You can deploy this model and start earning money today!

RichardErkhov/
mergekit-community_-_LLaMa-3.1-8B-InitializedEmbeds-gguf

Name: mergekit-community_-_LLaMa-3.1-8B-InitializedEmbeds-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

LLaMa-3.1-8B-InitializedEmbeds - GGUF

Model creator: https://huggingface.co/mergekit-community/
Original model: https://huggingface.co/mergekit-community/LLaMa-3.1-8B-InitializedEmbeds/

Name	Quant method	Size
LLaMa-3.1-8B-InitializedEmbeds.Q2_K.gguf	Q2_K	2.96GB
LLaMa-3.1-8B-InitializedEmbeds.IQ3_XS.gguf	IQ3_XS	3.28GB
LLaMa-3.1-8B-InitializedEmbeds.IQ3_S.gguf	IQ3_S	3.43GB
LLaMa-3.1-8B-InitializedEmbeds.Q3_K_S.gguf	Q3_K_S	3.41GB
LLaMa-3.1-8B-InitializedEmbeds.IQ3_M.gguf	IQ3_M	3.52GB
LLaMa-3.1-8B-InitializedEmbeds.Q3_K.gguf	Q3_K	3.74GB
LLaMa-3.1-8B-InitializedEmbeds.Q3_K_M.gguf	Q3_K_M	3.74GB
LLaMa-3.1-8B-InitializedEmbeds.Q3_K_L.gguf	Q3_K_L	4.03GB
LLaMa-3.1-8B-InitializedEmbeds.IQ4_XS.gguf	IQ4_XS	4.18GB
LLaMa-3.1-8B-InitializedEmbeds.Q4_0.gguf	Q4_0	4.34GB
LLaMa-3.1-8B-InitializedEmbeds.IQ4_NL.gguf	IQ4_NL	4.38GB
LLaMa-3.1-8B-InitializedEmbeds.Q4_K_S.gguf	Q4_K_S	4.37GB
LLaMa-3.1-8B-InitializedEmbeds.Q4_K.gguf	Q4_K	4.58GB
LLaMa-3.1-8B-InitializedEmbeds.Q4_K_M.gguf	Q4_K_M	4.58GB
LLaMa-3.1-8B-InitializedEmbeds.Q4_1.gguf	Q4_1	4.78GB
LLaMa-3.1-8B-InitializedEmbeds.Q5_0.gguf	Q5_0	5.21GB
LLaMa-3.1-8B-InitializedEmbeds.Q5_K_S.gguf	Q5_K_S	5.21GB
LLaMa-3.1-8B-InitializedEmbeds.Q5_K.gguf	Q5_K	5.34GB
LLaMa-3.1-8B-InitializedEmbeds.Q5_K_M.gguf	Q5_K_M	5.34GB
LLaMa-3.1-8B-InitializedEmbeds.Q5_1.gguf	Q5_1	5.65GB
LLaMa-3.1-8B-InitializedEmbeds.Q6_K.gguf	Q6_K	6.14GB
LLaMa-3.1-8B-InitializedEmbeds.Q8_0.gguf	Q8_0	7.95GB

Original model description:

base_model:

unsloth/Meta-Llama-3.1-8B
unsloth/Meta-Llama-3.1-8B-Instruct library_name: transformers tags:
mergekit
merge

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the linear merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

yaml

merge_method: linear
dtype: float32
out_dtype: bfloat16
models:
  - model: unsloth/Meta-Llama-3.1-8B
    parameters:
      weight: 1.0
  - model: unsloth/Meta-Llama-3.1-8B-Instruct
    parameters:
      weight: 0.0
tokenizer:
  source: unsloth/Meta-Llama-3.1-8B-Instruct
  tokens:
    <|begin_of_text|>:
      source: unsloth/Meta-Llama-3.1-8B-Instruct
      force: true
    <|end_of_text|>:
      source: unsloth/Meta-Llama-3.1-8B-Instruct
      force: true
    <|finetune_right_pad_id|>:
      source: unsloth/Meta-Llama-3.1-8B-Instruct
      force: true
    <|start_header_id|>:
      source: unsloth/Meta-Llama-3.1-8B-Instruct
      force: true
    <|end_header_id|>:
      source: unsloth/Meta-Llama-3.1-8B-Instruct
      force: true
    <|eom_id|>:
      source: unsloth/Meta-Llama-3.1-8B-Instruct
      force: true
    <|eot_id|>:
      source: unsloth/Meta-Llama-3.1-8B-Instruct
      force: true
    <|python_tag|>:
      source: unsloth/Meta-Llama-3.1-8B-Instruct
      force: true
    <|eot_id|>:
      source: unsloth/Meta-Llama-3.1-8B-Instruct
      force: true
    <|eot_id|>:
      source: unsloth/Meta-Llama-3.1-8B-Instruct
      force: true

RichardErkhov/mergekit-community_-_LLaMa-3.1-8B-InitializedEmbeds-gguf