lucyknada commited on
Commit
e5239e7
1 Parent(s): 51da752

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -11
README.md CHANGED
@@ -55,7 +55,7 @@ base_model: /workspace/models/Mistral-Small-Instruct-2409
55
  model_type: AutoModelForCausalLM
56
  tokenizer_type: AutoTokenizer
57
 
58
- hub_model_id: anthracite-core/magnum-v4-22b-r4
59
  hub_strategy: "all_checkpoints"
60
  push_dataset_to_hub:
61
  hf_use_auth_token: true
@@ -73,17 +73,17 @@ load_in_4bit: false
73
  strict: false
74
 
75
  datasets:
76
- - path: anthracite-core/c2_logs_32k_mistral-v3_v1.2_no_system
77
  type: custommistralv2v3
78
- - path: anthracite-core/kalo-opus-instruct-22k-no-refusal-no-system
79
  type: custommistralv2v3
80
- - path: anthracite-core/kalo-opus-instruct-3k-filtered-no-system
81
  type: custommistralv2v3
82
  - path: anthracite-org/nopm_claude_writing_fixed
83
  type: custommistralv2v3
84
- - path: anthracite-core/kalo_opus_misc_240827_no_system
85
  type: custommistralv2v3
86
- - path: anthracite-core/kalo_misc_part2_no_system
87
  type: custommistralv2v3
88
  #chat_template: mistral_v2v3
89
  shuffle_merged_datasets: true
@@ -151,12 +151,12 @@ We'd like to thank Recursal / Featherless for sponsoring the compute for this tr
151
  We would also like to thank all members of Anthracite who made this finetune possible.
152
 
153
  ## Datasets
154
- - [anthracite-core/c2_logs_32k_mistral-v3_v1.2_no_system](https://huggingface.co/datasets/anthracite-core/c2_logs_32k_mistral-v3_v1.2_no_system)
155
- - [anthracite-core/kalo-opus-instruct-22k-no-refusal-no-system](https://huggingface.co/datasets/anthracite-core/kalo-opus-instruct-22k-no-refusal-no-system)
156
- - [anthracite-core/kalo-opus-instruct-3k-filtered-no-system](https://huggingface.co/datasets/anthracite-core/kalo-opus-instruct-3k-filtered-no-system)
157
  - [anthracite-org/nopm_claude_writing_fixed](https://huggingface.co/datasets/anthracite-org/nopm_claude_writing_fixed)
158
- - [anthracite-core/kalo_opus_misc_240827_no_system](https://huggingface.co/datasets/anthracite-core/kalo_opus_misc_240827_no_system)
159
- - [anthracite-core/kalo_misc_part2_no_system](https://huggingface.co/datasets/anthracite-core/kalo_misc_part2_no_system)
160
 
161
  ## Training
162
  The training was done for 2 epochs. We used 8x[H100s](https://www.nvidia.com/en-us/data-center/h100/) GPUs graciously provided by [Recursal AI](https://recursal.ai/) / [Featherless AI](https://featherless.ai/) for the full-parameter fine-tuning of the model.
 
55
  model_type: AutoModelForCausalLM
56
  tokenizer_type: AutoTokenizer
57
 
58
+ hub_model_id: anthracite-org/magnum-v4-22b-r4
59
  hub_strategy: "all_checkpoints"
60
  push_dataset_to_hub:
61
  hf_use_auth_token: true
 
73
  strict: false
74
 
75
  datasets:
76
+ - path: anthracite-org/c2_logs_32k_mistral-v3_v1.2_no_system
77
  type: custommistralv2v3
78
+ - path: anthracite-org/kalo-opus-instruct-22k-no-refusal-no-system
79
  type: custommistralv2v3
80
+ - path: anthracite-org/kalo-opus-instruct-3k-filtered-no-system
81
  type: custommistralv2v3
82
  - path: anthracite-org/nopm_claude_writing_fixed
83
  type: custommistralv2v3
84
+ - path: anthracite-org/kalo_opus_misc_240827_no_system
85
  type: custommistralv2v3
86
+ - path: anthracite-org/kalo_misc_part2_no_system
87
  type: custommistralv2v3
88
  #chat_template: mistral_v2v3
89
  shuffle_merged_datasets: true
 
151
  We would also like to thank all members of Anthracite who made this finetune possible.
152
 
153
  ## Datasets
154
+ - [anthracite-org/c2_logs_32k_mistral-v3_v1.2_no_system](https://huggingface.co/datasets/anthracite-org/c2_logs_32k_mistral-v3_v1.2_no_system)
155
+ - [anthracite-org/kalo-opus-instruct-22k-no-refusal-no-system](https://huggingface.co/datasets/anthracite-org/kalo-opus-instruct-22k-no-refusal-no-system)
156
+ - [anthracite-org/kalo-opus-instruct-3k-filtered-no-system](https://huggingface.co/datasets/anthracite-org/kalo-opus-instruct-3k-filtered-no-system)
157
  - [anthracite-org/nopm_claude_writing_fixed](https://huggingface.co/datasets/anthracite-org/nopm_claude_writing_fixed)
158
+ - [anthracite-org/kalo_opus_misc_240827_no_system](https://huggingface.co/datasets/anthracite-org/kalo_opus_misc_240827_no_system)
159
+ - [anthracite-org/kalo_misc_part2_no_system](https://huggingface.co/datasets/anthracite-org/kalo_misc_part2_no_system)
160
 
161
  ## Training
162
  The training was done for 2 epochs. We used 8x[H100s](https://www.nvidia.com/en-us/data-center/h100/) GPUs graciously provided by [Recursal AI](https://recursal.ai/) / [Featherless AI](https://featherless.ai/) for the full-parameter fine-tuning of the model.