commit fd08122df49038a4fa04dd5f793be13887b3e343 Author: ModelHub XC Date: Fri Oct 23 10:26:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: QuantFactory/dolphin-2.9.4-llama3.1-8b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..20959c7 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +dolphin-2.9.4-llama3.1-8b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9.4-llama3.1-8b.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9.4-llama3.1-8b.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9.4-llama3.1-8b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9.4-llama3.1-8b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9.4-llama3.1-8b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9.4-llama3.1-8b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9.4-llama3.1-8b.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9.4-llama3.1-8b.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9.4-llama3.1-8b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9.4-llama3.1-8b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9.4-llama3.1-8b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9.4-llama3.1-8b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +dolphin-2.9.4-llama3.1-8b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..2d20418 --- /dev/null +++ b/README.md @@ -0,0 +1,379 @@ + +--- + +license: llama3.1 +base_model: meta-llama/Meta-Llama-3.1-8B +tags: +- generated_from_trainer +model-index: +- name: workspace/axolotl/dolphin-2.9.4-llama3.1-8b + results: [] + +--- + +![](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ) + +# QuantFactory/dolphin-2.9.4-llama3.1-8b-GGUF +This is quantized version of [cognitivecomputations/dolphin-2.9.4-llama3.1-8b](https://huggingface.co/cognitivecomputations/dolphin-2.9.4-llama3.1-8b) created using llama.cpp + +# Original Model Card + + +# warning - it's not working yet, recommend hold off on downloading + +
Evals + +``` +hf (pretrained=/workspace/axolotl/dolphin-2.9.4-llama3.1-8b-hf,dtype=bfloat16), gen_kwargs: (None), limit: None, num_fewshot: None, batch_size: auto (4) +| Tasks |Version|Filter|n-shot| Metric | |Value | |Stderr| +|-----------------------------------------------------------|-------|------|-----:|-----------------------|---|-----:|---|------| +|leaderboard |N/A |none | 0|acc |↑ |0.2926|± |0.0041| +| | |none | 0|acc_norm |↑ |0.4513|± |0.0053| +| | |none | 0|exact_match |↑ |0.0982|± |0.0079| +| | |none | 0|inst_level_loose_acc |↑ |0.3825|± |N/A | +| | |none | 0|inst_level_strict_acc |↑ |0.3597|± |N/A | +| | |none | 0|prompt_level_loose_acc |↑ |0.2421|± |0.0184| +| | |none | 0|prompt_level_strict_acc|↑ |0.2181|± |0.0178| +| - leaderboard_bbh |N/A |none | 3|acc_norm |↑ |0.4931|± |0.0061| +| - leaderboard_bbh_boolean_expressions | 0|none | 3|acc_norm |↑ |0.8000|± |0.0253| +| - leaderboard_bbh_causal_judgement | 0|none | 3|acc_norm |↑ |0.5615|± |0.0364| +| - leaderboard_bbh_date_understanding | 0|none | 3|acc_norm |↑ |0.4520|± |0.0315| +| - leaderboard_bbh_disambiguation_qa | 0|none | 3|acc_norm |↑ |0.6640|± |0.0299| +| - leaderboard_bbh_formal_fallacies | 0|none | 3|acc_norm |↑ |0.5600|± |0.0315| +| - leaderboard_bbh_geometric_shapes | 0|none | 3|acc_norm |↑ |0.3640|± |0.0305| +| - leaderboard_bbh_hyperbaton | 0|none | 3|acc_norm |↑ |0.6320|± |0.0306| +| - leaderboard_bbh_logical_deduction_five_objects | 0|none | 3|acc_norm |↑ |0.4600|± |0.0316| +| - leaderboard_bbh_logical_deduction_seven_objects | 0|none | 3|acc_norm |↑ |0.4360|± |0.0314| +| - leaderboard_bbh_logical_deduction_three_objects | 0|none | 3|acc_norm |↑ |0.6160|± |0.0308| +| - leaderboard_bbh_movie_recommendation | 0|none | 3|acc_norm |↑ |0.7880|± |0.0259| +| - leaderboard_bbh_navigate | 0|none | 3|acc_norm |↑ |0.5200|± |0.0317| +| - leaderboard_bbh_object_counting | 0|none | 3|acc_norm |↑ |0.4520|± |0.0315| +| - leaderboard_bbh_penguins_in_a_table | 0|none | 3|acc_norm |↑ |0.5205|± |0.0415| +| - leaderboard_bbh_reasoning_about_colored_objects | 0|none | 3|acc_norm |↑ |0.5120|± |0.0317| +| - leaderboard_bbh_ruin_names | 0|none | 3|acc_norm |↑ |0.6320|± |0.0306| +| - leaderboard_bbh_salient_translation_error_detection | 0|none | 3|acc_norm |↑ |0.4320|± |0.0314| +| - leaderboard_bbh_snarks | 0|none | 3|acc_norm |↑ |0.5843|± |0.0370| +| - leaderboard_bbh_sports_understanding | 0|none | 3|acc_norm |↑ |0.7040|± |0.0289| +| - leaderboard_bbh_temporal_sequences | 0|none | 3|acc_norm |↑ |0.1440|± |0.0222| +| - leaderboard_bbh_tracking_shuffled_objects_five_objects | 0|none | 3|acc_norm |↑ |0.1560|± |0.0230| +| - leaderboard_bbh_tracking_shuffled_objects_seven_objects| 0|none | 3|acc_norm |↑ |0.1320|± |0.0215| +| - leaderboard_bbh_tracking_shuffled_objects_three_objects| 0|none | 3|acc_norm |↑ |0.2840|± |0.0286| +| - leaderboard_bbh_web_of_lies | 0|none | 3|acc_norm |↑ |0.4840|± |0.0317| +| - leaderboard_gpqa |N/A |none | 0|acc_norm |↑ |0.2903|± |0.0132| +| - leaderboard_gpqa_diamond | 1|none | 0|acc_norm |↑ |0.2980|± |0.0326| +| - leaderboard_gpqa_extended | 1|none | 0|acc_norm |↑ |0.2839|± |0.0193| +| - leaderboard_gpqa_main | 1|none | 0|acc_norm |↑ |0.2946|± |0.0216| +| - leaderboard_ifeval | 2|none | 0|inst_level_loose_acc |↑ |0.3825|± |N/A | +| | |none | 0|inst_level_strict_acc |↑ |0.3597|± |N/A | +| | |none | 0|prompt_level_loose_acc |↑ |0.2421|± |0.0184| +| | |none | 0|prompt_level_strict_acc|↑ |0.2181|± |0.0178| +| - leaderboard_math_algebra_hard | 1|none | 4|exact_match |↑ |0.1596|± |0.0209| +| - leaderboard_math_counting_and_prob_hard | 1|none | 4|exact_match |↑ |0.0488|± |0.0195| +| - leaderboard_math_geometry_hard | 1|none | 4|exact_match |↑ |0.0530|± |0.0196| +| - leaderboard_math_hard |N/A |none | 4|exact_match |↑ |0.0982|± |0.0079| +| - leaderboard_math_intermediate_algebra_hard | 1|none | 4|exact_match |↑ |0.0143|± |0.0071| +| - leaderboard_math_num_theory_hard | 1|none | 4|exact_match |↑ |0.0455|± |0.0168| +| - leaderboard_math_prealgebra_hard | 1|none | 4|exact_match |↑ |0.2591|± |0.0316| +| - leaderboard_math_precalculus_hard | 1|none | 4|exact_match |↑ |0.0519|± |0.0192| +| - leaderboard_mmlu_pro | 0.1|none | 5|acc |↑ |0.2926|± |0.0041| +| - leaderboard_musr |N/A |none | 0|acc_norm |↑ |0.3862|± |0.0173| +| - leaderboard_musr_murder_mysteries | 1|none | 0|acc_norm |↑ |0.5280|± |0.0316| +| - leaderboard_musr_object_placements | 1|none | 0|acc_norm |↑ |0.3594|± |0.0300| +| - leaderboard_musr_team_allocation | 1|none | 0|acc_norm |↑ |0.2720|± |0.0282| + +| Groups |Version|Filter|n-shot| Metric | |Value | |Stderr| +|------------------------|-------|------|-----:|-----------------------|---|-----:|---|------| +|leaderboard |N/A |none | 0|acc |↑ |0.2926|± |0.0041| +| | |none | 0|acc_norm |↑ |0.4513|± |0.0053| +| | |none | 0|exact_match |↑ |0.0982|± |0.0079| +| | |none | 0|inst_level_loose_acc |↑ |0.3825|± |N/A | +| | |none | 0|inst_level_strict_acc |↑ |0.3597|± |N/A | +| | |none | 0|prompt_level_loose_acc |↑ |0.2421|± |0.0184| +| | |none | 0|prompt_level_strict_acc|↑ |0.2181|± |0.0178| +| - leaderboard_bbh |N/A |none | 3|acc_norm |↑ |0.4931|± |0.0061| +| - leaderboard_gpqa |N/A |none | 0|acc_norm |↑ |0.2903|± |0.0132| +| - leaderboard_math_hard|N/A |none | 4|exact_match |↑ |0.0982|± |0.0079| +| - leaderboard_musr |N/A |none | 0|acc_norm |↑ |0.3862|± |0.0173| +``` + +
+ +[Built with Axolotl](https://github.com/axolotl-ai-cloud/axolotl) +
See axolotl config + +axolotl version: `0.4.1` +```yaml +base_model: meta-llama/Meta-Llama-3.1-8B +model_type: LlamaForCausalLM +tokenizer_type: AutoTokenizer + +load_in_8bit: false +# load_in_4bit: true +strict: false + +datasets: + - path: /workspace/datasets/dolphin-2.9.4/dolphin201-sharegpt2.jsonl + type: sharegpt + conversation: chatml + +chat_template: chatml +# adapter: qlora +# lora_r: 128 +# lora_alpha: 16 +# lora_modules_to_save: [embed_tokens, lm_head] +# lora_dropout: 0.05 +# lora_target_linear: true + +unfrozen_parameters: +- input_layernorm +- model.norm +- post_attention_layernorm +- self_attn.rotary_emb +- ^lm_head.weight$ +- ^model.embed_tokens.weight$ +# mlp.down_proj layers +- model.layers.1.mlp.down_proj +- model.layers.0.mlp.down_proj +- model.layers.30.mlp.down_proj +- model.layers.2.mlp.down_proj +- model.layers.21.mlp.down_proj +- model.layers.22.mlp.down_proj +- model.layers.29.mlp.down_proj +- model.layers.5.mlp.down_proj +- model.layers.4.mlp.down_proj +- model.layers.20.mlp.down_proj +- model.layers.23.mlp.down_proj +- model.layers.19.mlp.down_proj +- model.layers.3.mlp.down_proj +- model.layers.17.mlp.down_proj +- model.layers.6.mlp.down_proj +- model.layers.31.mlp.down_proj +# mlp.up_proj layers +- model.layers.4.mlp.up_proj +- model.layers.3.mlp.up_proj +- model.layers.0.mlp.up_proj +- model.layers.5.mlp.up_proj +- model.layers.7.mlp.up_proj +- model.layers.6.mlp.up_proj +- model.layers.2.mlp.up_proj +- model.layers.1.mlp.up_proj +- model.layers.8.mlp.up_proj +- model.layers.12.mlp.up_proj +- model.layers.14.mlp.up_proj +- model.layers.9.mlp.up_proj +- model.layers.15.mlp.up_proj +- model.layers.17.mlp.up_proj +- model.layers.13.mlp.up_proj +- model.layers.19.mlp.up_proj +# self_attn.k_proj layers +- model.layers.29.self_attn.k_proj +- model.layers.25.self_attn.k_proj +- model.layers.23.self_attn.k_proj +- model.layers.28.self_attn.k_proj +- model.layers.21.self_attn.k_proj +- model.layers.19.self_attn.k_proj +- model.layers.22.self_attn.k_proj +- model.layers.20.self_attn.k_proj +- model.layers.24.self_attn.k_proj +- model.layers.31.self_attn.k_proj +- model.layers.27.self_attn.k_proj +- model.layers.26.self_attn.k_proj +- model.layers.17.self_attn.k_proj +- model.layers.11.self_attn.k_proj +- model.layers.18.self_attn.k_proj +- model.layers.14.self_attn.k_proj +# self_attn.o_proj layers +- model.layers.14.self_attn.o_proj +- model.layers.7.self_attn.o_proj +- model.layers.5.self_attn.o_proj +- model.layers.11.self_attn.o_proj +- model.layers.6.self_attn.o_proj +- model.layers.24.self_attn.o_proj +- model.layers.9.self_attn.o_proj +- model.layers.13.self_attn.o_proj +- model.layers.10.self_attn.o_proj +- model.layers.12.self_attn.o_proj +- model.layers.8.self_attn.o_proj +- model.layers.25.self_attn.o_proj +- model.layers.21.self_attn.o_proj +- model.layers.23.self_attn.o_proj +- model.layers.15.self_attn.o_proj +- model.layers.16.self_attn.o_proj +# self_attn.q_proj layers +- model.layers.8.self_attn.q_proj +- model.layers.13.self_attn.q_proj +- model.layers.9.self_attn.q_proj +- model.layers.14.self_attn.q_proj +- model.layers.10.self_attn.q_proj +- model.layers.11.self_attn.q_proj +- model.layers.0.self_attn.q_proj +- model.layers.15.self_attn.q_proj +- model.layers.1.self_attn.q_proj +- model.layers.6.self_attn.q_proj +- model.layers.5.self_attn.q_proj +- model.layers.7.self_attn.q_proj +- model.layers.12.self_attn.q_proj +- model.layers.16.self_attn.q_proj +- model.layers.17.self_attn.q_proj +- model.layers.26.self_attn.q_proj +# self_attn.v_proj layers +- model.layers.26.self_attn.v_proj +- model.layers.17.self_attn.v_proj +- model.layers.3.self_attn.v_proj +- model.layers.28.self_attn.v_proj +- model.layers.29.self_attn.v_proj +- model.layers.21.self_attn.v_proj +- model.layers.15.self_attn.v_proj +- model.layers.16.self_attn.v_proj +- model.layers.20.self_attn.v_proj +- model.layers.25.self_attn.v_proj +- model.layers.6.self_attn.v_proj +- model.layers.23.self_attn.v_proj +- model.layers.4.self_attn.v_proj +- model.layers.1.self_attn.v_proj +- model.layers.22.self_attn.v_proj +- model.layers.14.self_attn.v_proj +# mlp.gate_proj layers +- model.layers.1.mlp.gate_proj +- model.layers.2.mlp.gate_proj +- model.layers.3.mlp.gate_proj +- model.layers.4.mlp.gate_proj +- model.layers.0.mlp.gate_proj +- model.layers.25.mlp.gate_proj +- model.layers.26.mlp.gate_proj +- model.layers.5.mlp.gate_proj +- model.layers.24.mlp.gate_proj +- model.layers.28.mlp.gate_proj +- model.layers.23.mlp.gate_proj +- model.layers.27.mlp.gate_proj +- model.layers.21.mlp.gate_proj +- model.layers.22.mlp.gate_proj +- model.layers.29.mlp.gate_proj +- model.layers.20.mlp.gate_proj + + + + +dataset_prepared_path: /workspace/axolotl/dolph-2.9.4-nemo-prepared +val_set_size: 0.01 +output_dir: /workspace/axolotl/dolphin-2.9.4-llama3.1-8b + +sequence_len: 8192 +sample_packing: true +pad_to_sequence_len: true + +wandb_project: dolphin-2.9.4-llama3.1-8b +wandb_watch: +wandb_run_id: +wandb_log_model: + +gradient_accumulation_steps: 16 +micro_batch_size: 2 +num_epochs: 3 +optimizer: adamw_torch +lr_scheduler: cosine +learning_rate: 5e-6 +train_on_inputs: false +group_by_length: false +bf16: auto +fp16: +tf32: + +gradient_checkpointing: true +gradient_checkpointing_kwargs: + use_reentrant: false +early_stopping_patience: +resume_from_checkpoint: +logging_steps: 1 +xformers_attention: +flash_attention: true + +warmup_steps: 100 +# evals_per_epoch: 4 +eval_table_size: +saves_per_epoch: 1 +save_total_limit: 2 +save_steps: +debug: +deepspeed: deepspeed_configs/zero3_bf16.json +weight_decay: 0.1 +special_tokens: + eos_token: "<|im_end|>" + bos_token: "<|begin_of_text|>" + pad_token: "<|finetune_right_pad_id|>" +tokens: + - "<|im_start|>" + + +# fsdp: +# - full_shard +# - auto_wrap +# fsdp_config: +# fsdp_limit_all_gathers: true +# fsdp_sync_module_states: true +# fsdp_offload_params: true +# fsdp_use_orig_params: false +# fsdp_cpu_ram_efficient_loading: true +# fsdp_transformer_layer_cls_to_wrap: MixtralSparseMoeBlock +# fsdp_state_dict_type: FULL_STATE_DICT +# fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP +# fsdp_sharding_strategy: FULL_SHARD +# fsdp_forward_prefetch: false +# fsdp_backward_prefetch: BACKWARD_PRE +``` + +

+ +# workspace/axolotl/dolphin-2.9.4-llama3.1-8b + +This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the None dataset. +It achieves the following results on the evaluation set: +- Loss: 0.5655 + +## Model description + +More information needed + +## Intended uses & limitations + +More information needed + +## Training and evaluation data + +More information needed + +## Training procedure + +### Training hyperparameters + +The following hyperparameters were used during training: +- learning_rate: 5e-06 +- train_batch_size: 2 +- eval_batch_size: 2 +- seed: 42 +- distributed_type: multi-GPU +- num_devices: 8 +- gradient_accumulation_steps: 16 +- total_train_batch_size: 256 +- total_eval_batch_size: 16 +- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 +- lr_scheduler_type: cosine +- lr_scheduler_warmup_steps: 100 +- num_epochs: 3 + +### Training results + +| Training Loss | Epoch | Step | Validation Loss | +|:-------------:|:------:|:----:|:---------------:| +| 0.5837 | 1.0180 | 1161 | 0.5814 | +| 0.5525 | 2.0179 | 2322 | 0.5671 | +| 0.5514 | 2.9624 | 3420 | 0.5655 | + + +### Framework versions + +- Transformers 4.44.0.dev0 +- Pytorch 2.4.0+cu121 +- Datasets 2.19.1 +- Tokenizers 0.19.1 + diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..9e26dfe --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{} \ No newline at end of file diff --git a/dolphin-2.9.4-llama3.1-8b.Q2_K.gguf b/dolphin-2.9.4-llama3.1-8b.Q2_K.gguf new file mode 100644 index 0000000..2c2be43 --- /dev/null +++ b/dolphin-2.9.4-llama3.1-8b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28aaa0ec782e4fb345b48c75662bb6cbb676b8e7dc896e0f8dbf9a85987e5501 +size 3179141376 diff --git a/dolphin-2.9.4-llama3.1-8b.Q3_K_L.gguf b/dolphin-2.9.4-llama3.1-8b.Q3_K_L.gguf new file mode 100644 index 0000000..17d91fa --- /dev/null +++ b/dolphin-2.9.4-llama3.1-8b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73d7b658247ef378ce5bd53078818afb9c3cc5e977fc479985c48c9ded0bd078 +size 4321967168 diff --git a/dolphin-2.9.4-llama3.1-8b.Q3_K_M.gguf b/dolphin-2.9.4-llama3.1-8b.Q3_K_M.gguf new file mode 100644 index 0000000..59f1216 --- /dev/null +++ b/dolphin-2.9.4-llama3.1-8b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60965d4eb18f68ad3c460b1d625f292d1c709540cdf5bd477648699e1c28e997 +size 4018928704 diff --git a/dolphin-2.9.4-llama3.1-8b.Q3_K_S.gguf b/dolphin-2.9.4-llama3.1-8b.Q3_K_S.gguf new file mode 100644 index 0000000..6712842 --- /dev/null +++ b/dolphin-2.9.4-llama3.1-8b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:948d908d8d36b1361dc565462017c735f300ffc1f49a58dd535cd7c764dbe819 +size 3664510016 diff --git a/dolphin-2.9.4-llama3.1-8b.Q4_0.gguf b/dolphin-2.9.4-llama3.1-8b.Q4_0.gguf new file mode 100644 index 0000000..56359d9 --- /dev/null +++ b/dolphin-2.9.4-llama3.1-8b.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15f4922de0ff8773ec5d9059a2e3bc2e51595474a2a8ba35472efab67cb0df45 +size 4661223552 diff --git a/dolphin-2.9.4-llama3.1-8b.Q4_1.gguf b/dolphin-2.9.4-llama3.1-8b.Q4_1.gguf new file mode 100644 index 0000000..ab8f381 --- /dev/null +++ b/dolphin-2.9.4-llama3.1-8b.Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c9ec8555bc8387fd694695ab3b55a03f514215f433de021c2dad36f671e3cd9 +size 5130265216 diff --git a/dolphin-2.9.4-llama3.1-8b.Q4_K_M.gguf b/dolphin-2.9.4-llama3.1-8b.Q4_K_M.gguf new file mode 100644 index 0000000..a5b3d03 --- /dev/null +++ b/dolphin-2.9.4-llama3.1-8b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6963046fa6c64b763b5289b80647e304a4810df3b95334c16ba781192b73dba5 +size 4920746112 diff --git a/dolphin-2.9.4-llama3.1-8b.Q4_K_S.gguf b/dolphin-2.9.4-llama3.1-8b.Q4_K_S.gguf new file mode 100644 index 0000000..7d21621 --- /dev/null +++ b/dolphin-2.9.4-llama3.1-8b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a38853aff3f62e91007781b4aa3e5fd084fd957ad4b89c22f0d86f779e7cbc29 +size 4692680832 diff --git a/dolphin-2.9.4-llama3.1-8b.Q5_0.gguf b/dolphin-2.9.4-llama3.1-8b.Q5_0.gguf new file mode 100644 index 0000000..a5afb70 --- /dev/null +++ b/dolphin-2.9.4-llama3.1-8b.Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8b90c58197eb465a0eed38d23db51a0dc5fbde02021e3d9427fffef59535a7d +size 5599306880 diff --git a/dolphin-2.9.4-llama3.1-8b.Q5_1.gguf b/dolphin-2.9.4-llama3.1-8b.Q5_1.gguf new file mode 100644 index 0000000..5ffcb78 --- /dev/null +++ b/dolphin-2.9.4-llama3.1-8b.Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1d6459d8fd8c1fd118589297b554809cd93c11c0bc25cc9f2919ce4cff54766 +size 6068348544 diff --git a/dolphin-2.9.4-llama3.1-8b.Q5_K_M.gguf b/dolphin-2.9.4-llama3.1-8b.Q5_K_M.gguf new file mode 100644 index 0000000..b10bf96 --- /dev/null +++ b/dolphin-2.9.4-llama3.1-8b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4c8f31bd79b0280de7691131c8aed76519aca55673e66ef19e12d868f0b96b1 +size 5733000320 diff --git a/dolphin-2.9.4-llama3.1-8b.Q5_K_S.gguf b/dolphin-2.9.4-llama3.1-8b.Q5_K_S.gguf new file mode 100644 index 0000000..5849047 --- /dev/null +++ b/dolphin-2.9.4-llama3.1-8b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed6bd588daebe4d3d13474d797a5d24be4eb5356f1160ed8443f497be6ef646a +size 5599306880 diff --git a/dolphin-2.9.4-llama3.1-8b.Q6_K.gguf b/dolphin-2.9.4-llama3.1-8b.Q6_K.gguf new file mode 100644 index 0000000..c8cf82a --- /dev/null +++ b/dolphin-2.9.4-llama3.1-8b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c5c4cde375f2c53a590ae742bbe4afc9de04a8749f3b8a9bf57d9801cae8768 +size 6596020416 diff --git a/dolphin-2.9.4-llama3.1-8b.Q8_0.gguf b/dolphin-2.9.4-llama3.1-8b.Q8_0.gguf new file mode 100644 index 0000000..4ad2c6e --- /dev/null +++ b/dolphin-2.9.4-llama3.1-8b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ab3ad0e532b375e5cd9597011b2fd3682a09ca764621e056daa1deab271eb03 +size 8540788800