commit 7bf1099f63014fe95b361068cd36c0cb82ed4741 Author: ModelHub XC Date: Wed Oct 28 10:50:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: RedHatAI/DeepSeek-R1-Distill-Qwen-7B-FP8-dynamic 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..e68b30c --- /dev/null +++ b/README.md @@ -0,0 +1,763 @@ +--- +license: mit +tags: +- deepseek +- fp8 +- vllm +base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B +library_name: transformers +--- + +# DeepSeek-R1-Distill-Qwen-7B-FP8-dynamic + +## Model Overview +- **Model Architecture:** Qwen2ForCausalLM + - **Input:** Text + - **Output:** Text +- **Model Optimizations:** + - **Weight quantization:** FP8 + - **Activation quantization:** FP8 +- **Release Date:** 2/5/2025 +- **Version:** 1.0 +- **Model Developers:** Neural Magic + +Quantized version of [DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B). + + +### Model Optimizations + +This model was obtained by quantizing the weights and activations of [DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) to FP8 data type. +This optimization reduces the number of bits per parameter from 16 to 8, reducing the disk size and GPU memory requirements by approximately 50%. + +Only the weights and activations of the linear operators within transformers blocks are quantized. +Weights are quantized using a symmetric per-channel scheme, whereas quantizations are quantized using a symmetric per-token scheme. +[LLM Compressor](https://github.com/vllm-project/llm-compressor) is used for quantization. + + +## 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 + +number_gpus = 1 +model_name = "neuralmagic/DeepSeek-R1-Distill-Qwen-7B-dynamic" + +tokenizer = AutoTokenizer.from_pretrained(model_name) +sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id]) +llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True) + +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 also supports OpenAI-compatible serving. See the [documentation](https://docs.vllm.ai/en/latest/) for more details. + +## Creation + +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 +import os + +# Load model +model_stub = "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B" +model_name = model_stub.split("/")[-1] + +model = AutoModelForCausalLM.from_pretrained( + model_stub, + torch_dtype="auto", +) + +tokenizer = AutoTokenizer.from_pretrained(model_stub) + +# 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}") +``` + +## 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/DeepSeek-R1-Distill-Qwen-7B-FP8-dynamic",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=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/DeepSeek-R1-Distill-Qwen-7B-FP8-dynamic",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \ + --apply_chat_template \ + --fewshot_as_multiturn \ + --tasks leaderboard \ + --write_out \ + --batch_size auto \ + --output_path output_dir \ + --show_config +``` + +### Accuracy + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
CategoryMetricdeepseek-ai/DeepSeek-R1-Distill-Qwen-7Bneuralmagic/DeepSeek-R1-Distill-Qwen-7B-FP8-dynamicRecovery
ReasoningAIME 2024 (pass@1)53.1753.17100%
MATH-500 (pass@1)93.6693.6299.96%
GPQA Diamond (pass@1)50.5350.2899.51%
Average Score65.7965.6999.85%
OpenLLM V1ARC-Challenge (Acc-Norm, 25-shot)50.5150.51100.0%
GSM8K (Strict-Match, 5-shot)78.6279.83101.5%
HellaSwag (Acc-Norm, 10-shot)61.9061.6299.6%
MMLU (Acc, 5-shot)54.1953.7699.2%
TruthfulQA (MC2, 0-shot)45.5546.14101.3%
Winogrande (Acc, 5-shot)61.5660.5498.3%
Average Score58.7258.73100.0%
OpenLLM V2IFEval (Inst Level Strict Acc, 0-shot)39.3839.0199.1%
BBH (Acc-Norm, 3-shot)6.976.19---
Math-Hard (Exact-Match, 4-shot)0.000.00---
GPQA (Acc-Norm, 0-shot)1.811.63---
MUSR (Acc-Norm, 0-shot)4.685.08---
MMLU-Pro (Acc, 5-shot)1.661.76---
Average Score9.088.94---
CodingHumanEval (pass@1)40.8039.5096.8%
HumanEval (pass@10)64.4062.1096.4%
HumanEval+ (pass@10)38.5037.2096.6%
HumanEval+ (pass@10)60.4059.3098.2%
+ +## Inference Performance + + +This model achieves up to 1.4x speedup in single-stream deployment and up to 1.2x speedup in multi-stream asynchronous deployment, depending on hardware and use-case scenario. +The following performance benchmarks were conducted with [vLLM](https://docs.vllm.ai/en/latest/) version 0.7.2, and [GuideLLM](https://github.com/neuralmagic/guidellm). + +
+Benchmarking Command + +``` +guidellm --model neuralmagic/DeepSeek-R1-Distill-Qwen-7B-FP8-dynamic --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=,generated_tokens=" --max seconds 360 --backend aiohttp_server +``` +
+ +### Single-stream performance (measured with vLLM version 0.7.2) + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Instruction Following
256 / 128		Multi-turn Chat
512 / 256		Docstring Generation
768 / 128		RAG
1024 / 128		Code Completion
256 / 1024		Code Fixing
1024 / 1024		Large Summarization
4096 / 512		Large RAG
10240 / 1536
HardwareModelAverage cost reductionLatency (s)QPDLatency (s)QPDLatency (s)QPDLatency (s)QPDLatency (s)QPDLatency (s)QPDLatency (s)QPDLatency (s)QPD
A6000x1deepseek-ai/DeepSeek-R1-Distill-Qwen-7B---2.915765.77882.915353.0149622.619923.219412.137038.5117
neuralmagic/DeepSeek-R1-Distill-Qwen-7B-quantized.w8a81.561.824953.712231.923841.9239314.331514.83047.957225.3178
neuralmagic/DeepSeek-R1-Distill-Qwen-7B-quantized.w4a162.411.140862.319981.237831.335278.65268.85125.286022.7198
A100x1deepseek-ai/DeepSeek-R1-Distill-Qwen-7B---1.413892.96911.513581.5132911.517511.61746.232621.593
neuralmagic/DeepSeek-R1-Distill-Qwen-7B-quantized.w8a81.281.118502.29051.118071.117508.62338.72304.743123.187
neuralmagic/DeepSeek-R1-Distill-Qwen-7B-quantized.w4a161.720.825751.512980.824610.823826.13316.23233.656622.789
H100x1deepseek-ai/DeepSeek-R1-Distill-Qwen-7B---0.911611.95791.011381.011217.51467.61453.927915.471
neuralmagic/DeepSeek-R1-Distill-Qwen-7B-FP8-dynamic1.340.715851.47860.715770.715245.32075.51972.938214.377
neuralmagic/DeepSeek-R1-Distill-Qwen-7B-quantized.w4a161.330.715901.47930.715490.715095.42015.51982.938114.078
+ +**Use case profiles: prompt tokens / generation tokens + +**QPD: Queries per dollar, based on on-demand cost at [Lambda Labs](https://lambdalabs.com/service/gpu-cloud) (observed on 2/18/2025). + + +### Multi-stream asynchronous performance (measured with vLLM version 0.7.2) + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Instruction Following
256 / 128		Multi-turn Chat
512 / 256		Docstring Generation
768 / 128		RAG
1024 / 128		Code Completion
256 / 1024		Code Fixing
1024 / 1024		Large Summarization
4096 / 512		Large RAG
10240 / 1536
HardwareModelAverage cost reductionMaximum throughput (QPS)QPDMaximum throughput (QPS)QPDMaximum throughput (QPS)QPDMaximum throughput (QPS)QPDMaximum throughput (QPS)QPDMaximum throughput (QPS)QPDMaximum throughput (QPS)QPDMaximum throughput (QPS)QPD
A6000x1deepseek-ai/DeepSeek-R1-Distill-Qwen-7B---14.9671387.1320947.4330965.9264802.090041.566391.149380.31151
neuralmagic/DeepSeek-R1-Distill-Qwen-7B-quantized.w8a81.3620.2909568.83978610.2459638.1365963.1139682.196291.463740.31429
neuralmagic/DeepSeek-R1-Distill-Qwen-7B-quantized.w4a161.0013.3596816.1276335.9266894.7209442.9131081.983551.043620.31170
A100x1deepseek-ai/DeepSeek-R1-Distill-Qwen-7B---26.45307313.02621314.52911011.4229364.487493.366802.346340.51105
neuralmagic/DeepSeek-R1-Distill-Qwen-7B-quantized.w8a81.2734.36900914.82979119.03821415.7315985.6111864.283503.060200.71328
neuralmagic/DeepSeek-R1-Distill-Qwen-7B-quantized.w4a160.9323.94799312.02419412.52523910.0200294.590553.366812.141560.51043
H100x1deepseek-ai/DeepSeek-R1-Distill-Qwen-7B---54.35941026.02844032.13515426.7291908.087006.672755.256691.21266
neuralmagic/DeepSeek-R1-Distill-Qwen-7B-FP8-dynamic1.1662.96881830.33319639.44313231.1340739.2100587.177486.167141.31415
neuralmagic/DeepSeek-R1-Distill-Qwen-7B-quantized.w4a161.0256.26148326.72924332.53559226.9294618.390726.470275.257311.21291
+ +**Use case profiles: prompt tokens / generation tokens + +**QPS: Queries per second. + +**QPD: Queries per dollar, based on on-demand cost at [Lambda Labs](https://lambdalabs.com/service/gpu-cloud) (observed on 2/18/2025). diff --git a/config.json b/config.json new file mode 100644 index 0000000..83452e5 --- /dev/null +++ b/config.json @@ -0,0 +1,72 @@ +{ + "_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151643, + "hidden_act": "silu", + "hidden_size": 3584, + "initializer_range": 0.02, + "intermediate_size": 18944, + "max_position_embeddings": 131072, + "max_window_layers": 28, + "model_type": "qwen2", + "num_attention_heads": 28, + "num_hidden_layers": 28, + "num_key_value_heads": 4, + "quantization_config": { + "config_groups": { + "group_0": { + "input_activations": { + "actorder": null, + "block_structure": null, + "dynamic": true, + "group_size": null, + "num_bits": 8, + "observer": null, + "observer_kwargs": {}, + "strategy": "token", + "symmetric": true, + "type": "float" + }, + "output_activations": null, + "targets": [ + "Linear" + ], + "weights": { + "actorder": null, + "block_structure": null, + "dynamic": false, + "group_size": null, + "num_bits": 8, + "observer": "mse", + "observer_kwargs": {}, + "strategy": "channel", + "symmetric": true, + "type": "float" + } + } + }, + "format": "float-quantized", + "global_compression_ratio": 1.5268082955288436, + "ignore": [ + "lm_head" + ], + "kv_cache_scheme": null, + "quant_method": "compressed-tensors", + "quantization_status": "compressed" + }, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.48.1", + "use_cache": true, + "use_mrope": false, + "use_sliding_window": false, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..e91e530 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,9 @@ +{ + "_from_model_config": true, + "bos_token_id": 151646, + "do_sample": true, + "eos_token_id": 151643, + "temperature": 0.6, + "top_p": 0.95, + "transformers_version": "4.48.1" +} diff --git a/model-00001-of-00002.safetensors b/model-00001-of-00002.safetensors new file mode 100644 index 0000000..38d28c0 --- /dev/null +++ b/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ac2e963a3bf6fd8968ac94946691246d6649da683d75e21762073db961fab77 +size 4985986696 diff --git a/model-00002-of-00002.safetensors b/model-00002-of-00002.safetensors new file mode 100644 index 0000000..841227a --- /dev/null +++ b/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3212e2713a0e1224d11dc74617a9200907d35119ad1b30213403a19e2c878591 +size 3722801872 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..64b104a --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,542 @@ +{ + "metadata": { + "total_size": 8708725760 + }, + "weight_map": { + "lm_head.weight": "model-00002-of-00002.safetensors", + "model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.16.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.17.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.17.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.18.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.18.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.18.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.19.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.19.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.19.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.20.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.20.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.20.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors", + "model.norm.weight": "model-00002-of-00002.safetensors" + } +} diff --git a/recipe.yaml b/recipe.yaml new file mode 100644 index 0000000..044a5bf --- /dev/null +++ b/recipe.yaml @@ -0,0 +1,10 @@ +quant_stage: + quant_modifiers: + QuantizationModifier: + ignore: [lm_head] + config_groups: + group_0: + targets: [Linear] + weights: {num_bits: 8, type: float, symmetric: true, strategy: channel, observer: mse} + input_activations: {num_bits: 8, type: float, 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..1d385d6 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..8e71bf3 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88145e3c3249adc2546ede277e9819d6e405e19072456e4b521cbc724bd60773 +size 7031660 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..9967ff3 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,35 @@ +{ + "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": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "legacy": true, + "model_max_length": 16384, + "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", + "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\\n'}}{% endif %}" +} \ No newline at end of file