commit 0e82ae105f28267c7397403937668358bc57d998
Author: ModelHub XC <noreply@modelhub.org.cn>
Date:   Sun May 17 22:16:31 2026 +0800

    初始化项目，由ModelHub XC社区提供模型
    
    Model: EleutherAI/llemma_7b_muinstruct_camelmath
    Source: Original Platform

diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000..53d7257
--- /dev/null
+++ b/.gitattributes
@@ -0,0 +1,47 @@
+*.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
+*.safetensors 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
\ No newline at end of file
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..d967def
--- /dev/null
+++ b/README.md
@@ -0,0 +1,39 @@
+---
+license: apache-2.0
+datasets:
+- EleutherAI/muInstruct
+- camel-ai/math
+language:
+- en
+tags:
+- math
+---
+
+`llemma_7b_muinstruct_camelmath` is an instruction-following finetune of [Llemma 7B](https://huggingface.co/EleutherAI/llemma_7b), trained on the [μInstruct](https://huggingface.co/datasets/EleutherAI/muInstruct) and [camel-ai/math](https://huggingface.co/datasets/camel-ai/math) datasets.
+
+## Input Formatting
+Format input queries as follows:
+```
+input_text = f"Input:{input}\n\nResponse:"
+```
+
+Note that due to an error during training, this model's end-of-sequence token ID is `0` instead of the `2` which is standard for Llama-2 based models. Inference APIs should handle this automatically by reading this repo's `config.json`, but be aware of this difference if you are doing token surgery.
+
+## Evals
+`
+llemma_7b_muinstruct_camelmath` compares favorably to other 7B parameter models on the [Hungarian Math Exam](https://huggingface.co/datasets/keirp/hungarian_national_hs_finals_exam/blob/main/README.md). It surpasses the few-shot performance of Llemma 7B whilst being the strongest Llama-2 7B based model. 
+
+| Model                                                                          | Exam Score |
+| ------------------------------------------------------------------------------ | ---------- |
+| [Code Llama 7B](https://huggingface.co/codellama/CodeLlama-7b-hf) (few-shot)   | 8\%        |
+| [MetaMath 7B](https://huggingface.co/meta-math/MetaMath-7B-V1.0)               | 20\%       |
+| [MAmmoTH 7B](https://huggingface.co/TIGER-Lab/MAmmoTH-7B)                      | 17\%       | 
+| [MAmmoTH Coder 7B](https://huggingface.co/TIGER-Lab/MAmmoTH-Coder-7B)          | 11\%       | 
+| [Llemma 7B](https://huggingface.co/EleutherAI/llemma_7b) (few-shot)            | 23\%       | 
+| Llemma_7B_muinstruct_camelmath                                                 | 25\%       | 
+| -                                                                              | -          | 
+| [Mistral 7B](https://huggingface.co/mistralai/Mistral-7B-v0.1) (few-shot)      | 22\%       | 
+| [MetaMath Mistral 7B](https://huggingface.co/meta-math/MetaMath-Mistral-7B)    | 29\%       | 
+| [OpenChat 3.5](https://huggingface.co/openchat/openchat_3.5)                   | 37\%       | 
+
+
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..3a2c059
--- /dev/null
+++ b/config.json
@@ -0,0 +1,22 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 0,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.2",
+  "use_cache": true,
+  "vocab_size": 32016
+}
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..69da086
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 0,
+  "pad_token_id": 0,
+  "transformers_version": "4.30.2"
+}
diff --git a/pytorch_model-00001-of-00003.bin b/pytorch_model-00001-of-00003.bin
new file mode 100644
index 0000000..52b9838
--- /dev/null
+++ b/pytorch_model-00001-of-00003.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf73fc8b424994dedf1ce08093e2ee6838541affca66c4b76ceae68ba5dcf3cf
+size 9878251730
diff --git a/pytorch_model-00002-of-00003.bin b/pytorch_model-00002-of-00003.bin
new file mode 100644
index 0000000..f91feab
--- /dev/null
+++ b/pytorch_model-00002-of-00003.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdadc9c8173dd2679336b70ef5b64d311ae19b6d388d260b202b556926550f43
+size 9894801014
diff --git a/pytorch_model-00003-of-00003.bin b/pytorch_model-00003-of-00003.bin
new file mode 100644
index 0000000..f43d2ab
--- /dev/null
+++ b/pytorch_model-00003-of-00003.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7416526721b63be3687430df31a743a306f86e73d4120d016cb03e5d79a153b
+size 7181252793
diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json
new file mode 100644
index 0000000..b8d25be
--- /dev/null
+++ b/pytorch_model.bin.index.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83a799c899ddda20ec6d08e8806507f1fd296809ea0fbcbf46e253798ac2861f
+size 26788
diff --git a/tokenizer.model b/tokenizer.model
new file mode 100644
index 0000000..f6722e8
--- /dev/null
+++ b/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058