Big Deeper

New activity in mistralai/Mistral-Nemo-Base-2407 2 days ago

Does it need a specific template?

#12 opened 2 days ago by

New activity in google/gemma-2-27b-it 21 days ago

__ output

#19 opened 21 days ago by

New activity in mistralai/Codestral-22B-v0.1 about 2 months ago

What is the context size on this model? And it does not appear to deal with JSON, function calling well.

#15 opened about 2 months ago by

New activity in QuantFactory/Meta-Llama-3-120B-Instruct-GGUF 2 months ago

What does 120B really mean?

#1 opened 2 months ago by

New activity in meta-llama/Meta-Llama-3-70B 3 months ago

Does anyone know which specific Python library contains the tokenizer that was used to train Llama-3-70b?

#11 opened 3 months ago by

15 TeraTokens = 190 Million books

#4 opened 3 months ago by

Languido

New activity in meta-llama/Meta-Llama-3-8B 3 months ago

I was trying to fine-tune llama3 8b but getting following error - TypeError: LlamaForCausalLM.forward() got an unexpected keyword argument 'decoder_input_ids'

#117 opened 3 months ago by

aniiikket11

Llama-3-70b tokenizer.

#116 opened 3 months ago by

New activity in davidkim205/Rhea-72b-v0.5 3 months ago

Looking for a model to replace OpenAI API for use in agentic code generation, like gpt-pilot or devika. etc...

#7 opened 3 months ago by

New activity in Kotokin/Llama-3-70B-Instruct-exl2-4bpw-rpcal-32k 3 months ago

What does exl2-4bpw-rpcal in the model name mean?

#1 opened 3 months ago by

New activity in cognitivecomputations/dolphin-2.9-llama3-8b-gguf 3 months ago

Has anyone tried this gguf with agentic framework?

#6 opened 3 months ago by

New activity in cognitivecomputations/dolphin-2.9-llama3-8b-256k 3 months ago

Was trying to quantize to 8 bits to reduce VRAM footprint. Got the stuff below.

#3 opened 3 months ago by

New activity in microsoft/Phi-3-mini-128k-instruct 3 months ago

gguf

30

#24 opened 3 months ago by

LaferriereJC

New activity in pjh64/Phi-3-mini-128K-Instruct.gguf 3 months ago

How did you manage to produce gguf files, when llama.cpp/convert.py gives an error about the ROPE encoding?

4

#1 opened 3 months ago by

New activity in PrunaAI/Phi-3-mini-128k-instruct-GGUF-Imatrix-smashed 3 months ago

Do they work with ollama? How was the conversion done for 128K, llama.cpp/convert.py complains about ROPE.

8

#2 opened 3 months ago by

New activity in QuantFactory/Phi-3-mini-128k-instruct-GGUF 3 months ago

I have now tried two quantizations 8_0, and 6_K, they both fail like you see below.

#2 opened 3 months ago by

New activity in MaziyarPanahi/Meta-Llama-3-70B-Instruct-GGUF 3 months ago

Instruct versus non-Instruct

54

#8 opened 3 months ago by

New activity in stabilityai/stable-code-3b 4 months ago

Prompting template

#13 opened 4 months ago by

New activity in deepseek-ai/deepseek-coder-33b-instruct 4 months ago

tokenizer.model

#26 opened 4 months ago by

New activity in ByteDance/SDXL-Lightning 5 months ago

Can't load the model files. The same error whether it is 4 or 8.

#24 opened 5 months ago by

New activity in stabilityai/stable-cascade 5 months ago

4 GPUs with 12.2GiB each. Not totally clear from readme files all the steps to be done.

#21 opened 5 months ago by

New activity in TheBloke/Mixtral-8x7B-v0.1-GGUF 7 months ago

Anyone else seeing similar behavior? I especially like the start "Death, ..." plus some gobblygook.

#12 opened 7 months ago by

Not finding blk.0.ffn_gate.weight. I checked sha256sum, matches the Q6_K version. Any thoughts on how to fix this?

#6 opened 7 months ago by

New activity in DiscoResearch/DiscoLM-mixtral-8x7b-v2 7 months ago

Trying to quantize. Running into the issue below. Any suggestions?

#5 opened 7 months ago by

New activity in Salesforce/codegen-16B-multi 8 months ago

Where is tokenizer.model file?

#3 opened 8 months ago by

New activity in Salesforce/codegen-350M-nl 8 months ago

Why isn't "tokenizer.model" file in this repo?

#3 opened 8 months ago by

New activity in Salesforce/codegen2-7B_P 8 months ago

Where are your "tokenizer.model" files for all your models?

#2 opened 8 months ago by

New activity in TheBloke/Llama-2-70B-Chat-GGUF 10 months ago

invalid magic number 00000000

8

#1 opened 10 months ago by

New activity in EleutherAI/pythia-6.9b over 1 year ago

Open Assistant with Pythia

#1 opened over 1 year ago by

New activity in joaoalvarenga/bloom-8bit over 1 year ago

Even 330GB of host RAM is not enough

#8 opened over 1 year ago by

*.bin files

#7 opened over 1 year ago by