This model was trained with
Merlina
. Save the JSON below to
data/configs/<name>.json
(or import it via the
Load Configuration
dialog) to reproduce the exact training setup. Credentials are not included — Merlina will use your own
HF_TOKEN
and
WANDB_API_KEY
from
.env
or the form.
{"_metadata":{"name":"Hemlock-Qwopus3.5-9B-Coder","description":"Training configuration shared from a Merlina-trained model.","tags":[],"schema":"merlina/training-config","schema_version":1,"merlina_version":"2.0.1"},"base_model":"Jackrong/Qwopus3.5-9B-Coder","output_name":"Hemlock-Qwopus3.5-9B-Coder","use_lora":true,"lora_r":256,"lora_alpha":256,"lora_dropout":0.05,"target_modules":["k_proj","o_proj","q_proj","v_proj","down_proj","gate_proj","up_proj"],"modules_to_save":[],"lora_task_type":"CAUSAL_LM","learning_rate":0.0002,"num_epochs":2,"batch_size":2,"gradient_accumulation_steps":8,"max_length":4096,"max_prompt_length":1024,"model_type":"auto","training_mode":"sft","beta":0.1,"label_smoothing":0.0,"gamma":0.5,"vision_model_id":null,"stage":null,"unfreeze_vision_top_n":null,"image_token_id":null,"min_pixels":null,"max_pixels":null,"image_column":null,"caption_column":null,"instruction":null,"streaming":null,"model_name":null,"image_resolution":1024,"lora_rank":32,"lora_target_modules":null,"lora_use_dora":false,"mid_training_samples":true,"dataset_jsonl_path":null,"dataset_name":null,"dataset_split":null,"sample_prompts":null,"sample_num_steps":null,"dataset":{"source":{"source_type":"huggingface","repo_id":"hemlang/Hemlock2-DPO","split":"train","file_path":null,"file_format":null,"dataset_id":null,"streaming":false,"streaming_batch_size":10000,"column_mapping":null},"additional_sources":[{"source_type":"huggingface","repo_id":"hemlang/hemlock-formulary-SFT","split":"train","file_path":null,"file_format":null,"dataset_id":null,"streaming":false,"streaming_batch_size":10000,"column_mapping":{"instruction":"prompt","output":"chosen"}},{"source_type":"huggingface","repo_id":"hemlang/hemlock-codex-SFT","split":"train","file_path":null,"file_format":null,"dataset_id":null,"streaming":false,"streaming_batch_size":10000,"column_mapping":{"instruction":"prompt","output":"chosen"}}],"format":{"format_type":"tokenizer","custom_templates":null,"enable_thinking":true},"model_name":"Jackrong/Qwopus3.5-9B-Coder","column_mapping":{"prompt":"prompt","chosen":"chosen","rejected":"rejected"},"convert_messages_format":true,"deduplicate":false,"dedupe_strategy":"prompt_chosen","test_size":0.01,"max_samples":null,"system_prompt":null,"system_prompt_mode":"fill_empty","training_mode":"sft"},"seed":42,"max_grad_norm":1.0,"warmup_ratio":0.05,"eval_steps":0.2,"use_4bit":true,"use_wandb":true,"push_to_hub":true,"merge_lora_before_upload":true,"hf_hub_private":true,"export_gguf":false,"gguf_quant_types":["Q4_K_M"],"keep_gguf_fp16":false,"shuffle_dataset":true,"weight_decay":0.01,"lr_scheduler_type":"cosine","gradient_checkpointing":true,"logging_steps":1,"optimizer_type":"paged_adamw_8bit","adam_beta1":0.9,"adam_beta2":0.999,"adam_epsilon":1e-08,"adafactor_relative_step":false,"adafactor_scale_parameter":false,"adafactor_warmup_init":false,"adafactor_decay_rate":-0.8,"adafactor_beta1":null,"adafactor_clip_threshold":1.0,"attn_implementation":"sdpa","use_liger":true,"torch_compile":false,"neftune_alpha":null,"eval_on_start":false,"gpu_ids":null,"multi_gpu_strategy":"auto","wandb_project":null,"wandb_run_name":null,"wandb_tags":null,"wandb_notes":null}
Runs of nbeerbower Hemlock-Qwopus3.5-9B-Coder on huggingface.co
13
Total runs
0
24-hour runs
5
3-day runs
4
7-day runs
1
30-day runs
More Information About Hemlock-Qwopus3.5-9B-Coder huggingface.co Model
Hemlock-Qwopus3.5-9B-Coder huggingface.co
Hemlock-Qwopus3.5-9B-Coder huggingface.co is an AI model on huggingface.co that provides Hemlock-Qwopus3.5-9B-Coder's model effect (), which can be used instantly with this nbeerbower Hemlock-Qwopus3.5-9B-Coder model. huggingface.co supports a free trial of the Hemlock-Qwopus3.5-9B-Coder model, and also provides paid use of the Hemlock-Qwopus3.5-9B-Coder. Support call Hemlock-Qwopus3.5-9B-Coder model through api, including Node.js, Python, http.
Hemlock-Qwopus3.5-9B-Coder huggingface.co is an online trial and call api platform, which integrates Hemlock-Qwopus3.5-9B-Coder's modeling effects, including api services, and provides a free online trial of Hemlock-Qwopus3.5-9B-Coder, you can try Hemlock-Qwopus3.5-9B-Coder online for free by clicking the link below.
nbeerbower Hemlock-Qwopus3.5-9B-Coder online free url in huggingface.co:
Hemlock-Qwopus3.5-9B-Coder is an open source model from GitHub that offers a free installation service, and any user can find Hemlock-Qwopus3.5-9B-Coder on GitHub to install. At the same time, huggingface.co provides the effect of Hemlock-Qwopus3.5-9B-Coder install, users can directly use Hemlock-Qwopus3.5-9B-Coder installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
Hemlock-Qwopus3.5-9B-Coder install url in huggingface.co: