From efe3300b4194b9a899e5759694a1c26e4ea75330 Mon Sep 17 00:00:00 2001
From: ModelHub XC <noreply@modelhub.org.cn>
Date: Sun, 10 May 2026 20:43:03 +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: glaiveai/glaive-coder-7b
Source: Original Platform
---
 .gitattributes          | 47 ++++++++++++++++++++++++++++++++++++
 README.md               | 53 +++++++++++++++++++++++++++++++++++++++++
 added_tokens.json       |  3 +++
 config.json             | 27 +++++++++++++++++++++
 configuration.json      |  1 +
 generation_config.json  |  6 +++++
 pytorch_model.bin       |  3 +++
 special_tokens_map.json | 30 +++++++++++++++++++++++
 tokenizer.model         |  3 +++
 tokenizer_config.json   | 49 +++++++++++++++++++++++++++++++++++++
 10 files changed, 222 insertions(+)
 create mode 100644 .gitattributes
 create mode 100644 README.md
 create mode 100644 added_tokens.json
 create mode 100644 config.json
 create mode 100644 configuration.json
 create mode 100644 generation_config.json
 create mode 100644 pytorch_model.bin
 create mode 100644 special_tokens_map.json
 create mode 100644 tokenizer.model
 create mode 100644 tokenizer_config.json

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..934fb34
--- /dev/null
+++ b/README.md
@@ -0,0 +1,53 @@
+---
+license: llama2
+datasets:
+- glaiveai/glaive-code-assistant
+language:
+- en
+tags:
+- code
+---
+
+# Glaive-coder-7b
+
+Glaive-coder-7b is a 7B parameter code model trained on a dataset of ~140k programming related problems and solutions generated from Glaive’s synthetic data generation platform.
+
+The model is fine-tuned on the CodeLlama-7b model.
+
+## Usage:
+
+The model is trained to act as a code assistant, and can do both single instruction following and multi-turn conversations.
+It follows the same prompt format as CodeLlama-7b-Instruct-
+```
+<s>[INST]
+<<SYS>>
+{{ system_prompt }}
+<</SYS>>
+
+{{ user_msg }} [/INST] {{ model_answer }} </s>
+<s>[INST] {{ user_msg }} [/INST]
+```
+
+You can run the model in the following way-
+
+```python
+from transformers import AutoModelForCausalLM , AutoTokenizer
+
+tokenizer = AutoTokenizer.from_pretrained("glaiveai/glaive-coder-7b")
+model = AutoModelForCausalLM.from_pretrained("glaiveai/glaive-coder-7b").half().cuda()
+
+def fmt_prompt(prompt):
+    return f"<s> [INST] {prompt} [/INST]"
+
+inputs = tokenizer(fmt_prompt(prompt),return_tensors="pt").to(model.device)
+
+outputs = model.generate(**inputs,do_sample=True,temperature=0.1,top_p=0.95,max_new_tokens=100)
+
+print(tokenizer.decode(outputs[0],skip_special_tokens=True,clean_up_tokenization_spaces=False))
+```
+
+## Benchmarks:
+
+The model achieves a 63.1% pass@1 on HumanEval and a 45.2% pass@1 on MBPP, however it is evident that these benchmarks are not representative of real-world usage of code models so we are launching the [Code Models Arena](https://arena.glaive.ai/) to let users vote on model outputs so we can have a better understanding of user preference on code models and come up with new and better benchmarks. We plan to release the Arena results as soon as we have a sufficient amount of data.
+
+Join the Glaive [discord](https://discord.gg/fjQ4uf3yWD) for improvement suggestions, bug-reports and collaborating on more open-source projects.
\ No newline at end of file
diff --git a/added_tokens.json b/added_tokens.json
new file mode 100644
index 0000000..24d4035
--- /dev/null
+++ b/added_tokens.json
@@ -0,0 +1,3 @@
+{
+  "<|pad|>": 32016
+}
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..920e50d
--- /dev/null
+++ b/config.json
@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "codellama/CodeLlama-7b-Instruct-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 16384,
+  "max_seq_len": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.32.0",
+  "use_cache": true,
+  "vocab_size": 32017
+}
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..20e04b5
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.32.0"
+}
diff --git a/pytorch_model.bin b/pytorch_model.bin
new file mode 100644
index 0000000..e2c530b
--- /dev/null
+++ b/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4c35e92e96e3493907fb7e52af0638176ee92dd1067c64d3081ed2a0f19972d
+size 26954367285
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000..851316b
--- /dev/null
+++ b/special_tokens_map.json
@@ -0,0 +1,30 @@
+{
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|pad|>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}
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
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..03fa81a
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,49 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eot_token": "▁<EOT>",
+  "fill_token": "<FILL_ME>",
+  "legacy": null,
+  "middle_token": "▁<MID>",
+  "model_max_length": 4096,
+  "pad_token": null,
+  "padding_side": "right",
+  "prefix_token": "▁<PRE>",
+  "sp_model_kwargs": {},
+  "suffix_first": false,
+  "suffix_token": "▁<SUF>",
+  "tokenizer_class": "CodeLlamaTokenizer",
+  "trust_remote_code": true,
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_fast": false
+}