commit dbd43c798005f649f6450b4557b27a9caab94b0e Author: ModelHub XC Date: Sat Jun 6 02:30:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: DevQuasar/llama3_8b_chat_brainstorm-v2.1 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a6344aa --- /dev/null +++ b/.gitattributes @@ -0,0 +1,35 @@ +*.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 diff --git a/README.md b/README.md new file mode 100644 index 0000000..84b7512 --- /dev/null +++ b/README.md @@ -0,0 +1,85 @@ +--- +license: llama3 +datasets: +- DevQuasar/brainstorm-v2.1_vicuna_1k +base_model: meta-llama/Meta-Llama-3-8B +pipeline_tag: text-generation +model_context_window: 8192 +--- +[](https://devquasar.com) + +'Make knowledge free for everyone' + +Buy Me a Coffee at ko-fi.com + +# Brainstorm-v2.1 + +![image/png](https://cdn-uploads.huggingface.co/production/uploads/64e6d37e02dee9bcb9d9fa18/sGo1r3ShaLDvVs_fwhmbb.png) + +# Model intention +Brainstorm facilitates idea exploration through interaction with a Language Model (LLM). +Rather than providing direct answers, the model engages in a dialogue with users, offering +probing questions aimed at fostering deeper contemplation and consideration of various +facets of their ideas. Model can summarize the discussed ideas in Markdown format. + +## Examples + +### Inference code +https://github.com/csabakecskemeti/ai_utils/blob/main/brainstorm_inference.py + +### Example generations +[USER] (Ctrl+C to exit): +I'd like to organize my vintage computer collection + +[CHAT]: That sounds like a great idea! What kind of organization system are you thinking of using? + +[USER] (Ctrl+C to exit): +Make it sure that they are available for use any time, but I don't want to see all the cables hanging around + +[CHAT]: So you want to make it easy to access and tidy up the cables. Have you considered using a cable management system or tying up loose ends with ribbon cutters? + + +[USER] (Ctrl+C to exit): +That makes sense + +[CHAT]: What about labeling each device so you can find what you need quickly? + +[USER] (Ctrl+C to exit): +Can you please summaryze what we've been talked so far? + +[CHAT]: Here's a summary: + +**Organizing Vintage Computer Collection** +=============================== + +* Make sure devices are easily accessible for use +* Tidy up cables using a cable management system or ribbon cutters +* Label each device to find it quickly + +Let me know if you'd like to add or modify anything! + +[USER] (Ctrl+C to exit): +Ok let's continue: I also want to use a single monoytor an pheripherias for all computer + +[CHAT]: That could get expensive fast. Are you thinking of using a hub or a switch? Or maybe something more sophisticated like a KVM switch? + +[USER] (Ctrl+C to exit): +yest that's make sense, can you please add it to the summary? + +[CHAT]: Here's the updated summary: + +**Organizing Vintage Computer Collection** +=============================== + +* Make sure devices are easily accessible for use +* Tidy up cables using a cable management system or ribbon cutters +* Label each device to find it quickly +* Use a single monitor and peripherals for all computers (hub, switch, KVM switch) + +Let me know if there's anything else you'd like to add or change! + +[USER] (Ctrl+C to exit): +I also want to protect them from dust, not sure how to do that + +[CHAT]: For protecting against dust, one option could be using enclosures or cabinets. Another approach might be setting up a dedicated workspace with appropriate ventilation. Which of these ideas resonates with you? + diff --git a/config.json b/config.json new file mode 100644 index 0000000..aefae48 --- /dev/null +++ b/config.json @@ -0,0 +1,28 @@ +{ + "_name_or_path": "meta-llama/Meta-Llama-3-8B", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": 128001, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 8192, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "float32", + "transformers_version": "4.40.1", + "use_cache": true, + "vocab_size": 128256 +} 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 diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..c30ef49 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,9 @@ +{ + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": 128001, + "max_length": 4096, + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "4.40.1" +} diff --git a/model-00001-of-00007.safetensors b/model-00001-of-00007.safetensors new file mode 100644 index 0000000..263e02c --- /dev/null +++ b/model-00001-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b49ac8595805afe34d8a5689870074c8f184c60f561419f1f44b39aa2ac7a32b +size 4886466168 diff --git a/model-00002-of-00007.safetensors b/model-00002-of-00007.safetensors new file mode 100644 index 0000000..5399fd4 --- /dev/null +++ b/model-00002-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2aa7080416c35d7a21f69d11daffe6b488718cfbba981e4a864fc5f327eaf819 +size 4832007448 diff --git a/model-00003-of-00007.safetensors b/model-00003-of-00007.safetensors new file mode 100644 index 0000000..7c8ba50 --- /dev/null +++ b/model-00003-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df3c76cc570ebde87c16ad9c11342f98b6373c49ab641e725814afea72c2f30e +size 4999813112 diff --git a/model-00004-of-00007.safetensors b/model-00004-of-00007.safetensors new file mode 100644 index 0000000..fa2f951 --- /dev/null +++ b/model-00004-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbbedd8fccb1ecaea7ff31557081cd7a21a998561c866c4e6e73c1347353e1e8 +size 4999813128 diff --git a/model-00005-of-00007.safetensors b/model-00005-of-00007.safetensors new file mode 100644 index 0000000..b701de4 --- /dev/null +++ b/model-00005-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:367955eadca9f669d49d52858a1f8e21b6acde770b6ef1029e0deb17fd0ae25f +size 4832007496 diff --git a/model-00006-of-00007.safetensors b/model-00006-of-00007.safetensors new file mode 100644 index 0000000..8ba40ad --- /dev/null +++ b/model-00006-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ace769367e6ccd174025f6cfaf0718a595b7df18fcd1660b6b2f193d0ee39f62 +size 4999813120 diff --git a/model-00007-of-00007.safetensors b/model-00007-of-00007.safetensors new file mode 100644 index 0000000..e0ba244 --- /dev/null +++ b/model-00007-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:552e3796e9e0c8399eafa062a6fbf167b4f763b4e6737cb78466bc8611816353 +size 2571158184 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..faf6f20 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb83c0dcc965cf42c5bc8fa1b1d88eae170b5beb5b705297c33a6399be9d0d2d +size 23950 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..cfabacc --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,16 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..9a62752 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e134af98b985517b4f068e3755ae90d4e9cd2d45d328325dc503f1c6b2d06cc7 +size 9085698 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..9e49e8f --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:690727b4fed286383df1c7ca5e805124cb70c6eb4529f807c7b2e60ff741da7e +size 50566