From 7d4e257a40670c19dc264907a5ead37051c600cc Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Thu, 9 Jul 2026 02:22:04 +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: SupraLabs/Supra-1.5-50M-base-exp Source: Original Platform --- .gitattributes | 50 ++++++++++++++++++++++++++++ README.md | 74 +++++++++++++++++++++++++++++++++++++++++ config.json | 38 +++++++++++++++++++++ configuration.json | 1 + generation_config.json | 7 ++++ model.safetensors | 3 ++ special_tokens_map.json | 6 ++++ tokenizer.json | 3 ++ tokenizer_config.json | 44 ++++++++++++++++++++++++ 9 files changed, 226 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 config.json create mode 100644 configuration.json create mode 100644 generation_config.json create mode 100644 model.safetensors create mode 100644 special_tokens_map.json create mode 100644 tokenizer.json create mode 100644 tokenizer_config.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..16332c1 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text + +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +tokenizer.json filter=lfs diff=lfs merge=lfs -text +model.safetensors filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..def4086 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +license: apache-2.0 +language: +- en +pipeline_tag: text-generation +library_name: transformers +tags: +- supra +- supra-1.5 +- llama +- 50m +- base +- continued-pretraining +- long-context +- 5k-context +- Supra +- Supra-50M +--- + +

Supra1.5-50M Base

+ +

+ Continued Pretraining • 50M Parameters • 5K Context +

+ +![Supra-1.5-Base-EXP](https://cdn-uploads.huggingface.co/production/uploads/68a5d0966d33a07f8aad2e51/Lh7KcQs60Ht9iray8WFbp.png) + +Supra-1.5-50M-Base-exp is a continued-pretrained 50M parameter Llama-style base +model derived from `SupraLabs/Supra-50M-Base`. The target update expands the +usable context window from 1,024 tokens to 5,120 tokens using RoPE scaling and +full-weight continued pretraining. + + + +## Architecture + +The model keeps the original Supra-50M architecture and tokenizer: + +| Specification | Value | +|--------------|--------| +| Architecture | `LlamaForCausalLM` | +| Parameters | ~50M | +| Vocabulary Size | 32,000 | +| Hidden Size | 512 | +| Layers | 12 | +| Attention Heads | 8 | +| KV Heads | 4 | +| Context Length | 5,120 tokens | +| Tokenizer | Original Supra byte-level BPE tokenizer | + +## Continued Pretraining Objective + +This is CPT, not instruction fine-tuning. Training uses packed raw text with +standard causal language-modeling loss: + +- `labels = input_ids` +- all non-pad tokens are trained +- no response-only masking +- no system/user/assistant masking +- no LoRA adapters in the default run + +## Data Mix + +The current local training mix prepared for this run is: + +- 3,000,000,062 CPT tokens + - 30% Tool Calling + - 30% ChatML Conversations + - 25% Factual Text (articles, essays, blogs) + - 15% Math & Logic Questions + + +### Intended Use +Supervised Fine-Tuning (SFT) and Reinforcement Learning \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..67ea85c --- /dev/null +++ b/config.json @@ -0,0 +1,38 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 0, + "dtype": "float32", + "eos_token_id": 2, + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 512, + "initializer_range": 0.02, + "intermediate_size": 1408, + "max_position_embeddings": 5120, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 8, + "num_hidden_layers": 12, + "num_key_value_heads": 4, + "pad_token_id": 1, + "pretraining_tp": 1, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "factor": 1.0, + "rope_theta": 10000, + "rope_type": "linear" + }, + "rope_scaling": { + "factor": 1.0, + "type": "linear" + }, + "rope_theta": 10000.0, + "tie_word_embeddings": true, + "transformers_version": "4.57.6", + "use_cache": false, + "vocab_size": 32000 +} 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..a2b9d95 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 0, + "eos_token_id": 2, + "pad_token_id": 1, + "transformers_version": "4.57.6" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..e437f3a --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:952972f6bea7544402bcc9f025e43be4e5fe4053ca1858ece60558438fe8b961 +size 207157136 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..fdafe48 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,6 @@ +{ + "bos_token": "", + "eos_token": "", + "pad_token": "", + "unk_token": "" +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..19dcf9e --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78674e4a6e1ed782c30f506420976a25ee52018212ea90e368b7a1e806982b08 +size 2268112 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..ce85e7c --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,44 @@ +{ + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "extra_special_tokens": {}, + "model_max_length": 5120, + "pad_token": "", + "tokenizer_class": "PreTrainedTokenizerFast", + "unk_token": "" +}