Upload folder using huggingface_hub

README.md

@@ -0,0 +1,52 @@
+---
+license: other
+license_name: deepseek-license
+license_link: LICENSE
+---
+
+<p align="center">
+<img width="1000px" alt="DeepSeek Coder" src="https://github.com/deepseek-ai/DeepSeek-Coder/blob/main/pictures/logo.png?raw=true">
+</p>
+<p align="center"><a href="https://www.deepseek.com/">[🏠Homepage]</a>  |  <a href="https://coder.deepseek.com/">[🤖 Chat with DeepSeek Coder]</a>  |  <a href="https://discord.gg/Tc7c45Zzu5">[Discord]</a>  |  <a href="https://github.com/guoday/assert/blob/main/QR.png?raw=true">[Wechat(微信)]</a> </p>
+<hr>
+
+[AQLM](https://arxiv.org/abs/2401.06118) quantized version of deepseek-coder-6.7b-base model.
+Refer to the [official GitHub repo](https://github.com/Vahe1994/AQLM) for more information.
+
+---
+
+### 1. Introduction of Deepseek-Coder-7B-Base-v1.5
+
+Deepseek-Coder-7B-Base-v1.5 is continue pre-trained from Deepseek-LLM 7B on 2T tokens by employing a window size of 4K and next token prediction objective.
+
+- **Home Page:** [DeepSeek](https://deepseek.com/)
+- **Repository:** [deepseek-ai/deepseek-coder](https://github.com/deepseek-ai/deepseek-coder)
+- **Chat With DeepSeek Coder:** [DeepSeek-Coder](https://coder.deepseek.com/)
+
+
+### 2. Evaluation Results
+<img width="1000px" alt="DeepSeek Coder" src="https://cdn-uploads.huggingface.co/production/uploads/6538815d1bdb3c40db94fbfa/xOtCTW5xdoLCKY4FR6tri.png">
+
+
+
+### 3. How to Use
+Here give an example of how to use our model.
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/deepseek-coder-7b-base-v1.5", trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained("deepseek-ai/deepseek-coder-7b-base-v1.5", trust_remote_code=True).cuda()
+input_text = "#write a quick sort algorithm"
+inputs = tokenizer(input_text, return_tensors="pt").cuda()
+outputs = model.generate(**inputs, max_length=128)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+### 4. License
+This code repository is licensed under the MIT License. The use of DeepSeek Coder models is subject to the Model License. DeepSeek Coder supports commercial use.
+
+See the [LICENSE-MODEL](https://github.com/deepseek-ai/deepseek-coder/blob/main/LICENSE-MODEL) for more details.
+
+### 5. Contact
+
+If you have any questions, please raise an issue or contact us at [[email protected]](mailto:[email protected]).

config.json

@@ -0,0 +1,100 @@
+{
+    "vocab_size": 102400,
+    "max_position_embeddings": 4096,
+    "hidden_size": 4096,
+    "intermediate_size": 11008,
+    "num_hidden_layers": 30,
+    "num_attention_heads": 32,
+    "num_key_value_heads": 32,
+    "hidden_act": "silu",
+    "initializer_range": 0.02,
+    "rms_norm_eps": 1e-06,
+    "pretraining_tp": 1,
+    "use_cache": true,
+    "rope_theta": 10000.0,
+    "rope_scaling": null,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "torch_dtype": "float16",
+    "tie_word_embeddings": false,
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "bos_token_id": 100000,
+    "eos_token_id": 100001,
+    "_name_or_path": "deepseek-ai/deepseek-coder-7b-base-v1.5",
+    "transformers_version": "4.38.2",
+    "model_type": "llama",
+    "quantization_config": {
+        "quant_method": "aqlm",
+        "nbits_per_codebook": 16,
+        "num_codebooks": 1,
+        "out_group_size": 1,
+        "in_group_size": 8,
+        "linear_weights_not_to_quantize": [
+            "model.layers.0.input_layernorm.weight",
+            "model.layers.0.post_attention_layernorm.weight",
+            "model.layers.1.input_layernorm.weight",
+            "model.layers.1.post_attention_layernorm.weight",
+            "model.layers.2.input_layernorm.weight",
+            "model.layers.2.post_attention_layernorm.weight",
+            "model.layers.3.input_layernorm.weight",
+            "model.layers.3.post_attention_layernorm.weight",
+            "model.layers.4.input_layernorm.weight",
+            "model.layers.4.post_attention_layernorm.weight",
+            "model.layers.5.input_layernorm.weight",
+            "model.layers.5.post_attention_layernorm.weight",
+            "model.layers.6.input_layernorm.weight",
+            "model.layers.6.post_attention_layernorm.weight",
+            "model.layers.7.input_layernorm.weight",
+            "model.layers.7.post_attention_layernorm.weight",
+            "model.layers.8.input_layernorm.weight",
+            "model.layers.8.post_attention_layernorm.weight",
+            "model.layers.9.input_layernorm.weight",
+            "model.layers.9.post_attention_layernorm.weight",
+            "model.layers.10.input_layernorm.weight",
+            "model.layers.10.post_attention_layernorm.weight",
+            "model.layers.11.input_layernorm.weight",
+            "model.layers.11.post_attention_layernorm.weight",
+            "model.layers.12.input_layernorm.weight",
+            "model.layers.12.post_attention_layernorm.weight",
+            "model.layers.13.input_layernorm.weight",
+            "model.layers.13.post_attention_layernorm.weight",
+            "model.layers.14.input_layernorm.weight",
+            "model.layers.14.post_attention_layernorm.weight",
+            "model.layers.15.input_layernorm.weight",
+            "model.layers.15.post_attention_layernorm.weight",
+            "model.layers.16.input_layernorm.weight",
+            "model.layers.16.post_attention_layernorm.weight",
+            "model.layers.17.input_layernorm.weight",
+            "model.layers.17.post_attention_layernorm.weight",
+            "model.layers.18.input_layernorm.weight",
+            "model.layers.18.post_attention_layernorm.weight",
+            "model.layers.19.input_layernorm.weight",
+            "model.layers.19.post_attention_layernorm.weight",
+            "model.layers.20.input_layernorm.weight",
+            "model.layers.20.post_attention_layernorm.weight",
+            "model.layers.21.input_layernorm.weight",
+            "model.layers.21.post_attention_layernorm.weight",
+            "model.layers.22.input_layernorm.weight",
+            "model.layers.22.post_attention_layernorm.weight",
+            "model.layers.23.input_layernorm.weight",
+            "model.layers.23.post_attention_layernorm.weight",
+            "model.layers.24.input_layernorm.weight",
+            "model.layers.24.post_attention_layernorm.weight",
+            "model.layers.25.input_layernorm.weight",
+            "model.layers.25.post_attention_layernorm.weight",
+            "model.layers.26.input_layernorm.weight",
+            "model.layers.26.post_attention_layernorm.weight",
+            "model.layers.27.input_layernorm.weight",
+            "model.layers.27.post_attention_layernorm.weight",
+            "model.layers.28.input_layernorm.weight",
+            "model.layers.28.post_attention_layernorm.weight",
+            "model.layers.29.input_layernorm.weight",
+            "model.layers.29.post_attention_layernorm.weight",
+            "model.embed_tokens.weight",
+            "model.norm.weight",
+            "lm_head.weight"
+        ]
+    }
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 100000,
+  "eos_token_id": 100001,
+  "transformers_version": "4.35.2"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f17a472bfe01e384e377b26ca4b5b24301da7f06414398c5ae55d555ad4f589c
+size 3419025758

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|EOT|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sp_model_kwargs": {},
+  "unk_token": null,
+  "tokenizer_class": "LlamaTokenizerFast"
+}