初始化项目，由ModelHub XC社区提供模型

Model: anujjamwal/OpenMath-Nemotron-1.5B-PruneAware-2 Source: Original Platform
2026-07-11 08:46:09 +08:00
commit 15ef177445
10 changed files with 224 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,36 @@
+*.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,58 @@
+---
+base_model: anujjamwal/OpenMath-Nemotron-1.5B-PruneAware-2
+library_name: transformers
+model_name: OpenMath-Nemotron-1.5B-PruneAware-2
+tags:
+- generated_from_trainer
+- sft
+- trl
+licence: license
+---
+
+# Model Card for OpenMath-Nemotron-1.5B-PruneAware-2
+
+This model is a fine-tuned version of [anujjamwal/OpenMath-Nemotron-1.5B-PruneAware-2](https://huggingface.co/anujjamwal/OpenMath-Nemotron-1.5B-PruneAware-2).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="anujjamwal/OpenMath-Nemotron-1.5B-PruneAware-2", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/anujjamwal-stanford-university/huggingface/runs/bv63j8gc) 
+
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.29.0
+- Transformers: 5.0.0
+- Pytorch: 2.10.0+cu128
+- Datasets: 4.0.0
+- Tokenizers: 0.22.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@software{vonwerra2020trl,
+  title   = {{TRL: Transformers Reinforcement Learning}},
+  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
+  license = {Apache-2.0},
+  url     = {https://github.com/huggingface/trl},
+  year    = {2020}
+}
+```
--- a/chat_template.jinja
+++ b/chat_template.jinja
@@ -0,0 +1,21 @@
+    {%- if messages[0]['role'] == 'system' -%}
+    <|im_start|>system
+    {{ messages[0]['content'] | trim }}<|im_end|>
+    {%- else -%}
+    <|im_start|>system
+    <|im_end|>
+    {%- endif -%}
+    {%- for message in messages -%}
+    {%- if (message.role == 'user') or (message.role == 'system' and not loop.first) or (message.role == 'assistant') -%}
+    <|im_start|>{{ message.role }}
+    {%- if message['role'] == 'assistant' %}
+    {% generation %}{{ message['content'] | trim }}<|im_end|>{% endgeneration %}
+    {%- else %}
+    {{ message['content'] | trim }}<|im_end|>
+    {%- endif %}
+    {%- endif -%}
+    {%- endfor -%}
+    {%- if add_generation_prompt %}
+    <|im_start|>assistant
+    {%- endif -%}
+    
--- a/config.json
+++ b/config.json
@@ -0,0 +1,61 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 131072,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 500000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151670
+}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    151645
+  ],
+  "pad_token_id": 151643,
+  "transformers_version": "5.0.0"
+}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:401594adf6a346b5cc115e9b1c1dd204d1e6802cd3e068d148f7e4e148b20178
+size 3086649992
--- a/runs/Mar11_22-10-34_f461185ab6ff/events.out.tfevents.1773267034.f461185ab6ff.1180.0
+++ b/runs/Mar11_22-10-34_f461185ab6ff/events.out.tfevents.1773267034.f461185ab6ff.1180.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31e93459929bf640298772b0627fb446f30c1a1780d1173123dc315d3d23814c
+size 17562
--- a/tokenizer.json
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4aa0f6873d276e78d29759ff1ba764fe84358db27b39fe8501119662f4c1c55a
+size 11422819
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,28 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_end|>",
+    "<|endoftext|>",
+    "[THOUGHT]",
+    "[SOLUTION]",
+    "[RETURN]",
+    "<think>",
+    "</think>",
+    "[THOUGHT]",
+    "[SOLUTION]",
+    "[RETURN]",
+    "<think>",
+    "</think>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
--- a/training_args.bin
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be44e0df7ab2ce6026d0b044e1685ff873b7381a359eff829ce8aa7f9565bfff
+size 5713