Create README.md

README.md

@@ -0,0 +1,596 @@
+---
+library_name: transformers
+language:
+- en
+- fr
+- it
+- pt
+- hi
+- es
+- th
+- de
+base_model:
+- meta-llama/Llama-3.1-70B-Instruct
+tags:
+- facebook
+- meta
+- pytorch
+- llama
+- llama-3
+- fp8
+- quantized
+license: llama3.3
+---
+
+# Llama-3.3-70B-Instruct-FP8-dynamic
+
+## Model Overview
+- **Model Architecture:** Meta-Llama-3.1
+  - **Input:** Text
+  - **Output:** Text
+- **Model Optimizations:**
+  - **Weight quantization:** FP8
+  - **Activation quantization:** FP8
+- **Intended Use Cases:** Intended for commercial and research use in multiple languages. Instruction tuned text only models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks. The Llama 3.3 model also supports the ability to leverage the outputs of its models to improve other models including synthetic data generation and distillation. The Llama 3.3 Community License allows for these use cases.
+- **Out-of-scope:** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3.3 Community License. Use in languages beyond English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai.
+- **Release Date:** 12/11/2024
+- **Version:** 1.0
+- **License(s):** llama3.3
+- **Model Developers:** RedHat (Neural Magic)
+
+### Model Optimizations
+
+This model was obtained by quantizing activation and weights of [Llama-3.3-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct) to FP8 data type.
+This optimization reduces the number of bits used to represent weights and activations from 16 to 8, reducing GPU memory requirements (by approximately 50%) and increasing matrix-multiply compute throughput (by approximately 2x).
+Weight quantization also reduces disk size requirements by approximately 50%.
+
+Only weights and activations of the linear operators within transformers blocks are quantized.
+Weights are quantized with a symmetric static per-channel scheme, whereas activations are quantized with a symmetric dynamic per-token scheme.
+The [llm-compressor](https://github.com/vllm-project/llm-compressor) library is used for quantization.
+
+## Deployment
+
+This model can be deployed efficiently using the [vLLM](https://docs.vllm.ai/en/latest/) backend, as shown in the example below.
+
+```python
+from vllm import LLM, SamplingParams
+from transformers import AutoTokenizer
+
+model_id = "neuralmagic-ent/phi-4-FP8-dynamic"
+number_gpus = 1
+
+sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+prompt = "Give me a short introduction to large language model."
+
+llm = LLM(model=model_id, tensor_parallel_size=number_gpus)
+
+outputs = llm.generate(prompt, sampling_params)
+
+generated_text = outputs[0].outputs[0].text
+print(generated_text)
+```
+
+vLLM aslo supports OpenAI-compatible serving. See the [documentation](https://docs.vllm.ai/en/latest/) for more details.
+
+## Creation
+
+<details>
+  <summary>Creation details</summary>
+  This model was created with [llm-compressor](https://github.com/vllm-project/llm-compressor) by running the code snippet below. 
+
+
+  ```python
+  from transformers import AutoModelForCausalLM, AutoTokenizer
+  from llmcompressor.modifiers.quantization import QuantizationModifier
+  from llmcompressor.transformers import oneshot
+  
+  # Load model
+  model_stub = "meta-llama/Llama-3.3-70B-Instruct"
+  model_name = model_stub.split("/")[-1]
+  
+  tokenizer = AutoTokenizer.from_pretrained(model_stub)
+  
+  model = AutoModelForCausalLM.from_pretrained(
+      model_stub,
+      device_map="auto",
+      torch_dtype="auto",
+  )
+  
+  # Configure the quantization algorithm and scheme
+  recipe = QuantizationModifier(
+      targets="Linear",
+      scheme="FP8_dynamic",
+      ignore=["lm_head"],
+  )
+  
+  # Apply quantization
+  oneshot(
+      model=model,
+      recipe=recipe,
+  )
+  
+  # Save to disk in compressed-tensors format
+  save_path = model_name + "-FP8-dynamic"
+  model.save_pretrained(save_path)
+  tokenizer.save_pretrained(save_path)
+  print(f"Model and tokenizer saved to: {save_path}")
+  ```
+</details>
+
+## Evaluation
+
+This model was evaluated on the well-known OpenLLM v1, OpenLLM v2, HumanEval, and HumanEval+ benchmarks.
+In all cases, model outputs were generated with the [vLLM](https://docs.vllm.ai/en/stable/) engine.
+
+OpenLLM v1 and v2 evaluations were conducted using [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness) and the prompting style of [Meta-Llama-3.1-Instruct-evals](https://huggingface.co/datasets/meta-llama/Meta-Llama-3.1-8B-Instruct-evals) when available.
+
+HumanEval and HumanEval+ evaluations were conducted using Neural Magic's fork of the [EvalPlus](https://github.com/neuralmagic/evalplus) repository.
+
+<details>
+  <summary>Evaluation details</summary>
+
+  **MMLU**
+  ```
+  lm_eval \
+    --model vllm \
+    --model_args pretrained="neuralmagic-ent/Llama-3.3-70B-Instruct-FP8-dynamic",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
+    --tasks mmlu_llama \
+    --fewshot_as_multiturn \
+    --apply_chat_template \
+    --num_fewshot 5 \
+    --batch_size auto
+  ```
+
+  **MMLU-CoT**
+  ```
+  lm_eval \
+    --model vllm \
+    --model_args pretrained="neuralmagic-ent/Llama-3.3-70B-Instruct-FP8-dynamic",dtype=auto,max_model_len=4064,max_gen_toks=1024,tensor_parallel_size=1 \
+    --tasks mmlu_cot_llama \
+    --apply_chat_template \
+    --num_fewshot 0 \
+    --batch_size auto
+  ```
+
+  **ARC-Challenge**
+  ```
+  lm_eval \
+    --model vllm \
+    --model_args pretrained="neuralmagic-ent/Llama-3.3-70B-Instruct-FP8-dynamic",dtype=auto,max_model_len=3940,max_gen_toks=100,tensor_parallel_size=1 \
+    --tasks arc_challenge_llama \
+    --apply_chat_template \
+    --num_fewshot 0 \
+    --batch_size auto
+  ```
+
+  **GSM-8K**
+  ```
+  lm_eval \
+    --model vllm \
+    --model_args pretrained="neuralmagic-ent/Llama-3.3-70B-Instruct-FP8-dynamic",dtype=auto,max_model_len=4096,max_gen_toks=1024,tensor_parallel_size=1 \
+    --tasks gsm8k_llama \
+    --fewshot_as_multiturn \
+    --apply_chat_template \
+    --num_fewshot 8 \
+    --batch_size auto
+  ```
+
+  **Hellaswag**
+  ```
+  lm_eval \
+    --model vllm \
+    --model_args pretrained="neuralmagic-ent/Llama-3.3-70B-Instruct-FP8-dynamic",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \
+    --tasks hellaswag \
+    --num_fewshot 10 \
+    --batch_size auto
+  ```
+
+  **Winogrande**
+  ```
+  lm_eval \
+    --model vllm \
+    --model_args pretrained="neuralmagic-ent/Llama-3.3-70B-Instruct-FP8-dynamic",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \
+    --tasks winogrande \
+    --num_fewshot 5 \
+    --batch_size auto
+  ```
+
+  **TruthfulQA**
+  ```
+  lm_eval \
+    --model vllm \
+    --model_args pretrained="neuralmagic-ent/Llama-3.3-70B-Instruct-FP8-dynamic",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \
+    --tasks truthfulqa \
+    --num_fewshot 0 \
+    --batch_size auto
+  ```
+
+  **OpenLLM v2**
+  ```
+  lm_eval \
+    --model vllm \
+    --model_args pretrained="neuralmagic-ent/Llama-3.3-70B-Instruct-FP8-dynamic",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
+    --apply_chat_template \
+    --fewshot_as_multiturn \
+    --tasks leaderboard \
+    --batch_size auto
+  ```
+
+  **MMLU Portuguese**
+  ```
+  lm_eval \
+    --model vllm \
+    --model_args pretrained="neuralmagic-ent/Llama-3.3-70B-Instruct-FP8-dynamic",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
+    --tasks mmlu_pt_llama \
+    --fewshot_as_multiturn \
+    --apply_chat_template \
+    --num_fewshot 5 \
+    --batch_size auto
+  ```
+
+  **MMLU Spanish**
+  ```
+  lm_eval \
+    --model vllm \
+    --model_args pretrained="neuralmagic-ent/Llama-3.3-70B-Instruct-FP8-dynamic",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
+    --tasks mmlu_es_llama \
+    --fewshot_as_multiturn \
+    --apply_chat_template \
+    --num_fewshot 5 \
+    --batch_size auto
+  ```
+
+  **MMLU Italian**
+  ```
+  lm_eval \
+    --model vllm \
+    --model_args pretrained="neuralmagic-ent/Llama-3.3-70B-Instruct-FP8-dynamic",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
+    --tasks mmlu_it_llama \
+    --fewshot_as_multiturn \
+    --apply_chat_template \
+    --num_fewshot 5 \
+    --batch_size auto
+  ```
+
+  **MMLU German**
+  ```
+  lm_eval \
+    --model vllm \
+    --model_args pretrained="neuralmagic-ent/Llama-3.3-70B-Instruct-FP8-dynamic",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
+    --tasks mmlu_de_llama \
+    --fewshot_as_multiturn \
+    --apply_chat_template \
+    --num_fewshot 5 \
+    --batch_size auto
+  ```
+
+  **MMLU French**
+  ```
+  lm_eval \
+    --model vllm \
+    --model_args pretrained="neuralmagic-ent/Llama-3.3-70B-Instruct-FP8-dynamic",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
+    --tasks mmlu_fr_llama \
+    --fewshot_as_multiturn \
+    --apply_chat_template \
+    --num_fewshot 5 \
+    --batch_size auto
+  ```
+
+  **MMLU Hindi**
+  ```
+  lm_eval \
+    --model vllm \
+    --model_args pretrained="neuralmagic-ent/Llama-3.3-70B-Instruct-FP8-dynamic",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
+    --tasks mmlu_hi_llama \
+    --fewshot_as_multiturn \
+    --apply_chat_template \
+    --num_fewshot 5 \
+    --batch_size auto
+  ```
+
+  **MMLU Thai**
+  ```
+  lm_eval \
+    --model vllm \
+    --model_args pretrained="neuralmagic-ent/Llama-3.3-70B-Instruct-FP8-dynamic",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \
+    --tasks mmlu_th_llama \
+    --fewshot_as_multiturn \
+    --apply_chat_template \
+    --num_fewshot 5 \
+    --batch_size auto
+  ```
+
+  **HumanEval and HumanEval+**
+  *Generation*
+  ```
+  python3 codegen/generate.py \
+    --model neuralmagic-ent/Llama-3.3-70B-Instruct-FP8-dynamic \
+    --bs 16 \
+    --temperature 0.2 \
+    --n_samples 50 \
+    --root "." \
+    --dataset humaneval
+  ```
+
+  *Sanitization*
+  ```
+  python3 evalplus/sanitize.py \
+    humaneval/neuralmagic-ent--Llama-3.3-70B-Instruct-FP8-dynamic_vllm_temp_0.2
+  ```
+
+  *Evaluation*
+  ```
+  evalplus.evaluate \
+    --dataset humaneval \
+    --samples humaneval/neuralmagic-ent--Llama-3.3-70B-Instruct-FP8-dynamic_vllm_temp_0.2-sanitized
+  ```
+
+### Accuracy
+
+<table>
+  <tr>
+   <th>Category
+   </th>
+   <th>Benchmark
+   </th>
+   <th>Llama-3.3-70B-Instruct
+   </th>
+   <th>Llama-3.3-70B-Instruct-FP8-dynamic<br>(this model)
+   </th>
+   <th>Recovery
+   </th>
+  </tr>
+  <tr>
+   <td rowspan="8" ><strong>OpenLLM v1</strong>
+   </td>
+   <td>MMLU (5-shot)
+   </td>
+   <td>81.60
+   </td>
+   <td>81.31
+   </td>
+   <td>99.6%
+   </td>
+  </tr>
+  <tr>
+   <td>MMLU (CoT, 0-shot)
+   </td>
+   <td>86.58
+   </td>
+   <td>86.34
+   </td>
+   <td>99.7%
+   </td>
+  </tr>
+  <tr>
+   <td>ARC Challenge (0-shot)
+   </td>
+   <td>49.23
+   </td>
+   <td>51.96
+   </td>
+   <td>105.6%
+   </td>
+  </tr>
+  <tr>
+   <td>GSM-8K (CoT, 8-shot, strict-match)
+   </td>
+   <td>94.16
+   </td>
+   <td>94.92
+   </td>
+   <td>100.8%
+   </td>
+  </tr>
+  <tr>
+   <td>Hellaswag (10-shot)
+   </td>
+   <td>86.49
+   </td>
+   <td>86.43
+   </td>
+   <td>99.9%
+   </td>
+  </tr>
+  <tr>
+   <td>Winogrande (5-shot)
+   </td>
+   <td>84.77
+   </td>
+   <td>84.53
+   </td>
+   <td>99.7%
+   </td>
+  </tr>
+  <tr>
+   <td>TruthfulQA (0-shot, mc2)
+   </td>
+   <td>62.75
+   </td>
+   <td>63.21
+   </td>
+   <td>100.7%
+   </td>
+  </tr>
+  <tr>
+   <td><strong>Average</strong>
+   </td>
+   <td><strong>77.94</strong>
+   </td>
+   <td><strong>78.39</strong>
+   </td>
+   <td><strong>100.6%</strong>
+   </td>
+  </tr>
+  <tr>
+   <td rowspan="7" ><strong>OpenLLM v2</strong>
+   </td>
+   <td>MMLU-Pro (5-shot)
+   </td>
+   <td>51.89
+   </td>
+   <td>51.50
+   </td>
+   <td>99.3%
+   </td>
+  </tr>
+  <tr>
+   <td>IFEval (0-shot)
+   </td>
+   <td>90.89
+   </td>
+   <td>90.92
+   </td>
+   <td>100.0%
+   </td>
+  </tr>
+  <tr>
+   <td>BBH (3-shot)
+   </td>
+   <td>63.15
+   </td>
+   <td>62.84
+   </td>
+   <td>99.5%
+   </td>
+  </tr>
+  <tr>
+   <td>Math-lvl-5 (4-shot)
+   </td>
+   <td>0.17
+   </td>
+   <td>0.33
+   </td>
+   <td>N/A
+   </td>
+  </tr>
+  <tr>
+   <td>GPQA (0-shot)
+   </td>
+   <td>46.10
+   </td>
+   <td>46.30
+   </td>
+   <td>100.4%
+   </td>
+  </tr>
+  <tr>
+   <td>MuSR (0-shot)
+   </td>
+   <td>44.35
+   </td>
+   <td>43.96
+   </td>
+   <td>99.1%
+   </td>
+  </tr>
+  <tr>
+   <td><strong>Average</strong>
+   </td>
+   <td><strong>49.42</strong>
+   </td>
+   <td><strong>49.31</strong>
+   </td>
+   <td><strong>99.8%</strong>
+   </td>
+  </tr>
+  <tr>
+   <td rowspan="2" ><strong>Coding</strong>
+   </td>
+   <td>HumanEval pass@1
+   </td>
+   <td>83.20
+   </td>
+   <td>83.70
+   </td>
+   <td>100.6%
+   </td>
+  </tr>
+  <tr>
+   <td>HumanEval+ pass@1
+   </td>
+   <td>78.40
+   </td>
+   <td>78.70
+   </td>
+   <td>100.4%
+   </td>
+  </tr>
+  <tr>
+   <td rowspan="9" ><strong>Multilingual</strong>
+   </td>
+   <td>Portuguese MMLU (5-shot)
+   </td>
+   <td>79.76
+   </td>
+   <td>79.75
+   </td>
+   <td>100.0%
+   </td>
+  </tr>
+  <tr>
+   <td>Spanish MMLU (5-shot)
+   </td>
+   <td>79.33
+   </td>
+   <td>79.17
+   </td>
+   <td>99.8%
+   </td>
+  </tr>
+  <tr>
+   <td>Italian MMLU (5-shot)
+   </td>
+   <td>79.15
+   </td>
+   <td>78.84
+   </td>
+   <td>99.6%
+   </td>
+  </tr>
+  <tr>
+   <td>German MMLU (5-shot)
+   </td>
+   <td>77.94
+   </td>
+   <td>77.95
+   </td>
+   <td>100.0%
+   </td>
+  </tr>
+  <tr>
+   <td>French MMLU (5-shot)
+   </td>
+   <td>75.69
+   </td>
+   <td>75.45
+   </td>
+   <td>99.7%
+   </td>
+  </tr>
+  <tr>
+   <td>Hindi MMLU (5-shot)
+   </td>
+   <td>73.81
+   </td>
+   <td>73.71
+   </td>
+   <td>99.9%
+   </td>
+  </tr>
+  <tr>
+   <td>Thai MMLU (5-shot)
+   </td>
+   <td>71.98
+   </td>
+   <td>71.77
+   </td>
+   <td>99.7%
+   </td>
+  </tr>
+</table>
+
+