Hugging Face's logo
南栖's picture
27 5 332

南栖

Minami-su
Jamesmith's profile picture fieryTransition's profile picture upseem's profile picture
·

AI & ML interests

NLP，MultiModal，Human intelligence,Autonomous Cognitive,Self-instruction generation, enhanced instruction

Organizations

Future Girl Research Institute's profile picture DataComp 's profile picture

Minami-su's activity

New activity in huggingface/HuggingDiscussions 22 days ago

[FEEDBACK] Daily Papers

65
#32 opened 3 months ago by kramp
New activity in Minami-su/Qwen1.5-0.5B-Chat_llamafy 3 months ago

Could you convert also Qwen/Qwen2-0.5B-Instruct?

2
#1 opened 3 months ago by Felladrin
New activity in Minami-su/Qwen1.5-32B-Chat-quip-3bit 3 months ago

这模型可以用 vllm-gptq 这个分支部署推理嘛？

6
#1 opened 3 months ago by lich60132
New activity in deepseek-ai/DeepSeek-V2-Chat 4 months ago

MoE offloading strategy？

2
#8 opened 4 months ago by Minami-su
New activity in Minami-su/IA_14B 6 months ago

Update README.md
#1 opened 6 months ago by Minami-su
commented a paper 6 months ago
New activity in Minami-su/Qwen1.5-7B-Chat_mistral 7 months ago

Adding Evaluation Results
#1 opened 7 months ago by leaderboard-pr-bot

Adding Evaluation Results
#2 opened 7 months ago by Minami-su
New activity in Minami-su/Qwen1.5-7B-Chat_llamafy 7 months ago

Adding Evaluation Results
#3 opened 7 months ago by Minami-su

GGUF Creation from Llamafy

6
#1 opened 7 months ago by RonanMcGovern
commented 2 papers 7 months ago
New activity in OrionStarAI/Orion-14B-Chat 8 months ago

some text are not renamed to Orion

1
#4 opened 8 months ago by J22

llama rename？

1
#3 opened 8 months ago by Minami-su
New activity in cloudyu/Mixtral_34Bx2_MoE_60B 8 months ago

source code and paper?

8
#6 opened 9 months ago by josephykwang
New activity in KnutJaegersberg/Tess-M-34B-2bit 9 months ago

Re-Quantize Model

7
#1 opened 9 months ago by igoforth
New activity in Minami-su/SUS-Chat-34B_2bit 9 months ago

Re-Quantize?

1
#2 opened 9 months ago by igoforth

Hessian context length?

13
#1 opened 9 months ago by KnutJaegersberg
New activity in Minami-su/Yi_34B_Chat_2bit 9 months ago

Hessians?

3
#2 opened 9 months ago by somehumanperson1
New activity in Minami-su/Yi_34B_Chat_2bit 10 months ago

Chinese token capabilities?

2
#1 opened 10 months ago by at676
New activity in THUDM/cogvlm-chat-hf 10 months ago

Increasing throughput with batches and quantization

7
#11 opened 10 months ago by miguelcarv
New activity in BelleGroup/BELLE-on-Open-Datasets over 1 year ago

tokenizer加载非常的慢

3
#1 opened over 1 year ago by Minami-su
New activity in tiiuae/falcon-40b-instruct over 1 year ago

RuntimeError: CUDA error: CUBLAS_STATUS_NOT_INITIALIZED when calling `cublasCreate(handle)`

1
#3 opened over 1 year ago by Minami-su
New activity in tiiuae/falcon-40b over 1 year ago

RuntimeError: CUDA error: CUBLAS_STATUS_NOT_INITIALIZED when calling `cublasCreate(handle)`

2
#11 opened over 1 year ago by Minami-su

When query model for text generation I get this - The model 'RWForCausalLM' is not supported for text-generation.

19
#8 opened over 1 year ago by airtable
New activity in PygmalionAI/pygmalion-6b over 1 year ago

It should be a good choice to use bloom or bloomz to train the new pygmalion model?

4
#20 opened over 1 year ago by win10