0\",\"messages\":[{\"role\":\"system\",\"content\":\"You are a helpful assistant.\"},{\"role\":\"user\",\"content\":\"Hello, how are you today?\"},{\"role\":\"assistant\",\"content\":\"Thanks for asking! I am \"}],\"stream\":false}" ` `{"model":"llama3.1:8b-instruct-q8_0","created_at":"2024-07-23T23:42:14.5390654Z","message":{"role":"assistant","content":"I'm functioning properly and ready to assist you with any questions or tasks you may have. How about you? How's your day going so far?"},"done_reason":"stop","done":true,"total_duration":12412734900,"load_duration":9339561300,"prompt_eval_count":50,"prompt_eval_duration":371648000,"eval_count":31,"eval_duration":2694835000}` _______________________ `curl http://localhost:11434/api/chat -d "{\"model\":\"llama3-groq-tool-use:8b-q8_0\",\"messages\":[{\"role\":\"system\",\"content\":\"You are a helpful assistant.\"},{\"role\":\"user\",\"content\":\"Hello, how are you today?\"},{\"role\":\"assistant\",\"content\":\"Thanks for asking! I am \"}],\"stream\":false}"` `{"model":"llama3-groq-tool-use:8b-q8_0","created_at":"2024-07-23T23:42:36.5827607Z","message":{"role":"assistant","content":"Great! What can I assist you with today?"},"done_reason":"stop","done":true,"total_duration":8349428700,"load_duration":7211502800,"prompt_eval_count":40,"prompt_eval_duration":267179000,"eval_count":11,"eval_duration":865629000}` So, started to repeat the same request to see if something changes: `curl http://localhost:11434/api/chat -d "{\"model\":\"llama3-groq-tool-use:8b-q8_0\",\"messages\":[{\"role\":\"system\",\"content\":\"You are a helpful assistant.\"},{\"role\":\"user\",\"content\":\"Hello, how are you today?\"},{\"role\":\"assistant\",\"content\":\"Thanks for asking! I am \"}],\"stream\":false}"` ` {"model":"llama3-groq-tool-use:8b-q8_0","created_at":"2024-07-23T23:47:19.8793515Z","message":{"role":"assistant","content":"I'm here to help with any questions or tasks you have. What's on your mind today?"},"done_reason":"stop","done":true,"total_duration":2478095500,"load_duration":16654200,"prompt_eval_count":40,"prompt_eval_duration":454376000,"eval_count":21,"eval_duration":2005076000}` _______________________ `curl http://localhost:11434/api/chat -d "{\"model\":\"llama3-groq-tool-use:8b-q8_0\",\"messages\":[{\"role\":\"system\",\"content\":\"You are a helpful assistant.\"},{\"role\":\"user\",\"content\":\"Hello, how are you today?\"},{\"role\":\"assistant\",\"content\":\"Thanks for asking! I am \"}],\"stream\":false}"` `{"model":"llama3-groq-tool-use:8b-q8_0","created_at":"2024-07-23T23:47:30.7754623Z","message":{"role":"assistant","content":"Doing well, thanks. How can I assist you today?"},"done_reason":"stop","done":true,"total_duration":1656656700,"load_duration":22224900,"prompt_eval_count":40,"prompt_eval_duration":341294000,"eval_count":13,"eval_duration":1290546000}` _______________________ `curl http://localhost:11434/api/chat -d "{\"model\":\"llama3-groq-tool-use:8b-q8_0\",\"messages\":[{\"role\":\"system\",\"content\":\"You are a helpful assistant.\"},{\"role\":\"user\",\"content\":\"Hello, how are you today?\"},{\"role\":\"assistant\",\"content\":\"Thanks for asking! I am \"}],\"stream\":false}"` `{"model":"llama3-groq-tool-use:8b-q8_0","created_at":"2024-07-23T23:47:35.2650314Z","message":{"role":"assistant","content":"Do you need any help with something specific today?"},"done_reason":"stop","done":true,"total_duration":1140066400,"load_duration":12952200,"prompt_eval_count":40,"prompt_eval_duration":119064000,"eval_count":11,"eval_duration":1004321000}` _______________________ `curl http://localhost:11434/api/chat -d "{\"model\":\"llama3-groq-tool-use:8b-q8_0\",\"messages\":[{\"role\":\"system\",\"content\":\"You are a helpful assistant.\"},{\"role\":\"user\",\"content\":\"Hello, how are you today?\"},{\"role\":\"assistant\",\"content\":\"Thanks for asking! I am \"}],\"stream\":false}"` `{"model":"llama3-groq-tool-use:8b-q8_0","created_at":"2024-07-23T23:47:40.6509125Z","message":{"role":"assistant","content":"doing well and here to help. How can I assist you today?"},"done_reason":"stop","done":true,"total_duration":1574673700,"load_duration":12541900,"prompt_eval_count":40,"prompt_eval_duration":202849000,"eval_count":15,"eval_duration":1356576000}`
GiteaMirror commented 2026-04-22 08:19:20 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Jul 25, 2024):

Hi there, the templates for llama3.1 and llama3-groq-tool-use have been fixed. Sorry this happened!

To repull them:

ollama pull llama3.1
ollama pull llama3-groq-tool-use

And this should work. Thanks for the issue!

<!-- gh-comment-id:2249171264 --> @jmorganca commented on GitHub (Jul 25, 2024): Hi there, the templates for `llama3.1` and `llama3-groq-tool-use` have been fixed. Sorry this happened! To repull them: ``` ollama pull llama3.1 ollama pull llama3-groq-tool-use ``` And this should work. Thanks for the issue!
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#29436
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?