RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
Files
fc3478bf575bfeac6c534cc011f5eb04001f12de
grimjim_-_llama-3-experimen…/README.md
ModelHub XC fc3478bf57 初始化项目，由ModelHub XC社区提供模型 
Model: RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf
Source: Original Platform
2026-06-04 04:47:15 +08:00

226 lines
9.1 KiB
Markdown
Raw Blame History

Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
llama-3-experiment-v1-9B - GGUF
- Model creator: https://huggingface.co/grimjim/
- Original model: https://huggingface.co/grimjim/llama-3-experiment-v1-9B/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [llama-3-experiment-v1-9B.Q2_K.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.Q2_K.gguf) | Q2_K | 3.26GB |
| [llama-3-experiment-v1-9B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.IQ3_XS.gguf) | IQ3_XS | 3.61GB |
| [llama-3-experiment-v1-9B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.IQ3_S.gguf) | IQ3_S | 3.78GB |
| [llama-3-experiment-v1-9B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.Q3_K_S.gguf) | Q3_K_S | 3.76GB |
| [llama-3-experiment-v1-9B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.IQ3_M.gguf) | IQ3_M | 3.88GB |
| [llama-3-experiment-v1-9B.Q3_K.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.Q3_K.gguf) | Q3_K | 4.13GB |
| [llama-3-experiment-v1-9B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.Q3_K_M.gguf) | Q3_K_M | 4.13GB |
| [llama-3-experiment-v1-9B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.Q3_K_L.gguf) | Q3_K_L | 4.45GB |
| [llama-3-experiment-v1-9B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.IQ4_XS.gguf) | IQ4_XS | 4.61GB |
| [llama-3-experiment-v1-9B.Q4_0.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.Q4_0.gguf) | Q4_0 | 4.8GB |
| [llama-3-experiment-v1-9B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.IQ4_NL.gguf) | IQ4_NL | 4.84GB |
| [llama-3-experiment-v1-9B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.Q4_K_S.gguf) | Q4_K_S | 4.83GB |
| [llama-3-experiment-v1-9B.Q4_K.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.Q4_K.gguf) | Q4_K | 5.07GB |
| [llama-3-experiment-v1-9B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.Q4_K_M.gguf) | Q4_K_M | 5.07GB |
| [llama-3-experiment-v1-9B.Q4_1.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.Q4_1.gguf) | Q4_1 | 5.29GB |
| [llama-3-experiment-v1-9B.Q5_0.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.Q5_0.gguf) | Q5_0 | 5.77GB |
| [llama-3-experiment-v1-9B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.Q5_K_S.gguf) | Q5_K_S | 5.77GB |
| [llama-3-experiment-v1-9B.Q5_K.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.Q5_K.gguf) | Q5_K | 5.91GB |
| [llama-3-experiment-v1-9B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.Q5_K_M.gguf) | Q5_K_M | 5.91GB |
| [llama-3-experiment-v1-9B.Q5_1.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.Q5_1.gguf) | Q5_1 | 6.26GB |
| [llama-3-experiment-v1-9B.Q6_K.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.Q6_K.gguf) | Q6_K | 6.81GB |
| [llama-3-experiment-v1-9B.Q8_0.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.Q8_0.gguf) | Q8_0 | 8.82GB |
Original model description:
---
language:
- en
base_model:
- meta-llama/Meta-Llama-3-8B-Instruct
library_name: transformers
tags:
- meta
- llama-3
- pytorch
- mergekit
- merge
license: llama3
license_link: LICENSE
pipeline_tag: text-generation
widget:
- example_title: Hello
messages:
- role: user
content: Hey my name is Corwin! How are you?
- example_title: Hellriding out of Amber
messages:
- role: system
content: You are a helpful and honest assistant. Please, respond concisely and truthfully.
- role: user
content: Can you recommend a good destination for a hellride out of Amber?
inference:
parameters:
max_new_tokens: 300
stop:
- <|end_of_text|>
- <|eot_id|>
model-index:
- name: grimjim/grimjim/llama-3-experiment-v1-9B
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
num_few_shot: 25
metrics:
- type: acc_norm
value: 66.41
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/grimjim/llama-3-experiment-v1-9B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
num_few_shot: 10
metrics:
- type: acc_norm
value: 78.56
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/llama-3-experiment-v1-9B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU (5-Shot)
type: cais/mmlu
config: all
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 66.71
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/llama-3-experiment-v1-9B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: TruthfulQA (0-shot)
type: truthful_qa
config: multiple_choice
split: validation
args:
num_few_shot: 0
metrics:
- type: mc2
value: 50.7
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/llama-3-experiment-v1-9B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Winogrande (5-shot)
type: winogrande
config: winogrande_xl
split: validation
args:
num_few_shot: 5
metrics:
- type: acc
value: 75.93
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/llama-3-experiment-v1-9B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GSM8k (5-shot)
type: gsm8k
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 65.88
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/llama-3-experiment-v1-9B
name: Open LLM Leaderboard
---
# llama-3-experiment-v1-9B
This is an experimental merge, replicating additional layers to the model without post-merge healing.
There is damage to the model, but it appears to be tolerable as is; the performance difference in benchmarks from the original 8B Instruct model does not appear to be significant.
The resulting impact on narrative text completion may also be of interest.
Light testing performed with instruct prompting and the following sampler settings:
- temp=1 and minP=0.02
- temp=1 and smoothing factor=0.33
Full weights: [grimjim/llama-3-experiment-v1-9B](https://huggingface.co/grimjim/llama-3-experiment-v1-9B)
GGUF quants: [grimjim/llama-3-experiment-v1-9B-GGUF](https://huggingface.co/grimjim/llama-3-experiment-v1-9B-GGUF)
This is a merge of pre-trained language model meta-llama/Meta-Llama-3-8B-Instruct created using [mergekit](https://github.com/cg123/mergekit).
Built with Meta Llama 3.
## Merge Details
### Merge Method
This model was merged using the passthrough merge method.
### Models Merged
The following models were included in the merge:
* meta-llama/Meta-Llama-3-8B-Instruct
### Configuration
The following YAML configuration was used to produce this model:
```yaml
slices:
- sources:
- model: meta-llama/Meta-Llama-3-8B-Instruct
layer_range: [0, 12]
- sources:
- model: meta-llama/Meta-Llama-3-8B-Instruct
layer_range: [8, 32]
merge_method: passthrough
dtype: bfloat16
```
Reference in New Issue View Git Blame Copy Permalink