commit 8efa5f0844037fc3e4c095b9554b7372772d8f44 Author: ModelHub XC Date: Sun Jun 21 11:54:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: QuantFactory/Samantha-Qwen-2-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5411e6f --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +Samantha-Qwen-2-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Samantha-Qwen-2-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Samantha-Qwen-2-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Samantha-Qwen-2-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Samantha-Qwen-2-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Samantha-Qwen-2-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Samantha-Qwen-2-7B.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Samantha-Qwen-2-7B.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Samantha-Qwen-2-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Samantha-Qwen-2-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Samantha-Qwen-2-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Samantha-Qwen-2-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Samantha-Qwen-2-7B.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +Samantha-Qwen-2-7B.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..aaaced9 --- /dev/null +++ b/README.md @@ -0,0 +1,153 @@ +--- +base_model: macadeliccc/Samantha-Qwen-2-7B +datasets: +- macadeliccc/opus_samantha +- HuggingfaceH4/ultrachat_200k +- teknium/OpenHermes-2.5 +- Sao10K/Claude-3-Opus-Instruct-15K +license: apache-2.0 +language: +- en +- zh +pipeline_tag: text-generation +--- +# Samantha Qwen2 7B-GGUF +This is quantized version of [macadeliccc/Samantha-Qwen-2-7B](https://huggingface.co/macadeliccc/Samantha-Qwen-2-7B) created using llama.cpp + +# Model Description + +Trained on 2x4090 using QLoRa and FSDP + ++ [LoRa](macadeliccc/Samantha-Qwen2-7B-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. +``` + +[Built with Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) +
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: +``` + +

\ No newline at end of file diff --git a/Samantha-Qwen-2-7B.Q2_K.gguf b/Samantha-Qwen-2-7B.Q2_K.gguf new file mode 100644 index 0000000..68b9453 --- /dev/null +++ b/Samantha-Qwen-2-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:349cd04ad6a13979c4d1f62ff679077786cab07b855306732471fe4215fb4f55 +size 3015937536 diff --git a/Samantha-Qwen-2-7B.Q3_K_L.gguf b/Samantha-Qwen-2-7B.Q3_K_L.gguf new file mode 100644 index 0000000..1319974 --- /dev/null +++ b/Samantha-Qwen-2-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cce56c9a8661e53e6cf945cb871a8e2b6b03c8d78c6c9c839c547c1329fef60a +size 4088456704 diff --git a/Samantha-Qwen-2-7B.Q3_K_M.gguf b/Samantha-Qwen-2-7B.Q3_K_M.gguf new file mode 100644 index 0000000..4fd3df6 --- /dev/null +++ b/Samantha-Qwen-2-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ec207f55555ab1a24d04d6524bddc7a68f4b200a13655a1fb6991ad14cf1bb3 +size 3808388608 diff --git a/Samantha-Qwen-2-7B.Q3_K_S.gguf b/Samantha-Qwen-2-7B.Q3_K_S.gguf new file mode 100644 index 0000000..da98914 --- /dev/null +++ b/Samantha-Qwen-2-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad2539e58c693d5ee06eec4516b1299426135100867fb964d01e488062611af6 +size 3492365824 diff --git a/Samantha-Qwen-2-7B.Q4_0.gguf b/Samantha-Qwen-2-7B.Q4_0.gguf new file mode 100644 index 0000000..e87e69a --- /dev/null +++ b/Samantha-Qwen-2-7B.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:872a7128b43de36f6d86ee0382fbcbdd53f3e44d519d7d0226f679935a4293c3 +size 4431388160 diff --git a/Samantha-Qwen-2-7B.Q4_1.gguf b/Samantha-Qwen-2-7B.Q4_1.gguf new file mode 100644 index 0000000..18d0f96 --- /dev/null +++ b/Samantha-Qwen-2-7B.Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:389416406b41e9d34ce01672bf83e8c2ce654a752d6f6ec9c850581ba07afe8f +size 4873281024 diff --git a/Samantha-Qwen-2-7B.Q4_K_M.gguf b/Samantha-Qwen-2-7B.Q4_K_M.gguf new file mode 100644 index 0000000..f2ecdbf --- /dev/null +++ b/Samantha-Qwen-2-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f1f5f481f0545839a43a51df2267960ac350fb72be8f1baaf8c596380fb1b9f +size 4683070976 diff --git a/Samantha-Qwen-2-7B.Q4_K_S.gguf b/Samantha-Qwen-2-7B.Q4_K_S.gguf new file mode 100644 index 0000000..e7efb5b --- /dev/null +++ b/Samantha-Qwen-2-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0925ac84fabafe679bfc78a932e269927c68e6657987831f02a74bb9b81fc470 +size 4457766400 diff --git a/Samantha-Qwen-2-7B.Q5_0.gguf b/Samantha-Qwen-2-7B.Q5_0.gguf new file mode 100644 index 0000000..52e700c --- /dev/null +++ b/Samantha-Qwen-2-7B.Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f26872a6f57b32c9acffff20e4669ad166cf096904adedc3e3c1144b9a5f2f1f +size 5315173888 diff --git a/Samantha-Qwen-2-7B.Q5_1.gguf b/Samantha-Qwen-2-7B.Q5_1.gguf new file mode 100644 index 0000000..f61d49e --- /dev/null +++ b/Samantha-Qwen-2-7B.Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:254f866432fc7979260f3f9ca2e1036fb2c46f58f99830b7b4930bbd85088b7b +size 5757066752 diff --git a/Samantha-Qwen-2-7B.Q5_K_M.gguf b/Samantha-Qwen-2-7B.Q5_K_M.gguf new file mode 100644 index 0000000..c7d708b --- /dev/null +++ b/Samantha-Qwen-2-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4867596ae0cd70d4bb24c3c96482e83572214418bc48377949a3e1f520bb6ea +size 5444828672 diff --git a/Samantha-Qwen-2-7B.Q5_K_S.gguf b/Samantha-Qwen-2-7B.Q5_K_S.gguf new file mode 100644 index 0000000..84ad843 --- /dev/null +++ b/Samantha-Qwen-2-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edf4cd28fc9681227bb4d132fd85fb9df0fd9d994ffcb3a460c4623002d7b779 +size 5315173888 diff --git a/Samantha-Qwen-2-7B.Q6_K.gguf b/Samantha-Qwen-2-7B.Q6_K.gguf new file mode 100644 index 0000000..d0795f3 --- /dev/null +++ b/Samantha-Qwen-2-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b31f7ac3117252ae5b0826ad0ae15a62d37063f293914990c77105bcdff7a527 +size 6254196224 diff --git a/Samantha-Qwen-2-7B.Q8_0.gguf b/Samantha-Qwen-2-7B.Q8_0.gguf new file mode 100644 index 0000000..784a1e9 --- /dev/null +++ b/Samantha-Qwen-2-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:088265227c108b76ac244f95129faf2dacba0364986591a8d71918abd9910a2c +size 8098522624 diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..9e26dfe --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{} \ No newline at end of file