From cd2183f2bcb230f86df97fe4cae520cb4f4fbb38 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Mon, 22 Jun 2026 15:31:12 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: QuantFactory/Einstein-v7-Qwen2-7B-GGUF Source: Original Platform --- .gitattributes | 39 ++++ Einstein-v7-Qwen2-7B.Q4_0.gguf | 3 + Einstein-v7-Qwen2-7B.Q4_1.gguf | 3 + Einstein-v7-Qwen2-7B.Q4_K_M.gguf | 3 + Einstein-v7-Qwen2-7B.Q8_0.gguf | 3 + README.md | 294 +++++++++++++++++++++++++++++++ configuration.json | 1 + 7 files changed, 346 insertions(+) create mode 100644 .gitattributes create mode 100644 Einstein-v7-Qwen2-7B.Q4_0.gguf create mode 100644 Einstein-v7-Qwen2-7B.Q4_1.gguf create mode 100644 Einstein-v7-Qwen2-7B.Q4_K_M.gguf create mode 100644 Einstein-v7-Qwen2-7B.Q8_0.gguf create mode 100644 README.md create mode 100644 configuration.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b887198 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,39 @@ +*.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 +Einstein-v7-Qwen2-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v7-Qwen2-7B.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v7-Qwen2-7B.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v7-Qwen2-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Einstein-v7-Qwen2-7B.Q4_0.gguf b/Einstein-v7-Qwen2-7B.Q4_0.gguf new file mode 100644 index 0000000..844718c --- /dev/null +++ b/Einstein-v7-Qwen2-7B.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e00380ad73d1584c140aa63ed3a5ed1c2e518c0ad8620756e1ae61d383740f02 +size 4431388096 diff --git a/Einstein-v7-Qwen2-7B.Q4_1.gguf b/Einstein-v7-Qwen2-7B.Q4_1.gguf new file mode 100644 index 0000000..4149025 --- /dev/null +++ b/Einstein-v7-Qwen2-7B.Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72cd15751fc77d92723ba79ab3b66633566ee003a522be189a679d87a86a1b54 +size 4873280960 diff --git a/Einstein-v7-Qwen2-7B.Q4_K_M.gguf b/Einstein-v7-Qwen2-7B.Q4_K_M.gguf new file mode 100644 index 0000000..1a6bbd1 --- /dev/null +++ b/Einstein-v7-Qwen2-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d1493e68196b80a015ef68dcda558f59f606785177234c4ddafd3003be00914 +size 4683070912 diff --git a/Einstein-v7-Qwen2-7B.Q8_0.gguf b/Einstein-v7-Qwen2-7B.Q8_0.gguf new file mode 100644 index 0000000..993a835 --- /dev/null +++ b/Einstein-v7-Qwen2-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d80726a5ad9dabce8a56dd47282bac5d648acf5b7e20edfb734fadd2a0ecb232 +size 8098522560 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9956507 --- /dev/null +++ b/README.md @@ -0,0 +1,294 @@ +--- +language: +- en +license: other +tags: +- axolotl +- instruct +- finetune +- chatml +- gpt4 +- synthetic data +- science +- physics +- chemistry +- biology +- math +- qwen +- qwen2 +base_model: Weyaxi/Einstein-v7-Qwen2-7B +datasets: +- allenai/ai2_arc +- camel-ai/physics +- camel-ai/chemistry +- camel-ai/biology +- camel-ai/math +- metaeval/reclor +- openbookqa +- mandyyyyii/scibench +- derek-thomas/ScienceQA +- TIGER-Lab/ScienceEval +- jondurbin/airoboros-3.2 +- LDJnr/Capybara +- Cot-Alpaca-GPT4-From-OpenHermes-2.5 +- STEM-AI-mtl/Electrical-engineering +- knowrohit07/saraswati-stem +- sablo/oasst2_curated +- lmsys/lmsys-chat-1m +- TIGER-Lab/MathInstruct +- bigbio/med_qa +- meta-math/MetaMathQA-40K +- openbookqa +- piqa +- metaeval/reclor +- derek-thomas/ScienceQA +- scibench +- sciq +- Open-Orca/SlimOrca +- migtissera/Synthia-v1.3 +- TIGER-Lab/ScienceEval +- allenai/WildChat +- microsoft/orca-math-word-problems-200k +- openchat/openchat_sharegpt4_dataset +- teknium/GPTeacher-General-Instruct +- m-a-p/CodeFeedback-Filtered-Instruction +- totally-not-an-llm/EverythingLM-data-V3 +- HuggingFaceH4/no_robots +- OpenAssistant/oasst_top1_2023-08-25 +- WizardLM/WizardLM_evol_instruct_70k +- abacusai/SystemChat-1.1 +- H-D-T/Buzz-V1.2 +pipeline_tag: text-generation +--- + +# 🔬 Einstein-v7-Qwen2-7B-GGUF +This is quantized version of [Weyaxi/Einstein-v7-Qwen2-7B](https://huggingface.co/Weyaxi/Einstein-v7-Qwen2-7B) created using llama.cpp + +# Model Description + +![image/png](https://cdn-uploads.huggingface.co/production/uploads/6468ce47e134d050a58aa89c/KLQP1jK-DIzpwHzYRIH-Q.png) + +This model is a full fine-tuned version of [Qwen/Qwen2-7B](https://huggingface.co/Qwen/Qwen2-7B) on diverse datasets. + +This model is finetuned using `8xMI300X` using [axolotl](https://github.com/OpenAccess-AI-Collective/axolotl). + +
See axolotl config + +axolotl version: `0.4.0` +```yaml +base_model: Qwen/Qwen2-7B +model_type: AutoModelForCausalLM +tokenizer_type: AutoTokenizer + +load_in_8bit: false +load_in_4bit: false +strict: false + +chat_template: chatml +datasets: + - path: data/airoboros_3.2_without_contextual_slimorca_orca_sharegpt.json + ds_type: json + type: sharegpt + conversation: chatml + + - path: data/allenai_wild_chat_gpt4_english_toxic_random_half_4k_sharegpt.json + ds_type: json + type: sharegpt + strict: false + conversation: chatml + + - path: data/buzz_unstacked_chosen_math_removed_filtered.json + ds_type: json + type: alpaca + conversation: chatml + + - path: data/capybara_sharegpt.json + ds_type: json + type: sharegpt + conversation: chatml + + - path: data/cot_alpaca_gpt4_extracted_openhermes_2.5_sharegpt.json + ds_type: json + type: sharegpt + conversation: chatml + + - path: data/everythinglm-data-v3_sharegpt.json + ds_type: json + type: sharegpt + strict: false + conversation: chatml + + - path: data/gpt4_data_lmys_1m_sharegpt.json + ds_type: json + type: sharegpt + conversation: chatml + + - path: data/gpteacher-instruct-special-alpaca.json + ds_type: json + type: gpteacher + conversation: chatml + + - path: data/merged_all.json + ds_type: json + type: alpaca + conversation: chatml + + - path: data/no_robots_sharegpt.json + ds_type: json + type: sharegpt + strict: false + conversation: chatml + + - path: data/oasst_top1_from_fusechatmixture_sharegpt.json + ds_type: json + type: sharegpt + strict: false + conversation: chatml + + - path: data/pippa_bagel_repo_3k_sharegpt.json + ds_type: json + type: sharegpt + conversation: chatml + + - path: data/rpguild_quarter_alignment_lab_sharegpt.json + ds_type: json + type: sharegpt + conversation: chatml + + - path: data/sharegpt_gpt4_english.json + ds_type: json + type: sharegpt + conversation: chatml + + - path: data/slimorca_dedup_filtered_95k_sharegpt.json + ds_type: json + type: sharegpt + conversation: chatml + + - path: data/soda_diaolog_longest_tenth_buzz_sharegpt.json + ds_type: json + type: sharegpt + conversation: chatml + + - path: data/synthia-v1.3_sharegpt_12500.json + ds_type: json + type: sharegpt + conversation: chatml + + - path: data/system_conversations_dolphin_sharegpt.json + ds_type: json + type: sharegpt + conversation: chatml + +dataset_prepared_path: last_run_prepared +val_set_size: 0.002 + +output_dir: ./Einstein-v7-Qwen2-7B-model + +sequence_len: 8192 +sample_packing: true +pad_to_sequence_len: true +eval_sample_packing: false + +wandb_project: Einstein +wandb_entity: +wandb_watch: +wandb_name: +wandb_log_model: +hub_model_id: Weyaxi/Einstein-v7-Qwen2-7B + +gradient_accumulation_steps: 4 +micro_batch_size: 6 +num_epochs: 2 +optimizer: paged_adamw_8bit +lr_scheduler: cosine +learning_rate: 0.00001 # look + +train_on_inputs: false +group_by_length: false +bf16: auto +fp16: +tf32: false + +gradient_checkpointing: unsloth +gradient_checkpointing_kwargs: + use_reentrant: true # look +early_stopping_patience: +resume_from_checkpoint: +local_rank: +logging_steps: 1 +xformers_attention: +flash_attention: true + +warmup_steps: 10 +evals_per_epoch: 2 +eval_table_size: +eval_max_new_tokens: 128 +saves_per_epoch: 1 +debug: + +deepspeed: deepspeed_configs/zero3_bf16.json +weight_decay: 0.05 +fsdp: +fsdp_config: +special_tokens: + eos_token: "<|im_end|>" + pad_token: "<|end_of_text|>" +tokens: + - "<|im_start|>" + - "<|im_end|>" +``` + +

+ +# 💬 Prompt Template + +You can use ChatML prompt template while using the model: + +### ChatML + +``` +<|im_start|>system +{system}<|im_end|> +<|im_start|>user +{user}<|im_end|> +<|im_start|>assistant +{asistant}<|im_end|> +``` + +This prompt template is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating), which means you can format messages using the +`tokenizer.apply_chat_template()` method: + +```python +messages = [ + {"role": "system", "content": "You are helpful AI asistant."}, + {"role": "user", "content": "Hello!"} +] +gen_input = tokenizer.apply_chat_template(message, return_tensors="pt") +model.generate(**gen_input) +``` + +# 📊 Datasets used in this model + +The datasets used to train this model are listed in the metadata section of the model card. + +Please note that certain datasets mentioned in the metadata may have undergone filtering based on various criteria. + +The results of this filtering process and its outcomes are in a diffrent repository: + +[Weyaxi/sci-datasets/main](https://huggingface.co/datasets/Weyaxi/sci-datasets/tree/main) + + +# 🎯 [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) + +# 🤖 Additional information about training + +This model is full fine-tuned for 2 epoch. + +Total number of steps was 500. + +
Loss graph + +![image/png](https://cdn-uploads.huggingface.co/production/uploads/6468ce47e134d050a58aa89c/bkJGgh_JUfKeRlTLo_ZcB.png) + +

\ No newline at end of file diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file