Skip to content

feat(together-ai/LiquidAI/LFM2.5-8B-A1B): add new models [bot]#1733

Open
models-bot[bot] wants to merge 2 commits into
mainfrom
bot/add-together-ai-LiquidAI-LFM2.5-8B-A1B-20260710-001007
Open

feat(together-ai/LiquidAI/LFM2.5-8B-A1B): add new models [bot]#1733
models-bot[bot] wants to merge 2 commits into
mainfrom
bot/add-together-ai-LiquidAI-LFM2.5-8B-A1B-20260710-001007

Conversation

@models-bot

@models-bot models-bot Bot commented Jul 10, 2026

Copy link
Copy Markdown
Contributor

Auto-generated by model-addition-agent for together-ai/LiquidAI/LFM2.5-8B-A1B.


Note

Low Risk
Single new YAML model entry with no changes to application logic or security-sensitive paths.

Overview
Adds a new Together AI provider definition for LiquidAI/LFM2.5-8B-A1B, registering it as an active, serverless chat model with 32k context, text in/out, per-token pricing, and thinking: true.

This is catalog/metadata only (no runtime or routing logic changes).

Reviewed by Cursor Bugbot for commit 473891d. Bugbot is set up for automated code reviews on this repo. Configure here.

Comment thread providers/together-ai/LiquidAI/LFM2.5-8B-A1B.yaml
@github-actions

Copy link
Copy Markdown
Contributor

/test-models

@harshiv-26

Copy link
Copy Markdown
Collaborator

Gateway test results

  • Total: 4
  • Passed: 2
  • Failed: 0
  • Validation failed: 2
  • Errored: 0
  • Skipped: 0
  • Success rate: 50.0%
Provider Model Scenarios
together-ai LiquidAI/LFM2.5-8B-A1B success: params, params:stream

validation_failure: reasoning, reasoning:stream
Failures (2)

together-ai/LiquidAI/LFM2.5-8B-A1B — reasoning (validation_failure)

Error
Traceback (most recent call last):
  File "/tmp/tmp2qo2jjnx/snippet.py", line 39, in <module>
    raise Exception("VALIDATION FAILED: reasoning - no reasoning information in response")
Exception: VALIDATION FAILED: reasoning - no reasoning information in response
Code snippet
from openai import OpenAI

client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")

response = client.chat.completions.create(
    model="test-v2-together-ai/LiquidAI-LFM2.5-8B-A1B",
    messages=[
        {"role": "user", "content": "How to calculate 3^3^3^3? Think step by step and show all reasoning."},
    ],
    reasoning_effort="medium",
    stream=False,
)
_usage = getattr(response, "usage", None)
_reasoning_detected = False

_choices = getattr(response, "choices", None)
if _choices and len(_choices) > 0:
    _message = getattr(_choices[0], "message", None)
else:
    _message = None

if _message and getattr(_message, "content", None) is not None:
    print(_message.content)

if _usage is not None:
    _output_token_details = getattr(_usage, "completion_tokens_details", None)
    if _output_token_details and getattr(_output_token_details, "reasoning_tokens", 0) > 0:
        _reasoning_detected = True
    elif getattr(_usage, "reasoning", None) is not None:
        _reasoning_detected = True

if getattr(_message, "reasoning_content", None) is not None:
    _reasoning_detected = True
elif getattr(_message, "reasoning", None) is not None:
    _reasoning_detected = True

if not _reasoning_detected:
    print("Response: ", response)
    raise Exception("VALIDATION FAILED: reasoning - no reasoning information in response")
print("VALIDATION: reasoning SUCCESS")
Output
<think>
The user asks: "How to calculate 3^3^3^3? Think step by step and show all reasoning."

We need to interpret the expression. Usually exponentiation is right-associative, meaning a^b^c = a^(b^c). So 3^3^3^3 = 3^(3^(3^3)). Compute innermost exponent first: 3^3 = 27. Then next level: 3^(27) = huge number. Then outermost: 3 raised to that huge number.

Thus we can't compute exact decimal value because it's astronomically large (approx 10^(1.44e12) maybe?). Actually let's estimate: log10(3^(3^(27))) = (3^(27)) * log10(3). 3^27 = 7,625,597,484,987? Let's compute: 3^10 = 59049; 3^20 = (3^10)^2 = 59049^2 ≈ 3.486e9; 3^27 = 3^20 * 3^7 = 3,486,784,401 * 2187 = approx 7.625e12. Indeed 3^27 = 7,625,597,484,987. So exponent = about 7.6 trillion. Multiply by log10(3) ≈ 0.47712125472 => total log10 ≈ 3.64e12. So number of digits ~ 10^{3.64e12} which is insane.

Thus answer: It cannot be expressed in conventional notation; we can express as 3^(3^(27)). Or using Knuth's up-arrow notation: 3↑↑4 = 3^(3^(3^3)). That's a tetration of height 4. So final answer: \boxed{3^{3^{27}}} or more explicitly as a power tower: 3^{(3^{(3^{3})})}.

But they ask "How to calculate ... think step by step and show all reasoning". So we should explain associativity, evaluate from top down, etc., and then present the result in exponential form. Also note that direct computation is impossible due to size.

We could also discuss approximations, scientific notation, but not needed. Provide steps:

1. Recognize exponentiation is right-associative.
2. Write expression as 3^(3^(3^3)).
3. Compute innermost exponent: 3^3 = 27.
4. Next exponent: 3^(27) = huge number.
5. Outermost exponent: 3^(that huge number) = final result.

Thus final answer: \boxed{3^{3^{27}}}.

Alternatively, if they want numeric approximation: Use logs: log10(N) = (3^27)*log10(3) ≈ 3.64×10^{12}. So N ≈ 10^{3.64×10^{12}}.

We can also mention that this is a power tower of four 3's, known as 3↑↑4 in Knuth's up-arrow notation.

Thus answer will include reasoning and final boxed expression.

Make sure to be clear, step-by-step, no extraneous content. Provide explanation of why we don't compute fully.

Potential pitfalls: Some might misinterpret as (3^3)^(3^3) = 27^27, but that's wrong because exponentiation is right-associative. So we must clarify.

Thus final answer: \boxed{3^{3^{27}}}.

We can also write as 3^{(3^{(3^{3})})}.

Thus answer.

Now produce final output.
</think>

**Step‑by‑step evaluation**

1. **Understand the order of operations for exponentiation**  
   Exponentiation is *right‑associative*. This means that when several exponents are written together without parentheses, we evaluate them from the top down:
   \[
   a^{b^{c}} = a^{\,b^{\,c}}
   \]
   In other words, \(a^{b^{c}}\) is **not** \((a^{b})^{c}\); it is \(a^{(b^{c})}\).

2. **Apply this rule to the given tower**  
   The original expression is \(3^{3^{3^{3}}}\). Following the right‑associative rule,
   \[
   3^{3^{3^{3}}} \;=\; 3^{\,3^{\,3^{3}}}.
   \]

3. **Compute the innermost exponent first**  
   \[
   3^{3}=27.
   \]

4. **Move one level outward**  
   Replace the innermost part with its value:
   \[
   3^{\,3^{\,27}}.
   \]

5. **Recognize the resulting structure**  
   The expression now has three levels of exponentiation:
   \[
   3^{\,3^{\,27}} = 3^{\bigl(3^{27}\bigr)}.
   \]
   This is a *power tower* of four 3’s:
   \[
   \underbrace{3^{3^{3^{3}}}}_{\text{four 3’s}}.
   \]

6. **Why we stop here**  
   Evaluating \(3^{27}\) gives a concrete integer (≈ 7.6 × 10¹²), but raising 3 to that enormous power produces a number whose decimal representation would have on the order of \(10^{3.6\times10^{12}}\) digits—far beyond any practical representation. Hence the exact decimal expansion cannot be written out; we keep it in exponential form.

---

\[
\boxed{\,3^{\,3^{\,27}}\;}
\]

(Equivalently, in Knuth’s up‑arrow notation: \(3\uparrow\uparrow 4\).) This is the mathematically correct way to express the value of \(3^{3^{3^{3}}}\).
Response:  ChatCompletion(id='orVeEDB-6Ng1vN-a18ba773b93c17e5', choices=[Choice(finish_reason='stop', index=0, logprobs=None, message=ChatCompletionMessage(content='<think>\nThe user asks: "How to calculate 3^3^3^3? Think step by step and show all reasoning."\n\nWe need to interpret the expression. Usually exponentiation is right-associative, meaning a^b^c = a^(b^c). So 3^3^3^3 = 3^(3^(3^3)). Compute innermost exponent first: 3^3 = 27. Then next level: 3^(27) = huge number. Then outermost: 3 raised to that huge number.\n\nThus we can\'t compute exact decimal value because it\'s astronomically large (approx 10^(1.44e12) maybe?). Actually let\'s estimate: log10(3^(3^(27))) = (3^(27)) * log10(3). 3^27 = 7,625,597,484,987? Let\'s compute: 3^10 = 59049; 3^20 = (3^10)^2 = 59049^2 ≈ 3.486e9; 3^27 = 3^20 * 3^7 = 3,486,784,401 * 2187 = approx 7.625e12. Indeed 3^27 = 7,625,597,484,987. So exponent = about 7.6 trillion. Multiply by log10(3) ≈ 0.47712125472 => total log10 ≈ 3.64e12. So number of digits ~ 10^{3.64e12} which is insane.\n\nThus answer: It cannot be expressed in conventional notation; we can express as 3^(3^(27)). Or using Knuth\'s up-arrow notation: 3↑↑4 = 3^(3^(3^3)). That\'s a tetration of height 4. So final answer: \\boxed{3^{3^{27}}} or more explicitly as a power tower: 3^{(3^{(3^{3})})}.\n\nBut they ask "How to calculate ... think step by step and show all reasoning". So we should explain associativity, evaluate from top down, etc., and then present the result in exponential form. Also note that direct computation is impossible due to size.\n\nWe could also discuss approximations, scientific notation, but not needed. Provide steps:\n\n1. Recognize exponentiation is right-associative.\n2. Write expression as 3^(3^(3^3)).\n3. Compute innermost exponent: 3^3 = 27.\n4. Next exponent: 3^(27) = huge number.\n5. Outermost exponent: 3^(that huge number) = final result.\n\nThus final answer: \\boxed{3^{3^{27}}}.\n\nAlternatively, if they want numeric approximation: Use logs: log10(N) = (3^27)*log10(3) ≈ 3.64×10^{12}. So N ≈ 10^{3.64×10^{12}}.\n\nWe can also mention that this is a power tower of four 3\'s, known as 3↑↑4 in Knuth\'s up-arrow notation.\n\nThus answer will include reasoning and final boxed expression.\n\nMake sure to be clear, step-by-step, no extraneous content. Provide explanation of why we don\'t compute fully.\n\nPotential pitfalls: Some might misinterpret as (3^3)^(3^3) = 27^27, but that\'s wrong because exponentiation is right-associative. So we must clarify.\n\nThus final answer: \\boxed{3^{3^{27}}}.\n\nWe can also write as 3^{(3^{(3^{3})})}.\n\nThus answer.\n\nNow produce final output.\n</think>\n\n**Step‑by‑step evaluation**\n\n1. **Understand the order of operations for exponentiation**  \n   Exponentiation is *right‑associative*. This means that when several exponents are written together without parentheses, we evaluate them from the top down:\n   \\[\n   a^{b^{c}} = a^{\\,b^{\\,c}}\n   \\]\n   In other words, \\(a^{b^{c}}\\) is **not** \\((a^{b})^{c}\\); it is \\(a^{(b^{c})}\\).\n\n2. **Apply this rule to the given tower**  \n   The original expression is \\(3^{3^{3^{3}}}\\). Following the right‑associative rule,\n   \\[\n   3^{3^{3^{3}}} \\;=\\; 3^{\\,3^{\\,3^{3}}}.\n   \\]\n\n3. **Compute the innermost exponent first**  \n   \\[\n   3^{3}=27.\n   \\]\n\n4. **Move one level outward**  \n   Replace the innermost part with its value:\n   \\[\n   3^{\\,3^{\\,27}}.\n   \\]\n\n5. **Recognize the resulting structure**  \n   The expression now has three levels of exponentiation:\n   \\[\n   3^{\\,3^{\\,27}} = 3^{\\bigl(3^{27}\\bigr)}.\n   \\]\n   This is a *power tower* of four 3’s:\n   \\[\n   \\underbrace{3^{3^{3^{3}}}}_{\\text{four 3’s}}.\n   \\]\n\n6. **Why we stop here**  \n   Evaluating \\(3^{27}\\) gives a concrete integer (≈\u202f7.6\u202f×\u202f10¹²), but raising 3 to that enormous power produces a number whose decimal representation would have on the order of \\(10^{3.6\\times10^{12}}\\) digits—far beyond any practical representation. Hence the exact decimal expansion cannot be written out; we keep it in exponential form.\n\n---\n\n\\[\n\\boxed{\\,3^{\\,3^{\\,27}}\\;}\n\\]\n\n(Equivalently, in Knuth’s up‑arrow notation: \\(3\\uparrow\\uparrow 4\\).) This is the mathematically correct way to express the value of \\(3^{3^{3^{3}}}\\).', refusal=None, role='assistant', annotations=None, audio=None, function_call=None, tool_calls=[]))], created=1783645463, model='LiquidAI/LFM2.5-8B-A1B', object='chat.completion', service_tier=None, system_fingerprint=None, usage=CompletionUsage(completion_tokens=1232, prompt_tokens=30, total_tokens=1262, completion_tokens_details=None, prompt_tokens_details=None), provider='together-ai')

together-ai/LiquidAI/LFM2.5-8B-A1B — reasoning:stream (validation_failure)

Error
Traceback (most recent call last):
  File "/tmp/tmpn0facznt/snippet.py", line 31, in <module>
    raise Exception("VALIDATION FAILED: reasoning stream - no reasoning information in stream")
Exception: VALIDATION FAILED: reasoning stream - no reasoning information in stream
Code snippet
from openai import OpenAI

client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")

response = client.chat.completions.create(
    model="test-v2-together-ai/LiquidAI-LFM2.5-8B-A1B",
    messages=[
        {"role": "user", "content": "How to calculate 3^3^3^3? Think step by step and show all reasoning."},
    ],
    reasoning_effort="medium",
    stream=True,
)
_reasoning_detected = False
for chunk in response:
    if chunk.choices and len(chunk.choices) > 0:
        delta = chunk.choices[0].delta
        if delta.content is not None:
            print(delta.content, end="", flush=True)
        if getattr(delta, "reasoning_content", None) is not None:
            _reasoning_detected = True
        if getattr(delta, "reasoning", None) is not None:
            _reasoning_detected = True

    _usage = getattr(chunk, "usage", None)
    if _usage is not None:
        _details = getattr(_usage, "completion_tokens_details", None)
        if _details and getattr(_details, "reasoning_tokens", 0) > 0:
            _reasoning_detected = True

if not _reasoning_detected:
    raise Exception("VALIDATION FAILED: reasoning stream - no reasoning information in stream")
print("\nVALIDATION: reasoning stream SUCCESS")
Output
<think>
The user asks: "How to calculate 3^3^3^3? Think step by step and show all reasoning."

We need to interpret exponentiation associativity. Usually, exponentiation is right-associative, meaning a^b^c = a^(b^c). So 3^3^3^3 = 3^(3^(3^3)). Compute inner exponent first: 3^3 = 27. Then next: 3^(27) = huge number. Then final: 3 raised to that huge number.

But we cannot compute the exact decimal value because it's astronomically large (about 10^(1.5*10^12)? Actually let's approximate: log10(3^(3^(27))) = (3^(27)) * log10(3). 3^(27) is about e^(27 ln 3) ≈ e^(27 * 1.0986) = e^(29.6622) ≈ 7.0e12? Wait compute: e^29.66 ~ 1.9e12? Let's compute more precisely: Ln(3) ≈ 1.098612289. Multiply by 27 gives 29.6625. Exponential of that is approx e^29.6625 = 1.8e12? Actually e^10 ≈ 22026, e^20 ≈ 4.85e8, e^30 ≈ 1.068e13. So e^29.66 is slightly less than e^30, maybe around 9.8e12? Let's compute more accurately: Using approximation: e^29.6625 = exp(29.6625). We can compute using known values: log10(e) ≈ 0.4343. So log10(3^(27)) = 27 * log10(3) ≈ 27 * 0.47712125472 = 12.882... So 3^27 ≈ 10^12.882 ≈ 7.62 × 10^12. Indeed 10^0.882 ≈ 7.62. So 3^27 ≈ 7.6 × 10^12.

Thus 3^(3^27) = 3^(~7.6×10^12). That's enormous. Taking log10 again: log10(3^(7.6×10^12)) = (7.6×10^12) * log10(3) ≈ (7.6×10^12) * 0.4771 ≈ 3.63×10^12. So the number has about 3.6 trillion digits. That's insane.

Then final exponent: 3^(that huge number). Its logarithm base 10 would be (the previous number) * log10(3). So the final number has an astronomical number of digits itself. It's impossible to write out fully. So answer should explain steps, define right-associativity, compute innermost exponent, then successive exponentiations, discuss magnitude, perhaps express in terms of tetration notation: 3↑↑4 = 3^3^3^3 (tetration). Provide reasoning and note that direct computation is infeasible; we can only describe its size.

Thus we need to produce a step-by-step solution with reasoning, showing how to handle exponentiation order, compute intermediate results, and discuss magnitude. Also mention that if one wanted to compute modulo something, you could use modular arithmetic, but not asked.

Thus answer: Step 1: Recognize right-associativity. Step 2: Compute 3^3 = 27. Step 3: Compute 3^(27) = huge, call it A. Step 4: Compute 3^A = even larger, call it B. Provide approximations for number of digits. Possibly give scientific notation: B ≈ 10^(3.6×10^12). Then final result is 10^(10^(3.6×10^12))? Wait careful: B = 3^A, where A ≈ 7.6×10^12. So B ≈ 10^(log10(3)*A) ≈ 10^(0.4771 * 7.6×10^12) ≈ 10^(3.63×10^12). So B has about 3.6×10^12 digits. Then final exponent C = 3^B, so log10(C) = B * log10(3) ≈ 0.4771 * B ≈ 0.4771 * 10^(3.63×10^12). That's unbelievably huge. So we can say C has about 10^(3.63×10^12) digits. So it's a power tower of height 4.

Thus answer will include these steps, concluding that the exact numeric value cannot be written down, but we can describe its magnitude.

We also might discuss alternative interpretations: left-associative evaluation yields ((((3^3)^3)^3) = (3^3)^3 = 27^3 = 19683, then ^3 again etc. But typical convention is right-associative. So we should clarify that.

Thus final answer: Provide step-by-step reasoning, culminating in expression like:

3^3^3^3 = 3^{(3^{(3^3)})} = 3^{(3^{27})} = 3^{7.625597484987e12} ≈ 10^{3.63×10^{12}}.

Then final answer: \boxed{3^{3^{3^{3}}} = 3^{(3^{27})} \approx 10^{\,3.6\times10^{12}}}.

But we need to show all reasoning. So we can break down each step, compute logs, etc.

We should also mention that exponentiation is not associative, so parentheses matter. And we can talk about tetration notation: 3↑↑4.

Thus answer will be thorough.

Potential pitfalls: The user may want the actual number? No, it's too large. So we must explain why we cannot compute exactly.

Thus final answer: Provide step-by-step reasoning, including definitions, calculations, approximations, and conclusion.

Now produce final answer.
</think>

**Step 1 – Understand the notation**

Exponentiation is **right‑associative**, which means that when several exponents appear together they are evaluated from the top down:

\[
a^{b^{c^{d}}}=a^{\,b^{\,c^{\,d}}}\; .
\]

So for  

\[
3^{3^{3^{3}}}
\]

the evaluation order is  

\[
3^{\,3^{\,3^{\,3}}}.
\]

---

**Step 2 – Evaluate the innermost power**

\[
3^{3}=27 .
\]

Now the expression reduces to  

\[
3^{\,3^{\,27}} .
\]

---

**Step 3 – Compute the next level (still manageable)**  

\[
3^{27}=e^{27\ln 3}\approx e^{27\cdot1.098612289}
      \approx e^{29.6625}\approx 7.6\times10^{12}.
\]

Thus  

\[
3^{\,3^{\,27}}\;=\;3^{\,7.6\times10^{12}}.
\]

To see how many decimal digits this number has, take common logarithms:

\[
\log_{10}\!\bigl(3^{\,7.6\times10^{12}}\bigr)
   = (7.6\times10^{12})\,\log_{10}3
   \approx (7.6\times10^{12})\times0.4771
   \approx 3.6\times10^{12}.
\]

Hence  

\[
3^{\,3^{\,27}}\;\text{has roughly }3.6\times10^{12}\text{ digits.}
\]

For brevity we denote this huge integer by \(A\):

\[
A = 3^{\,3^{\,27}}\quad\text{(≈ }7.6\times10^{12}\text{ digits)}.
\]

---

**Step 4 – The outermost exponentiation**

Now we have to compute  

\[
3^{A}=3^{\,3^{\,3^{\,27}}}.
\]

Again we only need its logarithm to gauge its size:

\[
\log_{10}\!\bigl(3^{A}\bigr)=A\,\log_{10}3
   \approx (7.6\times10^{12})\times0.4771
   \approx 3.6\times10^{12}.
\]

That tells us that \(\log_{10}(3^{A})\) is on the order of \(10^{12}\).  
In other words, the final number has **an astronomically large number of digits**:

\[
3^{3^{3^{3}}}\;\approx\;10^{\,3.6\times10^{12}}.
\]

If we wanted to be even more explicit, we could write

\[
3^{3^{3^{3}}}=10^{\,0.4771\;\cdot\;3^{\,3^{\,27}}}
           =10^{\,0.4771\;\cdot\;A},
\]

which shows that the exponent itself is the gigantic integer \(A\).

---

### Final Result

Putting everything together, the exact value cannot be written out in full, but its size can be described succinctly as a power‑tower:

\[
\boxed{\,3^{3^{3^{3}}}=3^{\,3^{\,3^{\,3}}}
      =3^{\,7.6\times10^{12}}
      \approx 10^{\,3.6\times10^{12}}\,}.
\]

Equivalently, using tetration notation (\(3\uparrow\uparrow4\)):

\[
3^{3^{3^{3}}}=3\uparrow\uparrow4\;\approx\;10^{\,10^{\,3.
Successes (2)

together-ai/LiquidAI/LFM2.5-8B-A1B — params (success)

Output
<think>
The user asks: "What is the capital of France?" The answer: Paris. There's no disallowed content. Provide answer.
</think>
The capital of Fran
... (truncated, 17 chars omitted)

together-ai/LiquidAI/LFM2.5-8B-A1B — params:stream (success)

Output
<think>
The user asks: "What is the capital of France?" Straightforward factual question. Answer: Paris.

We must follow instructions: no extra format
... (truncated, 392 chars omitted)

@cursor cursor Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Cursor Bugbot has reviewed your changes using default effort and found 3 potential issues.

Fix All in Cursor

❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.

Reviewed by Cursor Bugbot for commit 473891d. Configure here.

output_cost_per_token: 1.2e-7
region: "*"
limits:
context_window: 32768

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Wrong context window limit

Medium Severity

limits.context_window is set to 32768, but the model’s cited Liquid AI release describes a 128K context window. Downstream consumers of this registry may cap or validate prompts at 32K tokens and block or truncate valid long-context use.

Fix in Cursor Fix in Web

Reviewed by Cursor Bugbot for commit 473891d. Configure here.

- https://www.liquid.ai/blog/lfm2-5-8b-a1b
status: active
supportedModes:
- chat

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Missing tool calling features

Medium Severity

The config has no features block, so capabilities like function_calling and tool_choice are not declared. LFM2.5-8B-A1B is positioned for tool calling, and the provider’s other Liquid entry lists those features explicitly.

Fix in Cursor Fix in Web

Reviewed by Cursor Bugbot for commit 473891d. Configure here.

status: active
supportedModes:
- chat
thinking: true

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Incorrect thinking flag set

Low Severity

thinking: true marks extended reasoning support, but LFM2.5 is documented for tool calling rather than step-by-step reasoning, and the other Liquid model on Together omits this flag.

Fix in Cursor Fix in Web

Reviewed by Cursor Bugbot for commit 473891d. Configure here.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant