You can deploy this model and start earning money today!

RichardErkhov/
macadeliccc_-_Samantha-Qwen-2-7B-gguf

Name: macadeliccc_-_Samantha-Qwen-2-7B-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Samantha-Qwen-2-7B - GGUF

Model creator: https://huggingface.co/macadeliccc/
Original model: https://huggingface.co/macadeliccc/Samantha-Qwen-2-7B/

Name	Quant method	Size
Samantha-Qwen-2-7B.Q2_K.gguf	Q2_K	2.81GB
Samantha-Qwen-2-7B.IQ3_XS.gguf	IQ3_XS	3.12GB
Samantha-Qwen-2-7B.IQ3_S.gguf	IQ3_S	3.26GB
Samantha-Qwen-2-7B.Q3_K_S.gguf	Q3_K_S	3.25GB
Samantha-Qwen-2-7B.IQ3_M.gguf	IQ3_M	3.33GB
Samantha-Qwen-2-7B.Q3_K.gguf	Q3_K	3.55GB
Samantha-Qwen-2-7B.Q3_K_M.gguf	Q3_K_M	3.55GB
Samantha-Qwen-2-7B.Q3_K_L.gguf	Q3_K_L	3.81GB
Samantha-Qwen-2-7B.IQ4_XS.gguf	IQ4_XS	3.96GB
Samantha-Qwen-2-7B.Q4_0.gguf	Q4_0	4.13GB
Samantha-Qwen-2-7B.IQ4_NL.gguf	IQ4_NL	4.16GB
Samantha-Qwen-2-7B.Q4_K_S.gguf	Q4_K_S	4.15GB
Samantha-Qwen-2-7B.Q4_K.gguf	Q4_K	4.36GB
Samantha-Qwen-2-7B.Q4_K_M.gguf	Q4_K_M	4.36GB
Samantha-Qwen-2-7B.Q4_1.gguf	Q4_1	4.54GB
Samantha-Qwen-2-7B.Q5_0.gguf	Q5_0	4.95GB
Samantha-Qwen-2-7B.Q5_K_S.gguf	Q5_K_S	4.95GB
Samantha-Qwen-2-7B.Q5_K.gguf	Q5_K	5.07GB
Samantha-Qwen-2-7B.Q5_K_M.gguf	Q5_K_M	5.07GB
Samantha-Qwen-2-7B.Q5_1.gguf	Q5_1	5.36GB
Samantha-Qwen-2-7B.Q6_K.gguf	Q6_K	5.82GB
Samantha-Qwen-2-7B.Q8_0.gguf	Q8_0	7.54GB

Original model description:

base_model: Qwen/Qwen2-7B datasets:

macadeliccc/opus_samantha
HuggingfaceH4/ultrachat_200k
teknium/OpenHermes-2.5
Sao10K/Claude-3-Opus-Instruct-15K license: apache-2.0 language:
en
zh

Samantha Qwen2 7B

Trained on 2x4090 using QLoRa and FSDP

LoRa

Launch Using VLLM

bash

python -m vllm.entrypoints.openai.api_server \
    --model macadeliccc/Samantha-Qwen-2-7B \
    --chat-template ./examples/template_chatml.jinja \

python

from openai import OpenAI
# Set OpenAI's API key and API base to use vLLM's API server.
openai_api_key = "EMPTY"
openai_api_base = "http://localhost:8000/v1"

client = OpenAI(
    api_key=openai_api_key,
    base_url=openai_api_base,
)

chat_response = client.chat.completions.create(
    model="macadeliccc/Samantha-Qwen-2-7B",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Tell me a joke."},
    ]
)
print("Chat response:", chat_response)

Prompt Template

<|im_start|>system
You are  a friendly assistant.<|im_end|>
<|im_start|>user
What is the capital of France?<|im_end|>
<|im_start|>assistant
The capital of France is Paris.

Quants

See axolotl config

axolotl version: 0.4.0

yaml

base_model: Qwen/Qwen-7B
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false

datasets:
  - path: macadeliccc/opus_samantha
    type: sharegpt
    field: conversations
    conversation: chatml
  - path: uncensored-ultrachat.json
    type: sharegpt
    field: conversations
    conversation: chatml
  - path: openhermes_200k.json
    type: sharegpt
    field: conversations
    conversation: chatml
  - path: opus_instruct.json
    type: sharegpt
    field: conversations
    conversation: chatml

chat_template: chatml
dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/lora-out

sequence_len: 2048
sample_packing: false
pad_to_sequence_len:

adapter: qlora
lora_model_dir:
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: false
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention:

warmup_steps: 250
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:

RichardErkhov/macadeliccc_-_Samantha-Qwen-2-7B-gguf