Upload folder using huggingface_hub

README.md

@@ -0,0 +1,186 @@
+---
+tags:
+- fp8
+- vllm
+license: other
+license_name: deepseek-license
+license_link: https://github.com/deepseek-ai/DeepSeek-Coder-V2/blob/main/LICENSE-MODEL
+---
+
+# DeepSeek-Coder-V2-Instruct-FP8
+
+## Model Overview
+- **Model Architecture:** DeepSeek-Coder-V2-Instruct
+  - **Input:** Text
+  - **Output:** Text
+- **Model Optimizations:**
+  - **Weight quantization:** FP8
+  - **Activation quantization:** FP8
+- **Intended Use Cases:** Intended for commercial and research use in English. Similarly to [Meta-Llama-3-7B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-7B-Instruct), this models is intended for assistant-like chat.
+- **Out-of-scope:** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in languages other than English.
+- **Release Date:** 7/22/2024
+- **Version:** 1.0
+- **License(s):** [deepseek-license](https://github.com/deepseek-ai/DeepSeek-Coder-V2/blob/main/LICENSE-MODEL)
+- **Model Developers:** Neural Magic
+
+Quantized version of [DeepSeek-Coder-V2-Instruct](https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Instruct).
+<!-- It achieves an average score of 73.19 on the [OpenLLM](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) benchmark (version 1), whereas the unquantized model achieves 73.48. -->
+It achieves an average score of 88.98 on the [HumanEval+](https://github.com/openai/human-eval?tab=readme-ov-file) benchmark, whereas the unquantized model achieves 87.63.
+
+### Model Optimizations
+
+This model was obtained by quantizing the weights and activations of [DeepSeek-Coder-V2-Instruct](https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Instruct) to FP8 data type, ready for inference with vLLM >= 0.5.2.
+This optimization reduces the number of bits per parameter from 16 to 8, reducing the disk size and GPU memory requirements by approximately 50%. In particular, this model can now be loaded and evaluated with only 4xH100 GPUs, as opposed to 8.
+
+Only the weights and activations of the linear operators within transformers blocks are quantized. Symmetric per-tensor quantization is applied, in which a single linear scaling maps the FP8 representations of the quantized weights and activations.
+[AutoFP8](https://github.com/neuralmagic/AutoFP8) is used for quantization with 512 sequences of UltraChat.
+
+## Deployment
+
+### Use with vLLM
+
+This model can be deployed efficiently using the [vLLM](https://docs.vllm.ai/en/latest/) backend, as shown in the example below.
+
+```python
+from transformers import AutoTokenizer
+from vllm import LLM, SamplingParams
+
+max_model_len, tp_size = 4096, 4
+model_name = "neuralmagic/DeepSeek-Coder-V2-Instruct-FP8"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+llm = LLM(model=model_name, tensor_parallel_size=tp_size, max_model_len=max_model_len, trust_remote_code=True, enforce_eager=True)
+sampling_params = SamplingParams(temperature=0.3, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
+
+messages_list = [
+    [{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
+]
+
+prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]
+
+outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)
+
+generated_text = [output.outputs[0].text for output in outputs]
+print(generated_text)
+```
+
+vLLM aslo supports OpenAI-compatible serving. See the [documentation](https://docs.vllm.ai/en/latest/) for more details.
+
+## Creation
+
+This model was created by applying [AutoFP8 with calibration samples from ultrachat](https://github.com/neuralmagic/AutoFP8/blob/147fa4d9e1a90ef8a93f96fc7d9c33056ddc017a/example_dataset.py) with expert gates kept at original precision, as presented in the code snipet below.
+Notably, a custom device map had to be used, as the model was being incorrectly loaded otherwise.
+Although AutoFP8 was used for this particular model, Neural Magic is transitioning to using [llm-compressor](https://github.com/vllm-project/llm-compressor) which supports several quantization schemes and models not supported by AutoFP8.
+
+```python
+from datasets import load_dataset
+from transformers import AutoTokenizer
+
+from auto_fp8 import AutoFP8ForCausalLM, BaseQuantizeConfig
+
+pretrained_model_dir = "deepseek-ai/DeepSeek-Coder-V2-Instruct"
+quantized_model_dir = "DeepSeek-Coder-V2-Instruct-FP8"
+
+tokenizer = AutoTokenizer.from_pretrained(pretrained_model_dir, use_fast=True, model_max_length=4096)
+tokenizer.pad_token = tokenizer.eos_token
+
+ds = load_dataset("mgoin/ultrachat_2k", split="train_sft").select(range(512))
+examples = [tokenizer.apply_chat_template(batch["messages"], tokenize=False) for batch in ds]
+examples = tokenizer(examples, padding=True, truncation=True, return_tensors="pt").to("cuda")
+
+quantize_config = BaseQuantizeConfig(
+    quant_method="fp8",
+    activation_scheme="static"
+    ignore_patterns=["re:.*lm_head"],
+)
+
+device_map = {
+    "model.embed_tokens": 0,
+    "model.layers.0": 0,
+}
+for i in range(1, 60):
+    device_map[f"model.layers.{i}"] = i//8
+
+device_map["model.norm"] = 7
+device_map["lm_head"] = 7
+
+model = AutoFP8ForCausalLM.from_pretrained(
+    pretrained_model_dir, quantize_config=quantize_config, device_map = device_map
+)
+model.quantize(examples)
+model.save_quantized(quantized_model_dir)
+```
+
+## Evaluation
+
+The model was evaluated on the [HumanEval+](https://github.com/openai/human-eval?tab=readme-ov-file) benchmark with the [Neural Magic fork](https://github.com/neuralmagic/evalplus) of the [EvalPlus implementation of HumanEval+](https://github.com/evalplus/evalplus) and the [vLLM](https://docs.vllm.ai/en/stable/) engine, using the following command:
+```
+python codegen/generate.py --model neuralmagic/DeepSeek-Coder-V2-Instruct-FP8 --temperature 0.2 --n_samples 50 --resume --root ~ --dataset humaneval
+python evalplus/sanitize.py ~/humaneval/neuralmagic--DeepSeek-Coder-V2-Instruct-FP8_vllm_temp_0.2
+evalplus.evaluate --dataset humaneval --samples ~/humaneval/neuralmagic--DeepSeek-Coder-V2-Instruct-FP8_vllm_temp_0.2-sanitized
+```
+
+### Accuracy
+
+#### HumanEval+ evaluation scores
+<table>
+  <tr>
+   <td><strong>Benchmark</strong>
+   </td>
+   <td><strong>DeepSeek-Coder-V2-Instruct</strong>
+   </td>
+   <td><strong>DeepSeek-Coder-V2-Instruct-FP8(this model)</strong>
+   </td>
+   <td><strong>Recovery</strong>
+   </td>
+  </tr>
+  <tr>
+   <td>base pass@1
+   </td>
+   <td>88.2
+   </td>
+   <td>87.6
+   </td>
+   <td>99.32%
+   </td>
+  </tr>
+  <tr>
+   <td>base pass@10
+   </td>
+   <td>92.3
+   </td>
+   <td>94.7
+   </td>
+   <td>102.60%
+   </td>
+  </tr>
+  <tr>
+   <td>base+extra pass@1
+   </td>
+   <td>83.3
+   </td>
+   <td>83.2
+   </td>
+   <td>99.88%
+   </td>
+  </tr>
+  <tr>
+   <td>base+extra pass@10
+   </td>
+   <td>86.7
+   </td>
+   <td>90.4
+   </td>
+   <td>104.27%
+   </td>
+  </tr>
+  <tr>
+   <td><strong>Average</strong>
+   </td>
+   <td><strong>87.63</strong>
+   </td>
+   <td><strong>88.98</strong>
+   </td>
+   <td><strong>101.5%</strong>
+   </td>
+  </tr>
+</table>

config.json

@@ -0,0 +1,68 @@
+{
+  "_name_or_path": "deepseek-ai/DeepSeek-Coder-V2-Instruct",
+  "architectures": [
+    "DeepseekV2ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "deepseek-ai/DeepSeek-Coder-V2-Instruct--configuration_deepseek.DeepseekV2Config",
+    "AutoModel": "deepseek-ai/DeepSeek-Coder-V2-Instruct--modeling_deepseek.DeepseekV2Model",
+    "AutoModelForCausalLM": "deepseek-ai/DeepSeek-Coder-V2-Instruct--modeling_deepseek.DeepseekV2ForCausalLM"
+  },
+  "aux_loss_alpha": 0.001,
+  "bos_token_id": 100000,
+  "eos_token_id": 100001,
+  "ep_size": 1,
+  "first_k_dense_replace": 1,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "kv_lora_rank": 512,
+  "max_position_embeddings": 163840,
+  "model_type": "deepseek_v2",
+  "moe_intermediate_size": 1536,
+  "moe_layer_freq": 1,
+  "n_group": 8,
+  "n_routed_experts": 160,
+  "n_shared_experts": 2,
+  "norm_topk_prob": false,
+  "num_attention_heads": 128,
+  "num_experts_per_tok": 6,
+  "num_hidden_layers": 60,
+  "num_key_value_heads": 128,
+  "pretraining_tp": 1,
+  "q_lora_rank": 1536,
+  "qk_nope_head_dim": 128,
+  "qk_rope_head_dim": 64,
+  "quantization_config": {
+    "activation_scheme": "static",
+    "ignored_layers": [
+      "lm_head"
+    ],
+    "quant_method": "fp8"
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "beta_fast": 32,
+    "beta_slow": 1,
+    "factor": 40,
+    "mscale": 1.0,
+    "mscale_all_dim": 1.0,
+    "original_max_position_embeddings": 4096,
+    "type": "yarn"
+  },
+  "rope_theta": 10000,
+  "routed_scaling_factor": 16.0,
+  "scoring_func": "softmax",
+  "seq_aux": true,
+  "tie_word_embeddings": false,
+  "topk_group": 3,
+  "topk_method": "group_limited_greedy",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.4",
+  "use_cache": true,
+  "v_head_dim": 128,
+  "vocab_size": 102400
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 100000,
+  "do_sample": true,
+  "eos_token_id": 100001,
+  "temperature": 0.3,
+  "top_p": 0.95,
+  "transformers_version": "4.42.4"
+}

model-00001-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8000e9949b4fd962ddbbb4eb3557eb0d04df40316ca4158b83cc34689890e631
+size 4996259528

model-00002-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afc58e048af69b21ccfaf196807266d68ba44616934aa74fe42f1571b2b98ed9
+size 4996987640

model-00003-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64fd5150522ae8c39273c109536d51d1f62857699942e07db90829b4e7d8c780
+size 4995526672

model-00004-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ade4c7a3483b6905e30117258a396367564951c1036795a4aeaa03358c46290
+size 4995526744

model-00005-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97e620157534c9850258ce5fb5418f9462e04a3354211238468e38a6cba2adeb
+size 4995527056

model-00006-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5d847d51f72bfa006b33a96ba231b3dfd0f19104fc66bb4968cb05743ea6d07
+size 4996987592

model-00007-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddb0e51292e95d1a59ad4aefcef962147c87802421fcf10a551b4afa898e00b5
+size 4995526672

model-00008-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a73e074ca5b57ccac8d2ff37b3b0f2457692feba684a46413b4e4711a1cd9aa
+size 4995527816

model-00009-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e66ca1b356a24133cba9cbbd61044e1388814faf8b5c9ec4f8ce01f070d59bff
+size 4995528912

model-00010-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e13ec513877839ff246492556f8b077704d8cbdba49d245d0abc00a5184927ca
+size 4996989368

model-00011-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02a1f43fa8c8f14a41b62a107a1ca40ce40a3558a71198416d00a460cb6b8b4c
+size 4995528528

model-00012-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ceeeeebdbf0333b112f8a346442da49312084c62a72f520765aa88c315749b7
+size 4995528696

model-00013-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4daa7499e1465313cceaae358458f40bca747e7047fba3763a90e9998d9f695
+size 4989302048

model-00014-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c7ae17d52b41f004331c54e1445127d7e3853b995fd6a982274ad0a658efd75
+size 4995351504

model-00015-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dde785a9b394a2d0842add9d869a59bf53c71909b2138b398061f0bfa259e5da
+size 4995528528

model-00016-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15768a4063205ab4af23981e4f09bd76733e209d92ca051dcfb94290722e50ea
+size 4995528736

model-00017-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a0dac72f27ac03e8d2b90ff9fbbbb9eb66dc9624711f29d5fd858462ec5017e
+size 4960291384

model-00018-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0f42c1ad70f04521ea015fad81204a8a5a2c790b3dffa801a03635fc7bf7dda
+size 4992903432

model-00019-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5451aa06f5079146ef7d2fd3dc398d7424e5d6d112899a2b5d2699ec0cbc77cc
+size 4995528528

model-00020-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eac491013508877af3d44a49679c5694f1fcb1ffc435304bd40f5e31995980b3
+size 4995528768

model-00021-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:127dce81a6ac7b9cf80f6b9b66b272aa0ec4d08fbef32d4d0daaf2cdbc2e1ba7
+size 4996989712

model-00022-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e8157545e78a9078234a5b6bc4c19b84cbee2c57d1c8aca93e1930157449589
+size 4995528448

model-00023-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9682308a785e38dc5ad45eee0236afcf4c951df198ef57d18403dc9c3c6276fb
+size 4995528528

model-00024-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5afc314499d2375d9557115fd0b8ed5d0be388554d25fd9c47ce08ff555b548
+size 4995528816

model-00025-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd1151986e1faec0a4bdb084f8356d9bc9133659b5027e5f00d4e46bb1a678d3
+size 4996989624

model-00026-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10149a53f3ab21d3ffa46a78fb50326bb65172959ad38efbf1eddb7805113eaa
+size 4995528488

model-00027-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c86e9ce223632a20fdebd45f74531a4d2b255857cd79e9dc7166f21cd48cb5d6
+size 4995528528

model-00028-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95e32b9b816ef5943908c7f2d6513dae5d8b2945ab874cacbaae9e9945d2b888
+size 4995528856

model-00029-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3df0e4ea67306a6b593044f58496f70ae4f988fd3b4b61145d407866c1d5fe6
+size 4996989544

model-00030-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:775a5d2221149e7da8132a9a2cbc7550311f4f9bf5aeeeb477d9e8b099934ac5
+size 4995528528

model-00031-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06679cf3f9f2f3ed58e48ceb3d2d0116365e132b5e2d9214eb914a2f2ea5c638
+size 4995528528

model-00032-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae73b4fabdced0fddbd7d9d0fae2fa432b55d4e70341b6369f2629dca5100c7f
+size 4995528904

model-00033-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:171827c7f4793c100641c235cd8966cd779e11a84a4bba29b3c9270e089e0cd0
+size 4996989504

model-00034-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35cb341b2f86495fd8c8dc67c9e7705efc8ede904fecc61167003c9a6d532329
+size 4995528528

model-00035-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e0e5e76f179390df5276a495a0cd07a840d0b65e92942bef511b75984cd7acf
+size 4995528560

model-00036-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b721899f02e1a8261204467642c89d84c066b82fde1b954c8ffbe6094e390d6e
+size 4995528920

model-00037-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b642144cd419a92f0c8aa43ab0443be6fecb698b41ac32f44d083ec7a548b0c
+size 4996989456

model-00038-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:246973a6c25d2554c474343dab2b7845d7e617a3d5524734fcf504680b716c53
+size 4995528528

model-00039-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f6876fcd793fe16c644034221084b4c4f7248f9c2e15edaf4abaf4845442384
+size 4995528600

model-00040-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:764fe67f93eb623e33704f17ca6e215e230954472d2bf981e9e85095e09c4226
+size 4995528920

model-00041-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a80098037868115f9917e9e6769a4ccda8cd4e707522aa7fd2ed6e1244a04b0
+size 4996989408

model-00042-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86e8a05d26e3c17e9e23f0354b28919722ac5432e45a91cb7c605235ff4e1f4f
+size 4995528528

model-00043-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c98a7db0721abc363a4091a3a3101278bae647a82ca0ab968272bee24e0b3deb
+size 4995528648

model-00044-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0046833ff80ef2fcb27d99c7d274205beba3bd4892a1d7217385085e5477601
+size 4995528920

model-00045-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79df5fbd6b911d35cdcfb92e869b2203232c3826c19c8868f620997990e3e8b6
+size 4996989368

model-00046-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c38c6a890754e4a7aad78186548a31a382d3f2f1cdaa4101cba2de3f5e7b60c1
+size 4995528528

model-00047-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c9da3ec73db485e9353ce6d2deda806716b30e63f006761eacec995fccabbe0
+size 4995528696