J22 (JJ) – Community Activity

#9 opened 11 days ago by

J22

no system message?

#14 opened 10 days ago by

mclassHF2023

New activity in microsoft/Phi-3-small-8k-instruct 9 days ago

"small" is so different from "mini" and "medium"

#8 opened 9 days ago by

J22

New activity in nvidia/Llama3-ChatQA-1.5-8B 24 days ago

how to set context in multi-turn QA?

#14 opened 25 days ago by

J22

New activity in microsoft/Phi-3-mini-128k-instruct about 1 month ago

clarification on the usage of `short_factor` and `long_factor`?

#49 opened about 1 month ago by

J22

Continue the discussion: `long_factor` and `short_factor`

#32 opened about 1 month ago by

J22

New activity in microsoft/Phi-3-mini-4k-instruct about 1 month ago

is the '\n' after `'<|end|>'`?

#43 opened about 1 month ago by

J22

Is sliding window used or not?

#25 opened about 1 month ago by

J22

New activity in microsoft/Phi-3-mini-128k-instruct about 1 month ago

`long_factor` is never used?

#22 opened about 1 month ago by

J22

generate +6 min, +20GB V-ram

#17 opened about 1 month ago by

NickyNicky

`sliding_window` is larger than `max_position_embeddings`

#21 opened about 1 month ago by

J22

New activity in meta-llama/Meta-Llama-3-8B about 1 month ago

When the text length exceeds 8k, the model begins to repeat, how to solve

#44 opened about 1 month ago by

zechangl

New activity in meta-llama/Meta-Llama-3-8B-Instruct about 1 month ago

can I run it on CPU ?

4

#28 opened about 1 month ago by

aljbali

ChatLLM.cpp fully supports Llama-3 now

#24 opened about 1 month ago by

J22

New activity in Qwen/CodeQwen1.5-7B-Chat about 2 months ago

comparing to Qwen1.5, the tokenizer is changed. Why?

#9 opened about 2 months ago by

J22

New activity in openbmb/MiniCPM-MoE-8x2B about 2 months ago

Run on CPU with ChatLLM.cpp

#1 opened about 2 months ago by

J22

New activity in jetmoe/jetmoe-8b about 2 months ago

why not include Qwen1.5-MoE-A2.7B in the table?

#4 opened about 2 months ago by

J22

New activity in Qwen/Qwen1.5-MoE-A2.7B-Chat 2 months ago

Run this on CPU with ChatLLM.cpp

#5 opened 2 months ago by

J22

New activity in xai-org/grok-1 2 months ago

Run this with 64GB RAM on CPU

4

#62 opened 2 months ago by

J22

New activity in CohereForAI/c4ai-command-r-v01 3 months ago

Run Command-R on CPU

4

#19 opened 3 months ago by

J22

New activity in openbmb/MiniCPM-2B-dpo-bf16 3 months ago

Run MiniCPM-2B on CPU

#2 opened 4 months ago by

J22

New activity in m-a-p/OpenCodeInterpreter-DS-6.7B 3 months ago

clarification needed in model card: this model is based on DeepSeekCoder.

#5 opened 3 months ago by

J22

New activity in Qwen/Qwen1.5-7B-Chat 4 months ago

大概试了一下，效果不如 v1 7B-Chat

#7 opened 4 months ago by

J22

New activity in adept/persimmon-8b-chat 4 months ago

the model can't generate any outputs

#5 opened 4 months ago by

J22

Run this on CPU with ChatLLM.cpp

#6 opened 4 months ago by

J22

New activity in internlm/internlm2-chat-7b 4 months ago

the art of renaming?

#6 opened 4 months ago by

J22

New activity in OrionStarAI/Orion-14B-Chat 4 months ago

ChatLLM.cpp now supports Orion

#6 opened 4 months ago by

J22

Differences bewteen OrionForCausalLM and LlamaForCausalLM

#5 opened 4 months ago by

J22

some text are not renamed to Orion

#4 opened 4 months ago by

J22

New activity in mlabonne/NeuralBeagle14-7B 4 months ago

Model follows ChatML format, but does not have the special tokens for ChatML

24

#3 opened 5 months ago by

andysalerno

New activity in 01-ai/Yi-VL-6B 4 months ago

where can we download "clip-vit-H-14-laion2B-s32B-b79K-yi-vl-6B-448"?

#2 opened 4 months ago by

J22

New activity in stabilityai/stable-code-3b 5 months ago

Run StableCode 3B on CPU

#4 opened 5 months ago by

J22

New activity in microsoft/phi-2 5 months ago

run Phi-2 on your CPU

12

#62 opened 5 months ago by

J22

New activity in Qwen/Qwen-72B-Chat 5 months ago

issues about config.json and model.py

#4 opened 5 months ago by

J22

New activity in vivo-ai/BlueLM-7B-Chat 5 months ago

Run BlueLM on CPU

#4 opened 5 months ago by

J22

New activity in mistralai/Mixtral-8x7B-Instruct-v0.1 5 months ago

How much memory do I need for this model (on Windows)?

3

#77 opened 5 months ago by

roboboot

New activity in openchat/openchat-3.5-1210 5 months ago

a very "plausible" model

#10 opened 5 months ago by

J22

New activity in WizardLMTeam/WizardMath-7B-V1.1 5 months ago

Limitation: could not solve the frog jumping from well problem

#3 opened 5 months ago by

J22

results are quite good

#2 opened 5 months ago by

J22

New activity in microsoft/phi-2 5 months ago

"Instruct: <prompt>\nOutput:" or "Instruction: <prompt>\nOutput:"

5

#60 opened 5 months ago by

J22

New activity in baichuan-inc/Baichuan2-7B-Chat 6 months ago

another error in data cleaning

#10 opened 6 months ago by

J22

New activity in baichuan-inc/Baichuan-7B 11 months ago

参数总数应该 7000293376 吧？

5

#16 opened 12 months ago by

J22

中文标点方面的不足

#20 opened 11 months 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

#19 opened 11 months ago by

redauzhang

语料未清洗案例1