Update - Tool Calling + Chat Template bug fixes
pinned
9
#20 opened about 1 month ago
by
danielhanchen
Please share feedback here!
pinned
34
#6 opened about 2 months ago
by
shimmyshimmer
Can you provide a comparison of model accuracy under different quantization types?
#24 opened about 1 month ago
by
followyourheart
TQ1_0 deepseek-r1-0528 could not run with ollama
#23 opened about 1 month 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 about 1 month ago
by
sdim
Help with finetuning
1
#19 opened about 2 months ago
by
Blazgo
Please add function calling support
👀
1
3
#16 opened about 2 months ago
by
0x010010
New 1.66-bit TQ1_0 quant that is 162GB
👍
3
4
#14 opened about 2 months ago
by
shimmyshimmer
Quantization method specified in the model config (fp8) does not match the quantization method specified in the `quantization` argument (gguf).
1
#13 opened about 2 months ago
by
Minami-su
invalid model: tensor 'blk.25.ffn_gate_exps.weight' is duplicated
2
#12 opened about 2 months ago
by
Rotating
1.78bit quant of full R1-0528 error
2
#10 opened about 2 months ago
by
d2rx
DeepSeek-V2-Lite needs to be GUFF! DeepSeek democracy is now!
🧠
1
#9 opened about 2 months ago
by
Talkingperson123
add 1bit ie q1 quants
2
#8 opened about 2 months ago
by
MarxistLeninist
Classic Q4_K_M?
7
#7 opened about 2 months ago
by
EricTri
Ask for correcting the Dynamic 2.0 links of R1-0528
1
#5 opened about 2 months ago
by
wangminle
When will it upload?thanks
👍
1
1
#3 opened about 2 months ago
by
t8star
typo in new doc?
4
#2 opened about 2 months ago
by
CHNtentes
太给力了
🔥
3
2
#1 opened about 2 months ago
by
DeepFount