JJ
J22
AI & ML interests
None yet
Organizations
None yet
J22's activity
Run this on CPU
#6 opened 19 days ago
by
J22
Run on CPU
#13 opened 21 days ago
by
J22
need gguf
17
#4 opened about 1 month ago
by
windkkk
Best practice for tool calling with meta-llama/Meta-Llama-3.1-8B-Instruct
1
#33 opened 2 months ago
by
zzclynn
Run this on CPU and use tool calling
1
#38 opened 2 months ago
by
J22
My alternative quantizations.
5
#5 opened 3 months ago
by
ZeroWw
Tool calling is supported by ChatLLM.cpp
#36 opened 4 months ago
by
J22
can't say hello
1
#9 opened 4 months ago
by
J22
no system message?
8
#14 opened 4 months ago
by
mclassHF2023
"small" is so different from "mini" and "medium"
1
#8 opened 4 months ago
by
J22
how to set context in multi-turn QA?
6
#14 opened 5 months ago
by
J22
clarification on the usage of `short_factor` and `long_factor`?
1
#49 opened 5 months ago
by
J22
Continue the discussion: `long_factor` and `short_factor`
2
#32 opened 5 months ago
by
J22
is the '\n' after `'<|end|>'`?
1
#43 opened 5 months ago
by
J22
Is sliding window used or not?
1
#25 opened 5 months ago
by
J22
`long_factor` is never used?
2
#22 opened 5 months ago
by
J22
generate +6 min, +20GB V-ram
2
#17 opened 5 months ago
by
NickyNicky
`sliding_window` is larger than `max_position_embeddings`
1
#21 opened 5 months ago
by
J22
When the text length exceeds 8k, the model begins to repeat, how to solve
1
#44 opened 5 months ago
by
zechangl
can I run it on CPU ?
5
#28 opened 6 months ago
by
aljbali
ChatLLM.cpp fully supports Llama-3 now
#24 opened 6 months ago
by
J22
comparing to Qwen1.5, the tokenizer is changed. Why?
1
#9 opened 6 months ago
by
J22
Run on CPU with ChatLLM.cpp
#1 opened 6 months ago
by
J22
why not include Qwen1.5-MoE-A2.7B in the table?
1
#4 opened 6 months ago
by
J22
Run this on CPU with ChatLLM.cpp
#5 opened 6 months ago
by
J22
Run this with 64GB RAM on CPU
4
#62 opened 6 months ago
by
J22
Run Command-R on CPU
4
#19 opened 7 months ago
by
J22
Run MiniCPM-2B on CPU
6
#2 opened 8 months ago
by
J22
clarification needed in model card: this model is based on DeepSeekCoder.
1
#5 opened 7 months ago
by
J22
大概试了一下,效果不如 v1 7B-Chat
1
#7 opened 8 months ago
by
J22
the model can't generate any outputs
2
#5 opened 8 months ago
by
J22
Run this on CPU with ChatLLM.cpp
#6 opened 8 months ago
by
J22
the art of renaming?
#6 opened 8 months ago
by
J22
ChatLLM.cpp now supports Orion
#6 opened 8 months ago
by
J22
Differences bewteen OrionForCausalLM and LlamaForCausalLM
1
#5 opened 8 months ago
by
J22
some text are not renamed to Orion
1
#4 opened 8 months ago
by
J22
Model follows ChatML format, but does not have the special tokens for ChatML
24
#3 opened 9 months ago
by
andysalerno
where can we download "clip-vit-H-14-laion2B-s32B-b79K-yi-vl-6B-448"?
2
#2 opened 8 months ago
by
J22
Run StableCode 3B on CPU
#4 opened 9 months ago
by
J22
run Phi-2 on your CPU
12
#62 opened 9 months ago
by
J22
issues about config.json and model.py
1
#4 opened 9 months ago
by
J22
Run BlueLM on CPU
#4 opened 9 months ago
by
J22
How much memory do I need for this model (on Windows)?
3
#77 opened 9 months ago
by
roboboot
a very "plausible" model
#10 opened 9 months ago
by
J22
Limitation: could not solve the frog jumping from well problem
1
#3 opened 9 months ago
by
J22
results are quite good
#2 opened 9 months ago
by
J22
"Instruct: <prompt>\nOutput:" or "Instruction: <prompt>\nOutput:"
5
#60 opened 9 months ago
by
J22
another error in data cleaning
#10 opened 10 months ago
by
J22
参数总数应该 7000293376 吧?
5
#16 opened over 1 year ago
by
J22
又可用的 baichuan.cpp 借用avx2运行的吗,我看都是 csm家族的模型呢
2
#19 opened about 1 year ago
by
redauzhang
语料未清洗案例1
6
#18 opened over 1 year ago
by
lupumusic