From f3692f2dc2303f3f224b0692fe91e7b50b29e655 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sat, 17 Oct 2026 21:22:13 +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: RedHatAI/Mistral-Small-24B-Instruct-2501-quantized.w4a16 Source: Original Platform --- .gitattributes | 38 +++ README.md | 434 +++++++++++++++++++++++++++++++ config.json | 59 +++++ configuration.json | 1 + generation_config.json | 8 + model-00001-of-00003.safetensors | 3 + model-00002-of-00003.safetensors | 3 + model-00003-of-00003.safetensors | 3 + model.safetensors.index.json | 3 + recipe.yaml | 14 + special_tokens_map.json | 3 + tekken.json | 3 + tokenizer.json | 3 + tokenizer_config.json | 3 + 14 files changed, 578 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 config.json create mode 100644 configuration.json create mode 100644 generation_config.json create mode 100644 model-00001-of-00003.safetensors create mode 100644 model-00002-of-00003.safetensors create mode 100644 model-00003-of-00003.safetensors create mode 100644 model.safetensors.index.json create mode 100644 recipe.yaml create mode 100644 special_tokens_map.json create mode 100644 tekken.json create mode 100644 tokenizer.json create mode 100644 tokenizer_config.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d8d7406 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,38 @@ +*.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 + +tekken.json 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..63ad782 --- /dev/null +++ b/README.md @@ -0,0 +1,434 @@ +--- +language: + - en + - fr + - de + - es + - it + - pt + - zh + - ja + - ru + - ko +base_model: +- mistralai/Mistral-Small-24B-Instruct-2501 +pipeline_tag: text-generation +tags: +- mistral +- mistral-small +- w4a16 +- int4 +- vllm +- conversational +- text-generation-inference +- compressed-tensors +license: apache-2.0 +license_name: apache-2.0 +name: RedHatAI/Mistral-Small-24B-Instruct-2501-quantized.w4a16 +description: This model was obtained by quantizing the weights of Mistral-Small-24B-Instruct-2501 to INT4 data type. +readme: https://huggingface.co/RedHatAI/Mistral-Small-24B-Instruct-2501-quantized.w4a16/main/README.md +tasks: +- text-to-text +provider: Mistral AI +license_link: https://www.apache.org/licenses/LICENSE-2.0 +validated_on: + - RHOAI 2.20 + - RHAIIS 3.0 + - RHELAI 1.5 + - vLLM 0.8.4 +--- + +

+ Mistral-Small-24B-Instruct-2501-quantized.w4a16 + Model Icon +

+ + +Validated Badge + + +## Model Overview +- **Model Architecture:** Mistral-Small-24B-Instruct-2501 + - **Input:** Text + - **Output:** Text +- **Model Optimizations:** + - **Weight quantization:** INT4 + - **Activation quantization:** None +- **Release Date:** 3/1/2025 +- **Version:** 1.0 +- **Validated on:** RHOAI 2.20, RHAIIS 3.0, RHELAI 1.5 +- **Model Developers:** Neural Magic + +Quantized version of [Mistral-Small-24B-Instruct-2501](https://huggingface.co/mistralai/Mistral-Small-24B-Instruct-2501). + +### Model Optimizations + +This model was obtained by quantizing the weights to INT4 data type, ready for inference with vLLM. +This optimization reduces the number of bits per parameter from 16 to 4, reducing the disk size and GPU memory requirements by approximately 75%. Only the weights of the linear operators within transformers blocks are quantized. + +## Deployment + +### Use with vLLM + +1. Initialize vLLM server: +``` +vllm serve RedHatAI/Mistral-Small-24B-Instruct-2501-quantized.w4a16 --tensor_parallel_size 1 --tokenizer_mode mistral +``` + +2. Send requests to the server: + +```python +from openai import OpenAI + +# Modify OpenAI's API key and API base to use vLLM's API server. +openai_api_key = "EMPTY" +openai_api_base = "http://:8000/v1" + +client = OpenAI( + api_key=openai_api_key, + base_url=openai_api_base, +) + +model = "RedHatAI/Mistral-Small-24B-Instruct-2501-quantized.w4a16" + + +messages = [ + {"role": "user", "content": "Explain quantum mechanics clearly and concisely."}, +] + +outputs = client.chat.completions.create( + model=model, + messages=messages, +) + +generated_text = outputs.choices[0].message.content +print(generated_text) +``` + +
+ 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/Mistral-Small-24B-Instruct-2501-quantized.w4a16 +``` +​​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/mistral-small-24b-instruct-2501-quantized-w4a16:1.5 +``` + +```bash +# Serve model via ilab +ilab model serve --model-path ~/.cache/instructlab/models/mistral-small-24b-instruct-2501-quantized-w4a16 --gpu 1 -- --trust-remote-code + +# Chat with model +ilab model chat --model ~/.cache/instructlab/models/mistral-small-24b-instruct-2501-quantized-w4a16 +``` +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: Mistral-Small-24B-Instruct-2501-quantized.w4a16 # OPTIONAL CHANGE + serving.kserve.io/deploymentMode: RawDeployment + name: Mistral-Small-24B-Instruct-2501-quantized.w4a16 # 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: + args: + - "--trust-remote-code" + 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-mistral-small-24b-instruct-2501-quantized-w4a16:1.5 + 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": "Mistral-Small-24B-Instruct-2501-quantized.w4a16", + "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 with [llm-compressor](https://github.com/vllm-project/llm-compressor) by running the code snippet below. + +```bash +python quantize.py --model_path mistralai/Mistral-Small-24B-Instruct-2501 --quant_path "output_dir" --calib_size 1024 --dampening_frac 0.05 --observer minmax --actorder false +``` + +```python +from datasets import load_dataset +from transformers import AutoTokenizer +from llmcompressor.modifiers.quantization import GPTQModifier +from llmcompressor.transformers import SparseAutoModelForCausalLM, oneshot, apply +import argparse +from compressed_tensors.quantization import QuantizationScheme, QuantizationArgs, QuantizationType, QuantizationStrategy + +def parse_actorder(value): + # Interpret the input value for --actorder + if value.lower() == "false": + return False + elif value.lower() == "group": + return "group" + elif value.lower() == "weight": + return "weight" + else: + raise argparse.ArgumentTypeError("Invalid value for --actorder. Use 'group' or 'False'.") + + +parser = argparse.ArgumentParser() +parser.add_argument('--model_path', type=str) +parser.add_argument('--quant_path', type=str) +parser.add_argument('--num_bits', type=int, default=4) +parser.add_argument('--sequential_update', type=bool, default=True) +parser.add_argument('--calib_size', type=int, default=256) +parser.add_argument('--dampening_frac', type=float, default=0.05) +parser.add_argument('--observer', type=str, default="minmax") +parser.add_argument( + '--actorder', + type=parse_actorder, + default=False, # Default value is False + help="Specify actorder as 'group' (string) or False (boolean)." +) + +args = parser.parse_args() + +model = SparseAutoModelForCausalLM.from_pretrained( + args.model_path, + device_map="auto", + torch_dtype="auto", + use_cache=False, +) +tokenizer = AutoTokenizer.from_pretrained(args.model_path) + +NUM_CALIBRATION_SAMPLES = args.calib_size +DATASET_ID = "garage-bAInd/Open-Platypus" +DATASET_SPLIT = "train" +ds = load_dataset(DATASET_ID, split=DATASET_SPLIT) +ds = ds.shuffle(seed=42).select(range(NUM_CALIBRATION_SAMPLES)) + +def preprocess(example): + concat_txt = example["instruction"] + "\n" + example["output"] + return {"text": concat_txt} + +ds = ds.map(preprocess) + +def tokenize(sample): + return tokenizer( + sample["text"], + padding=False, + truncation=False, + add_special_tokens=True, + ) + + +ds = ds.map(tokenize, remove_columns=ds.column_names) + +quant_scheme = QuantizationScheme( + targets=["Linear"], + weights=QuantizationArgs( + num_bits=args.num_bits, + type=QuantizationType.INT, + symmetric=True, + group_size=128, + strategy=QuantizationStrategy.GROUP, + observer=args.observer, + actorder=args.actorder + ), + input_activations=None, + output_activations=None, +) + +recipe = [ + GPTQModifier( + targets=["Linear"], + ignore=["lm_head"], + sequential_update=args.sequential_update, + dampening_frac=args.dampening_frac, + config_groups={"group_0": quant_scheme}, + ) +] +oneshot( + model=model, + dataset=ds, + recipe=recipe, + num_calibration_samples=args.calib_size, +) + +# Save to disk compressed. +SAVE_DIR = args.quant_path +model.save_pretrained(SAVE_DIR, save_compressed=True) +tokenizer.save_pretrained(SAVE_DIR) +``` + +## Evaluation + +The model was evaluated on OpenLLM Leaderboard [V1](https://huggingface.co/spaces/open-llm-leaderboard-old/open_llm_leaderboard) and [V2](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/), using the following commands: + +OpenLLM Leaderboard V1: +``` +lm_eval \ + --model vllm \ + --model_args pretrained="neuralmagic/Mistral-Small-24B-Instruct-2501-quantized.w4a16",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \ + --tasks openllm \ + --write_out \ + --batch_size auto \ + --output_path output_dir \ + --show_config +``` + +OpenLLM Leaderboard V2: +``` +lm_eval \ + --model vllm \ + --model_args pretrained="neuralmagic/Mistral-Small-24B-Instruct-2501-quantized.w4a16",dtype=auto,add_bos_token=False,max_model_len=4096,tensor_parallel_size=1,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \ + --apply_chat_template \ + --fewshot_as_multiturn \ + --tasks leaderboard \ + --write_out \ + --batch_size auto \ + --output_path output_dir \ + --show_config + +``` + +### Accuracy + +#### OpenLLM Leaderboard V1 evaluation scores + + +| Metric | mistralai/Mistral-Small-24B-Instruct-2501 | neuralmagic/Mistral-Small-24B-Instruct-2501-quantized.w4a16 | +|-----------------------------------------|:---------------------------------:|:-------------------------------------------:| +| ARC-Challenge (Acc-Norm, 25-shot) | 72.18 | 71.16 | +| GSM8K (Strict-Match, 5-shot) | 90.14 | 89.69 | +| HellaSwag (Acc-Norm, 10-shot) | 85.05 | 84.43 | +| MMLU (Acc, 5-shot) | 80.69 | 80.00 | +| TruthfulQA (MC2, 0-shot) | 65.55 | 63.92 | +| Winogrande (Acc, 5-shot) | 83.11 | 82.24 | +| **Average Score** | **79.45** | **78.57** | +| **Recovery (%)** | **100.00** | **98.9** | + +#### OpenLLM Leaderboard V2 evaluation scores + +| Metric | mistralai/Mistral-Small-24B-Instruct-2501 | neuralmagic/Mistral-Small-24B-Instruct-2501-quantized.w4a16 | +|---------------------------------------------------------|:---------------------------------:|:-------------------------------------------:| +| IFEval (Inst-and-Prompt Level Strict Acc, 0-shot) | 73.27 | 74.37 | +| BBH (Acc-Norm, 3-shot) | 45.18 | 45.15 | +| MMLU-Pro (Acc, 5-shot) | 38.83 | 36.00 | +| **Average Score** | **52.42** | **51.84** | +| **Recovery (%)** | **100.00** | **98.89** | +| GPQA (Acc-Norm, 0-shot) | 8.29 | 6.81 | +| MUSR (Acc-Norm, 0-shot) | 7.84 | 9.46 | + +Results on GPQA and MUSR are not considred for accuracy recovery calculation because the unquantized model has close to random prediction accuracy (8.29, 7.84) which doesn't provide a reliable baseline for recovery calculation. + diff --git a/config.json b/config.json new file mode 100644 index 0000000..ca16edc --- /dev/null +++ b/config.json @@ -0,0 +1,59 @@ +{ + "_name_or_path": "mistralai/Mistral-Small-24B-Instruct-2501", + "architectures": [ + "MistralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 32768, + "max_position_embeddings": 32768, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 40, + "num_key_value_heads": 8, + "quantization_config": { + "config_groups": { + "group_0": { + "input_activations": null, + "output_activations": null, + "targets": [ + "Linear" + ], + "weights": { + "actorder": null, + "block_structure": null, + "dynamic": false, + "group_size": 128, + "num_bits": 4, + "observer": "minmax", + "observer_kwargs": {}, + "strategy": "group", + "symmetric": true, + "type": "int" + } + } + }, + "format": "pack-quantized", + "global_compression_ratio": 2.0797400655392253, + "ignore": [ + "lm_head" + ], + "kv_cache_scheme": null, + "quant_method": "compressed-tensors", + "quantization_status": "compressed", + "sparsity_config": {} + }, + "rms_norm_eps": 1e-05, + "rope_theta": 100000000.0, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.48.2", + "use_cache": false, + "vocab_size": 131072 +} 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..25ecfe7 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,8 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "do_sample": true, + "eos_token_id": 2, + "temperature": 0.15, + "transformers_version": "4.48.2" +} diff --git a/model-00001-of-00003.safetensors b/model-00001-of-00003.safetensors new file mode 100644 index 0000000..077b47a --- /dev/null +++ b/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88c75e7d5c2933ded1ef3452b3770f56ba27d7fdd201346cad3bed08cca72696 +size 4981180656 diff --git a/model-00002-of-00003.safetensors b/model-00002-of-00003.safetensors new file mode 100644 index 0000000..0378e0f --- /dev/null +++ b/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80caaaf3de240147958713dd8863eddd82f9c0aa06d642834a1244988ca5c835 +size 4985413200 diff --git a/model-00003-of-00003.safetensors b/model-00003-of-00003.safetensors new file mode 100644 index 0000000..fdfead2 --- /dev/null +++ b/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a098a6bba64c7389355bb09891d72a23782f639b09d506358096c41d0d7f165 +size 4180946336 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..87650f8 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eeef73c38225f74e2eb13556ee452cc6feb16a080c090881bac6bec8cbdc2607 +size 80674 diff --git a/recipe.yaml b/recipe.yaml new file mode 100644 index 0000000..ffe0052 --- /dev/null +++ b/recipe.yaml @@ -0,0 +1,14 @@ +DEFAULT_stage: + DEFAULT_modifiers: + GPTQModifier: + sequential_update: true + dampening_frac: 0.05 + config_groups: + group_0: + targets: [Linear] + weights: {num_bits: 4, type: int, symmetric: true, group_size: 128, strategy: group, + actorder: null, observer: minmax} + input_activations: null + output_activations: null + targets: [Linear] + ignore: [lm_head] diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..e730fbf --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bc5d1c106bf86895473568ef5211f3fde8415e6fdee039223d6db8ca52cbe01 +size 21311 diff --git a/tekken.json b/tekken.json new file mode 100644 index 0000000..f973db9 --- /dev/null +++ b/tekken.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4b90a968dbc67ef3975129d0b78a2e3cbb6bea340ab9205f22e8a0308b1ffc5 +size 14801223 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..4135d4b --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b76085f9923309d873994d444989f7eb6ec074b06f25b58f1e8d7b7741070949 +size 17078037 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..1bcd904 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:350d9c44f99942e4dd52b8f11bca7d0ac1eeee9acf9e8ee13cfc72de753f1cf1 +size 199721