mistralai

/

Mamba-Codestral-7B-v0.1

like 562

Follow

Mistral AI_ 3.73k

!mistral-chat /root/mistral_models/Mamba-Codestral-7B-v0.1 --instruct --max_tokens 256

7]
1m
12
!mistral-chat /root/mistral_models/Mamba-Codestral-7B-v0.1 --instruct --max_tokens 256

/usr/local/lib/python3.10/dist-packages/mamba_ssm/ops/selective_scan_interface.py:164: FutureWarning: torch.cuda.amp.custom_fwd(args...) is deprecated. Please use torch.amp.custom_fwd(args..., device_type='cuda') instead.
def forward(ctx, xz, conv1d_weight, conv1d_bias, x_proj_weight, delta_proj_weight,
/usr/local/lib/python3.10/dist-packages/mamba_ssm/ops/selective_scan_interface.py:240: FutureWarning: torch.cuda.amp.custom_bwd(args...) is deprecated. Please use torch.amp.custom_bwd(args..., device_type='cuda') instead.
def backward(ctx, dout):
/usr/local/lib/python3.10/dist-packages/mamba_ssm/ops/triton/layer_norm.py:986: FutureWarning: torch.cuda.amp.custom_fwd(args...) is deprecated. Please use torch.amp.custom_fwd(args..., device_type='cuda') instead.
def forward(
/usr/local/lib/python3.10/dist-packages/mamba_ssm/ops/triton/layer_norm.py:1045: FutureWarning: torch.cuda.amp.custom_bwd(args...) is deprecated. Please use torch.amp.custom_bwd(args..., device_type='cuda') instead.
def backward(ctx, dout, *args):
/usr/local/lib/python3.10/dist-packages/mamba_ssm/distributed/tensor_parallel.py:26: FutureWarning: torch.cuda.amp.custom_fwd(args...) is deprecated. Please use torch.amp.custom_fwd(args..., device_type='cuda') instead.
def forward(ctx, x, weight, bias, process_group=None, sequence_parallel=True):
/usr/local/lib/python3.10/dist-packages/mamba_ssm/distributed/tensor_parallel.py:62: FutureWarning: torch.cuda.amp.custom_bwd(args...) is deprecated. Please use torch.amp.custom_bwd(args..., device_type='cuda') instead.
def backward(ctx, grad_output):
/usr/local/lib/python3.10/dist-packages/mamba_ssm/ops/triton/ssd_combined.py:758: FutureWarning: torch.cuda.amp.custom_fwd(args...) is deprecated. Please use torch.amp.custom_fwd(args..., device_type='cuda') instead.
def forward(ctx, zxbcdt, conv1d_weight, conv1d_bias, dt_bias, A, D, chunk_size, initial_states=None, seq_idx=None, dt_limit=(0.0, float("inf")), return_final_states=False, activation="silu",
/usr/local/lib/python3.10/dist-packages/mamba_ssm/ops/triton/ssd_combined.py:836: FutureWarning: torch.cuda.amp.custom_bwd(args...) is deprecated. Please use torch.amp.custom_bwd(args..., device_type='cuda') instead.
def backward(ctx, dout, *args):
Prompt: how are you?
Traceback (most recent call last):
File "/usr/local/bin/mistral-chat", line 8, in
sys.exit(mistral_chat())
File "/usr/local/lib/python3.10/dist-packages/mistral_inference/main.py", line 259, in mistral_chat
fire.Fire(interactive)
File "/usr/local/lib/python3.10/dist-packages/fire/core.py", line 135, in Fire
component_trace = _Fire(component, args, parsed_flag_args, context, name)
File "/usr/local/lib/python3.10/dist-packages/fire/core.py", line 468, in _Fire
component, remaining_args = _CallAndUpdateTrace(
File "/usr/local/lib/python3.10/dist-packages/fire/core.py", line 684, in _CallAndUpdateTrace
component = fn(*varargs, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/mistral_inference/main.py", line 172, in interactive
generated_tokens, _ = generate_fn( # type: ignore[operator]
File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
TypeError: generate_mamba() takes 2 positional arguments but 3 positional arguments (and 3 keyword-only arguments) were given