Hugging Face's logo
Mike Ravkine's picture
44 3 293

Mike Ravkine

mike-ravkine
victor's profile picture Keron's profile picture rexzen's profile picture
·
whatsmypot
the-crypt-keeper

AI & ML interests

AI, Research

Organizations

None yet

mike-ravkine's activity

New activity in mike-ravkine/can-ai-code-results about 1 month ago

New Phi-3-vision-128k-instruct Dropped today, please test it

2
#14 opened about 1 month ago by Dotoro22
New activity in mike-ravkine/can-ai-code-results about 2 months ago

What does best result only option mean? How does it differ from the original leaderboard?

3
#6 opened 5 months ago by zhiminy

Why doesn't the number of rows of both Python and Javascript add up to both?

1
#10 opened 3 months ago by zhiminy

Model request. (Instruct-senior)

4
#8 opened 4 months ago by rombodawg

Evaluate interview.ndjson

2
#13 opened about 2 months ago by Dotoro22
New activity in ddh0/Meta-Llama-3-8B-Instruct-bf16-GGUF about 2 months ago

CUDA support

2
#2 opened about 2 months ago by mike-ravkine
New activity in mike-ravkine/can-ai-code-results about 2 months ago

Model request - Codeqwen-7b-code-v1.5-fp16

10
#12 opened about 2 months ago by Dotoro22
New activity in ibm-granite/granite-3b-code-instruct about 2 months ago

Fix trailing , in generation_config.json

2
#1 opened about 2 months ago by mike-ravkine
New activity in mike-ravkine/can-ai-code-results 4 months ago

What is `junior-dev` after all?

1
#7 opened 5 months ago by zhiminy
New activity in budecosystem/code-millenials-3b 5 months ago

Update boomer_code_tokenizer.py
#1 opened 5 months ago by mike-ravkine
New activity in mike-ravkine/can-ai-code-results 5 months ago

Any manner to download the evaluation results in the leaderboard as csv or json format?

7
#2 opened 7 months ago by zhiminy
New activity in TencentARC/LLaMA-Pro-8B-Instruct 6 months ago

Prompting

2
#7 opened 6 months ago by AliceThirty
New activity in mike-ravkine/can-ai-code-results 6 months ago

Can you include my models?

6
#5 opened 6 months ago by ajibawa-2023

What does summarization result option mean? How does it differ from the original leaderboard?

4
#4 opened 7 months ago by zhiminy
New activity in replit/replit-code-v1_5-3b 6 months ago

Error with new version of transformers v4.35.0

2
#10 opened 8 months ago by alonsosilva
New activity in TheBloke/Mixtral-8x7B-Instruct-v0.1-AWQ 6 months ago

OOM under vLLM even with 80GB GPU

5
#2 opened 6 months ago by mike-ravkine
New activity in mike-ravkine/can-ai-code-results 6 months ago

Why not only keep the latest version?

2
#3 opened 7 months ago by zhiminy
New activity in The-Face-Of-Goonery/Huginn-13b-v1.2 11 months ago

Recommended prompt format

1
#3 opened 11 months ago by mike-ravkine
New activity in mike-ravkine/can-ai-code-results 11 months ago

Apply for community grant: Personal project (gpu and storage)
#1 opened 11 months ago by mike-ravkine
New activity in HuggingFaceH4/starchat-alpha 11 months ago

Warning

1
#23 opened 12 months ago by Sardar
New activity in TheBloke/WizardCoder-Guanaco-15B-V1.1-GPTQ 11 months ago

exllama requires that pad_token_id be specified in config.json

2
#2 opened 12 months ago by mike-ravkine
New activity in TheBloke/Llama-2-7B-Chat-GGML 12 months ago

Benchmark of different GGML version

2
#2 opened 12 months ago by aiapprentice101

Update prompt format

8
#4 opened 12 months ago by mike-ravkine

Chat prompt format?

12
#3 opened 12 months ago by mike-ravkine
New activity in abhinavkulkarni/tiiuae-falcon-40b-instruct-w4-g128-awq 12 months ago

Successful inference using a 24GB GPU
#2 opened 12 months ago by mike-ravkine

Fix q_group_size

1
#1 opened 12 months ago by mike-ravkine
New activity in mrm8488/falcoder-7b 12 months ago

ValueError: If `eos_token_id` is defined, make sure that `pad_token_id` is defined.
#2 opened 12 months ago by mike-ravkine
New activity in abhinavkulkarni/tiiuae-falcon-7b-instruct-w4-g64-awq 12 months ago

Thanks for this model!

4
#1 opened 12 months ago by mike-ravkine
New activity in TheBloke/starchat-beta-GGML about 1 year ago

special tokens in prompt with ggml/examples/starcoder

1
#3 opened about 1 year ago by mljxy
New activity in TheBloke/minotaur-15B-GPTQ about 1 year ago

Upload merges.txt

5
#1 opened about 1 year ago by mike-ravkine
New activity in jondurbin/rosettacode-raw about 1 year ago

Cleaned version

5
#3 opened about 1 year ago by mike-ravkine

First attempt at a cleaning

3
#2 opened about 1 year ago by mike-ravkine

Upload solutions-2023-06-17.jsonl
#1 opened about 1 year ago by mike-ravkine
New activity in HuggingFaceH4/falcon-chat about 1 year ago

Does this model support FIM?

1
#1 opened about 1 year ago by mike-ravkine
New activity in tiiuae/falcon-40b-instruct about 1 year ago

The default eos_token_id is 2, should be 11

3
#11 opened about 1 year ago by mike-ravkine
New activity in TheBloke/falcon-40b-instruct-GPTQ about 1 year ago

Update config.json

1
#10 opened about 1 year ago by mike-ravkine
New activity in TheBloke/Falcon-7B-Instruct-GPTQ about 1 year ago

Update config.json
#8 opened about 1 year ago by mike-ravkine
New activity in TheBloke/falcon-40b-instruct-GPTQ about 1 year ago

Default eos_token_id=2 is incorrect, needs to be 11

1
#8 opened about 1 year ago by mike-ravkine
New activity in TheBloke/Falcon-7B-Instruct-GPTQ about 1 year ago

Fix eos_token_id to align with vocabulary of this model
#6 opened about 1 year ago by mike-ravkine
New activity in TheBloke/falcon-40b-instruct-GPTQ about 1 year ago

Fix eos_token_id to align with vocabulary of this model

1
#9 opened about 1 year ago by mike-ravkine

Any working tag/release/hash of AutoGPTQ?

4
#4 opened about 1 year ago by mike-ravkine
New activity in bigcode/tiny_starcoder_py about 1 year ago

Fim tokens use _ as seperator not -

1
#2 opened about 1 year ago by mike-ravkine
New activity in navteca/ms-marco-MiniLM-L-6-v2 about 1 year ago

Thanks! But what happened to cross-encoder organization?

2
#1 opened about 1 year ago by mike-ravkine