Magnum v4 72B

anthracite-org/magnum-v4-72b

Modalities: text->text
In / out price: $2.5 / $5
Context: 33K
Released: Oct 22, 2024
Knowledge cutoff: 2024-06-30

This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus).

The model is fine-tuned on top of Qwen2.5 72B.

Structured output

Supported parameters

frequency_penalty
Frequency penalty
Lowers the chance of a token in proportion to how often it already appeared.
logit_bias
Logit bias
Add or subtract from token ids to encourage or ban them.
logprobs
Logprobs
Return the log probability of each output token.
max_tokens
Max tokens
Upper bound on generated tokens. Output stops at the limit.
min_p
Min-p
Drops tokens below this probability threshold.
presence_penalty
Presence penalty
Lowers the chance of any token that has already appeared.
repetition_penalty
Repetition penalty
Penalizes text that already appeared. Common on open models.
response_format
Response format
For example json_object or json_schema, to constrain the shape.
seed
Seed
A fixed seed helps reproduce sampling. It does not guarantee byte-identical output.
stop
Stop
Stop when these strings are produced. A string or an array of strings.
structured_outputs
Structured outputs
Generate a parseable structure that follows a JSON Schema.
temperature
Temperature
Sampling temperature. Lower is steadier, higher is more varied. Often 0 to 2.
top_a
Top-A
Narrows the candidate tokens dynamically by relative probability.
top_k
Top-K
Sample only from the K most likely tokens.
top_logprobs
Top logprobs
Also return the most likely alternatives at each position.
top_p
Top-p
Sample only from tokens whose cumulative probability reaches top_p.

Supported parameters

frequency_penalty

Frequency penalty

Lowers the chance of a token in proportion to how often it already appeared.

logit_bias

Logit bias

Add or subtract from token ids to encourage or ban them.

logprobs

Logprobs

Return the log probability of each output token.

max_tokens

Max tokens

Upper bound on generated tokens. Output stops at the limit.

min_p

Min-p

Drops tokens below this probability threshold.

presence_penalty

Presence penalty

Lowers the chance of any token that has already appeared.

repetition_penalty

Repetition penalty

Penalizes text that already appeared. Common on open models.

response_format

Response format

For example json_object or json_schema, to constrain the shape.

seed

Seed

A fixed seed helps reproduce sampling. It does not guarantee byte-identical output.

stop

Stop

Stop when these strings are produced. A string or an array of strings.

structured_outputs

Structured outputs

Generate a parseable structure that follows a JSON Schema.

temperature

Temperature

Sampling temperature. Lower is steadier, higher is more varied. Often 0 to 2.

top_a

Top-A

Narrows the candidate tokens dynamically by relative probability.

top_k

Top-K

Sample only from the K most likely tokens.

top_logprobs

Top logprobs

Also return the most likely alternatives at each position.

top_p

Top-p

Sample only from tokens whose cumulative probability reaches top_p.