Resources

View closed (5)

Update - Tool Calling + Chat Template bug fixes

pinned

#20 opened 18 days ago by

danielhanchen

Please share feedback here!

pinned

#6 opened about 1 month ago by

shimmyshimmer

Can you provide a comparison of model accuracy under different quantization types?

#24 opened 5 days ago by

followyourheart

TQ1_0 deepseek-r1-0528 could not run with ollama

#23 opened 8 days ago by

yoummiegao

Problem with llama-server - llama_model_load: error loading model: check_tensor_dims: tensor 'blk.0.attn_q_b.weight' has wrong shape

#22 opened 10 days ago by

sdim

Help with finetuning

#19 opened 19 days ago by

Blazgo

Please add function calling support

👀 1

#16 opened 24 days ago by

0x010010

New 1.66-bit TQ1_0 quant that is 162GB

👍 3

#14 opened 27 days ago by

shimmyshimmer

Quantization method specified in the model config (fp8) does not match the quantization method specified in the `quantization` argument (gguf).

#13 opened 28 days ago by

Minami-su

invalid model: tensor 'blk.25.ffn_gate_exps.weight' is duplicated

#12 opened 29 days ago by

Rotating

Q4_0?

#11 opened 29 days ago by

teneriffa

1.78bit quant of full R1-0528 error

#10 opened 30 days ago by

d2rx

DeepSeek-V2-Lite needs to be GUFF! DeepSeek democracy is now!

🧠 1

#9 opened about 1 month ago by

Talkingperson123

add 1bit ie q1 quants

#8 opened about 1 month ago by

MarxistLeninist

Classic Q4_K_M?

#7 opened about 1 month ago by

EricTri

Ask for correcting the Dynamic 2.0 links of R1-0528

#5 opened about 1 month ago by

wangminle

When will it upload?thanks

👍 1

#3 opened about 1 month ago by

t8star

typo in new doc?

#2 opened about 1 month ago by

CHNtentes

太给力了

🔥 3

#1 opened about 1 month ago by

DeepFount