commit 3e47283496139a28003ac23826c577d455b2e37f Author: ModelHub XC Date: Tue Oct 6 03:55:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: RedHatAI/Llama-3.3-70B-Instruct-quantized.w8a8 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt 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 +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz 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 +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl 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 +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* 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 +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..832d6c7 --- /dev/null +++ b/README.md @@ -0,0 +1,786 @@ +--- +language: +- en +- de +- fr +- it +- pt +- hi +- es +- th +base_model: +- meta-llama/Llama-3.3-70B-Instruct +pipeline_tag: text-generation +tags: +- llama +- facebook +- meta +- llama-3 +- int8 +- vllm +- chat +- neuralmagic +- llmcompressor +- conversational +- 8-bit precision +- compressed-tensors +license: llama3.3 +license_name: llama3.3 +name: RedHatAI/Llama-3.3-70B-Instruct-quantized.w8a8 +description: This model was obtained by quantizing the weights and activations of Llama-3.3-70B-Instruct to INT8 data type. +readme: https://huggingface.co/RedHatAI/Llama-3.3-70B-Instruct-quantized.w8a8/main/README.md +tasks: +- text-to-text +provider: Meta +license_link: https://github.com/meta-llama/llama-models/blob/main/models/llama3_3/LICENSE +validated_on: + - RHOAI 2.20 + - RHAIIS 3.0 + - RHELAI 1.5 + - vLLM 0.8.4 +--- +

+ Llama-3.3-70B-Instruct-quantized.w8a8 + Model Icon +

+ + +Validated Badge + + +## Model Overview +- **Model Architecture:** Llama + - **Input:** Text + - **Output:** Text +- **Model Optimizations:** + - **Activation quantization:** INT8 + - **Weight quantization:** INT8 +- **Intended Use Cases:** Intended for commercial and research use multiple languages. Similarly to [Llama-3.3-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.3-70B-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). +- **Release Date:** 01/20/2025 +- **Version:** 1.0 +- **Validated on:** RHOAI 2.20, RHAIIS 3.0, RHELAI 1.5 +- **Model Developers:** Neural Magic + +Quantized version of [Llama-3.3-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct). +It was evaluated on a several tasks to assess the its quality in comparison to the unquatized model, including multiple-choice, math reasoning, and open-ended text generation. +Llama-3.3-70B-Instruct-quantized.w8a8 achieves 99.4% recovery for OpenLLM v1 (using Meta's prompting when available) and 100% for both HumanEval and HumanEval+ pass@1. + +### Model Optimizations + +This model was obtained by quantizing the weights and activations of [Llama-3.3-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct) to INT8 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, where a fixed linear scaling factor is applied between INT8 and floating point representations for each output channel dimension. +Activations are quantized with a symmetric dynamic per-token scheme, computing a linear scaling factor at runtime for each token between INT8 and floating point representations. + +## 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/Llama-3.3-70B-Instruct-quantized.w8a8" +number_gpus = 1 +max_model_len = 8192 + +sampling_params = SamplingParams(temperature=0.6, top_p=0.9, max_tokens=256) + +tokenizer = AutoTokenizer.from_pretrained(model_id) + +messages = [ + {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"}, + {"role": "user", "content": "Who are you?"}, +] + +prompts = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False) + +llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len) + +outputs = llm.generate(prompts, 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. + +
+ Deploy on Red Hat AI Inference Server + +```bash +podman run --rm -it --device nvidia.com/gpu=all -p 8000:8000 \ + --ipc=host \ +--env "HUGGING_FACE_HUB_TOKEN=$HF_TOKEN" \ +--env "HF_HUB_OFFLINE=0" -v ~/.cache/vllm:/home/vllm/.cache \ +--name=vllm \ +registry.access.redhat.com/rhaiis/rh-vllm-cuda \ +vllm serve \ +--tensor-parallel-size 8 \ +--max-model-len 32768 \ +--enforce-eager --model RedHatAI/Llama-3.3-70B-Instruct-quantized.w8a8 +``` +​​See [Red Hat AI Inference Server documentation](https://docs.redhat.com/en/documentation/red_hat_ai_inference_server/) for more details. +
+ +
+ Deploy on Red Hat Enterprise Linux AI + +```bash +# Download model from Red Hat Registry via docker +# Note: This downloads the model to ~/.cache/instructlab/models unless --model-dir is specified. +ilab model download --repository docker://registry.redhat.io/rhelai1/llama-3-3-70b-instruct-quantized-w8a8:1.5 +``` + +```bash +# Serve model via ilab +ilab model serve --model-path ~/.cache/instructlab/models/llama-3-3-70b-instruct-quantized-w8a8 + +# Chat with model +ilab model chat --model ~/.cache/instructlab/models/llama-3-3-70b-instruct-quantized-w8a8 +``` +See [Red Hat Enterprise Linux AI documentation](https://docs.redhat.com/en/documentation/red_hat_enterprise_linux_ai/1.4) for more details. +
+ +
+ Deploy on Red Hat Openshift AI + +```python +# Setting up vllm server with ServingRuntime +# Save as: vllm-servingruntime.yaml +apiVersion: serving.kserve.io/v1alpha1 +kind: ServingRuntime +metadata: + name: vllm-cuda-runtime # OPTIONAL CHANGE: set a unique name + annotations: + openshift.io/display-name: vLLM NVIDIA GPU ServingRuntime for KServe + opendatahub.io/recommended-accelerators: '["nvidia.com/gpu"]' + labels: + opendatahub.io/dashboard: 'true' +spec: + annotations: + prometheus.io/port: '8080' + prometheus.io/path: '/metrics' + multiModel: false + supportedModelFormats: + - autoSelect: true + name: vLLM + containers: + - name: kserve-container + image: quay.io/modh/vllm:rhoai-2.20-cuda # CHANGE if needed. If AMD: quay.io/modh/vllm:rhoai-2.20-rocm + command: + - python + - -m + - vllm.entrypoints.openai.api_server + args: + - "--port=8080" + - "--model=/mnt/models" + - "--served-model-name={{.Name}}" + env: + - name: HF_HOME + value: /tmp/hf_home + ports: + - containerPort: 8080 + protocol: TCP +``` + +```python +# Attach model to vllm server. This is an NVIDIA template +# Save as: inferenceservice.yaml +apiVersion: serving.kserve.io/v1beta1 +kind: InferenceService +metadata: + annotations: + openshift.io/display-name: llama-3-3-70b-instruct-quantized-w8a8 # OPTIONAL CHANGE + serving.kserve.io/deploymentMode: RawDeployment + name: llama-3-3-70b-instruct-quantized-w8a8 # specify model name. This value will be used to invoke the model in the payload + labels: + opendatahub.io/dashboard: 'true' +spec: + predictor: + maxReplicas: 1 + minReplicas: 1 + model: + modelFormat: + name: vLLM + name: '' + resources: + limits: + cpu: '2' # this is model specific + memory: 8Gi # this is model specific + nvidia.com/gpu: '1' # this is accelerator specific + requests: # same comment for this block + cpu: '1' + memory: 4Gi + nvidia.com/gpu: '1' + runtime: vllm-cuda-runtime # must match the ServingRuntime name above + storageUri: oci://registry.redhat.io/rhelai1/modelcar-llama-3-3-70b-instruct-quantized-w8a8:1.5 + tolerations: + - effect: NoSchedule + key: nvidia.com/gpu + operator: Exists +``` + +```bash +# make sure first to be in the project where you want to deploy the model +# oc project + +# apply both resources to run model + +# Apply the ServingRuntime +oc apply -f vllm-servingruntime.yaml + +# Apply the InferenceService +oc apply -f qwen-inferenceservice.yaml +``` + +```python +# Replace and below: +# - Run `oc get inferenceservice` to find your URL if unsure. + +# Call the server using curl: +curl https://-predictor-default./v1/chat/completions + -H "Content-Type: application/json" \ + -d '{ + "model": "llama-3-3-70b-instruct-quantized-w8a8 ", + "stream": true, + "stream_options": { + "include_usage": true + }, + "max_tokens": 1, + "messages": [ + { + "role": "user", + "content": "How can a bee fly when its wings are so small?" + } + ] +}' + +``` + +See [Red Hat Openshift AI documentation](https://docs.redhat.com/en/documentation/red_hat_openshift_ai/2025) for more details. +
+ + +## Creation + +This model was created by using the [llm-compressor](https://github.com/vllm-project/llm-compressor) library as presented in the code snipet below. + +```python +from transformers import AutoTokenizer, AutoModelForCausalLM +from datasets import Dataset +from llmcompressor.transformers import oneshot +from llmcompressor.modifiers.quantization import GPTQModifier +import random + +model_id = "meta-llama/Meta-Llama-3.1-8B-Instruct" + +num_samples = 1024 +max_seq_len = 8192 + +tokenizer = AutoTokenizer.from_pretrained(model_id) + +max_token_id = len(tokenizer.get_vocab()) - 1 +input_ids = [[random.randint(0, max_token_id) for _ in range(max_seq_len)] for _ in range(num_samples)] +attention_mask = num_samples * [max_seq_len * [1]] +ds = Dataset.from_dict({"input_ids": input_ids, "attention_mask": attention_mask}) + +recipe = GPTQModifier( + targets="Linear", + scheme="W8A8", + ignore=["lm_head"], + dampening_frac=0.01, +) + +model = SparseAutoModelForCausalLM.from_pretrained( + model_id, + device_map="auto", +) + +oneshot( + model=model, + dataset=ds, + recipe=recipe, + max_seq_length=max_seq_len, + num_calibration_samples=num_samples, +) + +model.save_pretrained("Llama-3.3-70B-Instruct-quantized.w8a8") +``` + +## 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 Neural Magic's fork of [lm-evaluation-harness](https://github.com/neuralmagic/lm-evaluation-harness/tree/llama_3.1_instruct) (branch llama_3.1_instruct). +This version of the lm-evaluation-harness includes versions of MMLU, ARC-Challenge and GSM-8K that match the prompting style of [Meta-Llama-3.1-Instruct-evals](https://huggingface.co/datasets/meta-llama/Meta-Llama-3.1-8B-Instruct-evals) and a few fixes to OpenLLM v2 tasks. + +HumanEval and HumanEval+ evaluations were conducted using Neural Magic's fork of the [EvalPlus](https://github.com/neuralmagic/evalplus) repository. + +### Accuracy + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Category + Benchmark + Llama-3.3-70B-Instruct + Llama-3.3-70B-Instruct-quantized.w8a8 (this model) + Recovery +
OpenLLM v1 + MMLU (5-shot) + 81.60 + 81.19 + 99.5% +
MMLU (CoT, 0-shot) + 86.58 + 85.92 + 99.2% +
ARC Challenge (0-shot) + 49.23 + 48.04 + 97.6% +
GSM-8K (CoT, 8-shot, strict-match) + 94.16 + 94.01 + 99.8% +
Hellaswag (10-shot) + 86.49 + 86.47 + 100.0% +
Winogrande (5-shot) + 84.77 + 83.74 + 98.8% +
TruthfulQA (0-shot, mc2) + 62.75 + 63.09 + 99.5% +
Average + 77.94 + 77.49 + 99.4% +
OpenLLM v2 + MMLU-Pro (5-shot) + 51.89 + 51.59 + 99.7% +
IFEval (0-shot) + 90.89 + 90.68 + 99.4% +
BBH (3-shot) + 63.15 + 62.54 + 99.0% +
Math-lvl-5 (4-shot) + 0.17 + 0.00 + N/A +
GPQA (0-shot) + 46.10 + 46.44 + 100.8% +
MuSR (0-shot) + 44.35 + 44.34 + 100.0% +
Average + 49.42 + 49.27 + 99.7% +
Coding + HumanEval pass@1 + 83.20 + 83.30 + 100.1% +
HumanEval+ pass@1 + 78.40 + 78.60 + 100.3% +
Multilingual + Portuguese MMLU (5-shot) + 79.76 + 79.47 + 99.6% +
Spanish MMLU (5-shot) + 79.33 + 79.23 + 99.9% +
Italian MMLU (5-shot) + 79.15 + 78.80 + 99.6% +
German MMLU (5-shot) + 77.94 + 77.92 + 100.0% +
French MMLU (5-shot) + 75.69 + 75.79 + 100.1% +
Hindi MMLU (5-shot) + 73.81 + 73.49 + 99.6% +
Thai MMLU (5-shot) + 71.97 + 71.44 + 99.2% +
+ +### Reproduction + +The results were obtained using the following commands: + +#### MMLU +``` +lm_eval \ + --model vllm \ + --model_args pretrained="neuralmagic-ent/Llama-3.3-70B-Instruct-quantized.w8a8",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \ + --tasks mmlu_llama_3.1_instruct \ + --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-quantized.w8a8",dtype=auto,max_model_len=4064,max_gen_toks=1024,tensor_parallel_size=1 \ + --tasks mmlu_cot_0shot_llama_3.1_instruct \ + --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-quantized.w8a8",dtype=auto,max_model_len=3940,max_gen_toks=100,tensor_parallel_size=1 \ + --tasks arc_challenge_llama_3.1_instruct \ + --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-quantized.w8a8",dtype=auto,max_model_len=4096,max_gen_toks=1024,tensor_parallel_size=1 \ + --tasks gsm8k_cot_llama_3.1_instruct \ + --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-quantized.w8a8",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-quantized.w8a8",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-quantized.w8a8",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-quantized.w8a8",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-quantized.w8a8",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \ + --tasks mmlu_pt_llama_3.1_instruct \ + --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-quantized.w8a8",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \ + --tasks mmlu_es_llama_3.1_instruct \ + --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-quantized.w8a8",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \ + --tasks mmlu_it_llama_3.1_instruct \ + --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-quantized.w8a8",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \ + --tasks mmlu_de_llama_3.1_instruct \ + --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-quantized.w8a8",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \ + --tasks mmlu_fr_llama_3.1_instruct \ + --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-quantized.w8a8",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \ + --tasks mmlu_hi_llama_3.1_instruct \ + --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-quantized.w8a8",dtype=auto,max_model_len=3850,max_gen_toks=10,tensor_parallel_size=1 \ + --tasks mmlu_th_llama_3.1_instruct \ + --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-quantized.w8a8 \ + --bs 16 \ + --temperature 0.2 \ + --n_samples 50 \ + --root "." \ + --dataset humaneval +``` +##### Sanitization +``` +python3 evalplus/sanitize.py \ + humaneval/neuralmagic-ent--Llama-3.3-70B-Instruct-quantized.w8a8_vllm_temp_0.2 +``` +##### Evaluation +``` +evalplus.evaluate \ + --dataset humaneval \ + --samples humaneval/neuralmagic-ent--Llama-3.3-70B-Instruct-quantized.w8a8_vllm_temp_0.2-sanitized +``` diff --git a/config.json b/config.json new file mode 100644 index 0000000..841f7d5 --- /dev/null +++ b/config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78aec001995478cd9315db2484034e46d2a84f405c74a679e14fe9fb26e9517a +size 1995 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..87d5860 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,12 @@ +{ + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": [ + 128001, + 128008, + 128009 + ], + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "4.48.0" +} diff --git a/model-00001-of-00015.safetensors b/model-00001-of-00015.safetensors new file mode 100644 index 0000000..717a65b --- /dev/null +++ b/model-00001-of-00015.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80b546cfe115c86caee3717ae67b174e32a1c2c06604c52161993fb4c8e14b12 +size 4819900928 diff --git a/model-00002-of-00015.safetensors b/model-00002-of-00015.safetensors new file mode 100644 index 0000000..9479984 --- /dev/null +++ b/model-00002-of-00015.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4953ebf70cfa05865fe9ae62af2d965d0654ecd00c4f185e9e252941d446c23 +size 4984010360 diff --git a/model-00003-of-00015.safetensors b/model-00003-of-00015.safetensors new file mode 100644 index 0000000..5868084 --- /dev/null +++ b/model-00003-of-00015.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:954135fa222ccf5746e5280c15640dde4dfeed90b5be9a8f1c808a22e8e409b2 +size 4900112536 diff --git a/model-00004-of-00015.safetensors b/model-00004-of-00015.safetensors new file mode 100644 index 0000000..bc25172 --- /dev/null +++ b/model-00004-of-00015.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc5f2a34fb6118ef4a0a0a0151690e9ee4ae26456d4e741446cd7822e831cac9 +size 4900104584 diff --git a/model-00005-of-00015.safetensors b/model-00005-of-00015.safetensors new file mode 100644 index 0000000..b522703 --- /dev/null +++ b/model-00005-of-00015.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8912ec39e9389e3e7758d6bc5311431d72342b36880ec8e98b5896f4d037933 +size 4900104584 diff --git a/model-00006-of-00015.safetensors b/model-00006-of-00015.safetensors new file mode 100644 index 0000000..35a2776 --- /dev/null +++ b/model-00006-of-00015.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92d31d8ced5d5b5cde002f25173ea7476b08e11957d13114adffee0c37be8880 +size 4984010448 diff --git a/model-00007-of-00015.safetensors b/model-00007-of-00015.safetensors new file mode 100644 index 0000000..bd787da --- /dev/null +++ b/model-00007-of-00015.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31e6c8201ce6680ebda1448cc6a6f1c3dd05ba282dadc2d95b3080bf11224371 +size 4900112552 diff --git a/model-00008-of-00015.safetensors b/model-00008-of-00015.safetensors new file mode 100644 index 0000000..3f414ce --- /dev/null +++ b/model-00008-of-00015.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25c6bb236d4d99725744f87b1c496289aece57fa77e5bfef15f933174866b23b +size 4900104584 diff --git a/model-00009-of-00015.safetensors b/model-00009-of-00015.safetensors new file mode 100644 index 0000000..495ca2b --- /dev/null +++ b/model-00009-of-00015.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3aac343e21a80a4f53bd63cf874f9a310afba966863101d3b05df63577e9ca42 +size 4900104584 diff --git a/model-00010-of-00015.safetensors b/model-00010-of-00015.safetensors new file mode 100644 index 0000000..5ef7369 --- /dev/null +++ b/model-00010-of-00015.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77edcac43c2d08d72f54a10b1c1a977932dad9aa31ffddbb97aebab7be2d6048 +size 4984010448 diff --git a/model-00011-of-00015.safetensors b/model-00011-of-00015.safetensors new file mode 100644 index 0000000..2d715f7 --- /dev/null +++ b/model-00011-of-00015.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac2b3a35355d7686f778e66dfa21c69236a29015825b22fc38604a35c652f8d2 +size 4900112552 diff --git a/model-00012-of-00015.safetensors b/model-00012-of-00015.safetensors new file mode 100644 index 0000000..2d20f21 --- /dev/null +++ b/model-00012-of-00015.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f2b8a0a3174e721bc9af7ca41d0837d13fb4037fd1feab13615166a7e3e0283 +size 4900104584 diff --git a/model-00013-of-00015.safetensors b/model-00013-of-00015.safetensors new file mode 100644 index 0000000..2e26192 --- /dev/null +++ b/model-00013-of-00015.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e029a49ee948da1bfddc70088b97306bf8e9c3dd691d317224d4fb9b85075498 +size 4900104584 diff --git a/model-00014-of-00015.safetensors b/model-00014-of-00015.safetensors new file mode 100644 index 0000000..cfece84 --- /dev/null +++ b/model-00014-of-00015.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc641fce3440464b2d8c33707a2c269b95d51c10212db189824a3d1df508ab8a +size 4984010448 diff --git a/model-00015-of-00015.safetensors b/model-00015-of-00015.safetensors new file mode 100644 index 0000000..fa910bd --- /dev/null +++ b/model-00015-of-00015.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bd6c75738fb668e0db4eadbe0422283ece855a7e22bfa35d19acd858940f176 +size 3813044096 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..873315f --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcde01c04860007d9a522fbb4f9c161be84e26395e1b49847a7ea32b97bdfa24 +size 108504 diff --git a/recipe.yaml b/recipe.yaml new file mode 100644 index 0000000..1ab789e --- /dev/null +++ b/recipe.yaml @@ -0,0 +1,21 @@ +quant_stage: + quant_modifiers: + SmoothQuantModifier: + smoothing_strength: 0.8 + mappings: + - - ['re:.*q_proj', 're:.*k_proj', 're:.*v_proj'] + - re:.*input_layernorm + - - ['re:.*gate_proj', 're:.*up_proj'] + - re:.*post_attention_layernorm + - - ['re:.*down_proj'] + - re:.*up_proj + GPTQModifier: + sequential_update: true + dampening_frac: 0.01 + ignore: [lm_head] + config_groups: + group_0: + targets: [Linear] + weights: {num_bits: 8, type: int, symmetric: true, strategy: channel, observer: mse} + input_activations: {num_bits: 8, type: int, symmetric: true, strategy: token, dynamic: true, + observer: memoryless} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..3c1d049 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..1c1d8d5 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..89911b9 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c756ad6048c884974a331963ae3c3e1624b548a11174dadda02a69041c87352 +size 55425