lucyknada commited on
Commit
d40d98a
1 Parent(s): b531768

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -11
README.md CHANGED
@@ -63,7 +63,7 @@ base_model: /workspace/models/Mistral-Small-Instruct-2409
63
  model_type: AutoModelForCausalLM
64
  tokenizer_type: AutoTokenizer
65
 
66
- hub_model_id: anthracite-core/magnum-v4-22b-r4
67
  hub_strategy: "all_checkpoints"
68
  push_dataset_to_hub:
69
  hf_use_auth_token: true
@@ -81,17 +81,17 @@ load_in_4bit: false
81
  strict: false
82
 
83
  datasets:
84
- - path: anthracite-core/c2_logs_32k_mistral-v3_v1.2_no_system
85
  type: custommistralv2v3
86
- - path: anthracite-core/kalo-opus-instruct-22k-no-refusal-no-system
87
  type: custommistralv2v3
88
- - path: anthracite-core/kalo-opus-instruct-3k-filtered-no-system
89
  type: custommistralv2v3
90
  - path: anthracite-org/nopm_claude_writing_fixed
91
  type: custommistralv2v3
92
- - path: anthracite-core/kalo_opus_misc_240827_no_system
93
  type: custommistralv2v3
94
- - path: anthracite-core/kalo_misc_part2_no_system
95
  type: custommistralv2v3
96
  #chat_template: mistral_v2v3
97
  shuffle_merged_datasets: true
@@ -159,12 +159,12 @@ We'd like to thank Recursal / Featherless for sponsoring the compute for this tr
159
  We would also like to thank all members of Anthracite who made this finetune possible.
160
 
161
  ## Datasets
162
- - [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)
163
- - [anthracite-core/kalo-opus-instruct-22k-no-refusal-no-system](https://huggingface.co/datasets/anthracite-core/kalo-opus-instruct-22k-no-refusal-no-system)
164
- - [anthracite-core/kalo-opus-instruct-3k-filtered-no-system](https://huggingface.co/datasets/anthracite-core/kalo-opus-instruct-3k-filtered-no-system)
165
  - [anthracite-org/nopm_claude_writing_fixed](https://huggingface.co/datasets/anthracite-org/nopm_claude_writing_fixed)
166
- - [anthracite-core/kalo_opus_misc_240827_no_system](https://huggingface.co/datasets/anthracite-core/kalo_opus_misc_240827_no_system)
167
- - [anthracite-core/kalo_misc_part2_no_system](https://huggingface.co/datasets/anthracite-core/kalo_misc_part2_no_system)
168
 
169
  ## Training
170
  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.
 
63
  model_type: AutoModelForCausalLM
64
  tokenizer_type: AutoTokenizer
65
 
66
+ hub_model_id: anthracite-org/magnum-v4-22b-r4
67
  hub_strategy: "all_checkpoints"
68
  push_dataset_to_hub:
69
  hf_use_auth_token: true
 
81
  strict: false
82
 
83
  datasets:
84
+ - path: anthracite-org/c2_logs_32k_mistral-v3_v1.2_no_system
85
  type: custommistralv2v3
86
+ - path: anthracite-org/kalo-opus-instruct-22k-no-refusal-no-system
87
  type: custommistralv2v3
88
+ - path: anthracite-org/kalo-opus-instruct-3k-filtered-no-system
89
  type: custommistralv2v3
90
  - path: anthracite-org/nopm_claude_writing_fixed
91
  type: custommistralv2v3
92
+ - path: anthracite-org/kalo_opus_misc_240827_no_system
93
  type: custommistralv2v3
94
+ - path: anthracite-org/kalo_misc_part2_no_system
95
  type: custommistralv2v3
96
  #chat_template: mistral_v2v3
97
  shuffle_merged_datasets: true
 
159
  We would also like to thank all members of Anthracite who made this finetune possible.
160
 
161
  ## Datasets
162
+ - [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)
163
+ - [anthracite-org/kalo-opus-instruct-22k-no-refusal-no-system](https://huggingface.co/datasets/anthracite-org/kalo-opus-instruct-22k-no-refusal-no-system)
164
+ - [anthracite-org/kalo-opus-instruct-3k-filtered-no-system](https://huggingface.co/datasets/anthracite-org/kalo-opus-instruct-3k-filtered-no-system)
165
  - [anthracite-org/nopm_claude_writing_fixed](https://huggingface.co/datasets/anthracite-org/nopm_claude_writing_fixed)
166
+ - [anthracite-org/kalo_opus_misc_240827_no_system](https://huggingface.co/datasets/anthracite-org/kalo_opus_misc_240827_no_system)
167
+ - [anthracite-org/kalo_misc_part2_no_system](https://huggingface.co/datasets/anthracite-org/kalo_misc_part2_no_system)
168
 
169
  ## Training
170
  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.