metadata
language:
- en
license: apache-2.0
tags:
- text-generation
- TensorBlock
- GGUF
datasets:
- THUDM/webglm-qa
- databricks/databricks-dolly-15k
- cognitivecomputations/wizard_vicuna_70k_unfiltered
- totally-not-an-llm/EverythingLM-data-V3
- Amod/mental_health_counseling_conversations
- sablo/oasst2_curated
- starfishmedical/webGPT_x_dolly
- Open-Orca/OpenOrca
- mlabonne/chatml_dpo_pairs
base_model: Felladrin/Llama-68M-Chat-v1
widget:
- messages:
- role: system
content: >-
You are a career counselor. The user will provide you with an
individual looking for guidance in their professional life, and your
task is to assist them in determining what careers they are most
suited for based on their skills, interests, and experience. You
should also conduct research into the various options available,
explain the job market trends in different industries, and advice on
which qualifications would be beneficial for pursuing particular
fields.
- role: user
content: Heya!
- role: assistant
content: Hi! How may I help you?
- role: user
content: >-
I am interested in developing a career in software engineering. What
would you recommend me to do?
- messages:
- role: system
content: You are a knowledgeable assistant. Help the user as much as you can.
- role: user
content: How to become healthier?
- messages:
- role: system
content: You are a helpful assistant who provides concise responses.
- role: user
content: Hi!
- role: assistant
content: Hello there! How may I help you?
- role: user
content: >-
I need to build a simple website. Where should I start learning about
web development?
- messages:
- role: system
content: >-
You are a very creative assistant. User will give you a task, which
you should complete with all your knowledge.
- role: user
content: >-
Write the background story of an RPG game about wizards and dragons in
a sci-fi world.
inference:
parameters:
max_new_tokens: 64
penalty_alpha: 0.5
top_k: 4
model-index:
- name: Llama-68M-Chat-v1
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: 23.29
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Llama-68M-Chat-v1
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: 28.27
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Llama-68M-Chat-v1
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: 25.18
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Llama-68M-Chat-v1
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: 47.27
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Llama-68M-Chat-v1
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: 54.3
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Llama-68M-Chat-v1
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: 0
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Felladrin/Llama-68M-Chat-v1
name: Open LLM Leaderboard
Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
Felladrin/Llama-68M-Chat-v1 - GGUF
This repo contains GGUF format model files for Felladrin/Llama-68M-Chat-v1.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.
Prompt template
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| Llama-68M-Chat-v1-Q2_K.gguf | Q2_K | 0.033 GB | smallest, significant quality loss - not recommended for most purposes |
| Llama-68M-Chat-v1-Q3_K_S.gguf | Q3_K_S | 0.037 GB | very small, high quality loss |
| Llama-68M-Chat-v1-Q3_K_M.gguf | Q3_K_M | 0.038 GB | very small, high quality loss |
| Llama-68M-Chat-v1-Q3_K_L.gguf | Q3_K_L | 0.039 GB | small, substantial quality loss |
| Llama-68M-Chat-v1-Q4_0.gguf | Q4_0 | 0.042 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| Llama-68M-Chat-v1-Q4_K_S.gguf | Q4_K_S | 0.042 GB | small, greater quality loss |
| Llama-68M-Chat-v1-Q4_K_M.gguf | Q4_K_M | 0.043 GB | medium, balanced quality - recommended |
| Llama-68M-Chat-v1-Q5_0.gguf | Q5_0 | 0.047 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| Llama-68M-Chat-v1-Q5_K_S.gguf | Q5_K_S | 0.047 GB | large, low quality loss - recommended |
| Llama-68M-Chat-v1-Q5_K_M.gguf | Q5_K_M | 0.048 GB | large, very low quality loss - recommended |
| Llama-68M-Chat-v1-Q6_K.gguf | Q6_K | 0.053 GB | very large, extremely low quality loss |
| Llama-68M-Chat-v1-Q8_0.gguf | Q8_0 | 0.068 GB | very large, extremely low quality loss - not recommended |
Downloading instruction
Command line
Firstly, install Huggingface Client
pip install -U "huggingface_hub[cli]"
Then, downoad the individual model file the a local directory
huggingface-cli download tensorblock/Llama-68M-Chat-v1-GGUF --include "Llama-68M-Chat-v1-Q2_K.gguf" --local-dir MY_LOCAL_DIR
If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:
huggingface-cli download tensorblock/Llama-68M-Chat-v1-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'